2026-06 papers

2026-11 2026-10 2026-09 2026-08 2026-07 2026-06 2026-05 dispatches about

2026-06 · 945 records

date	id	title	authors	venue	↑
2026-06-30	2606.30616	Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent	Lei Bai et al.	arXiv	104
2026-06-30	2606.26740	LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing	Xinyu Wang et al.	arXiv	82
2026-06-30	2606.28480	TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents	Shoufa Chen et al.	arXiv	48
2026-06-30	2606.28733	Agentic Abstention: Do Agents Know When to Stop Instead of Act?	Han Luo et al.	arXiv	47
2026-06-30	2502.16886	ReFreeKV: Towards Threshold-Free KV Cache Compression	Xuanfan Ni et al.	arXiv	42
2026-06-30	2606.30410	Beyond IID: How General Are Tabular Foundation Models, Really?	Lennart Purucker et al.	arXiv	41
2026-06-30	2606.24256	Trimming the Long-Tail of Visual World Modeling Evaluation	Bingxuan Li et al.	arXiv	31
2026-06-30	2606.24143	AsyncOPD: How Stale Can On-Policy Distillation Be?	Wonjun Kang et al.	arXiv	29
2026-06-30	2606.27828	Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning	Hohin Kwan et al.	arXiv	25
2026-06-30	2606.29445	Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction	Sunqi Fan et al.	arXiv	25
2026-06-30	2606.29537	OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks	Mengqi Yuan et al.	arXiv	24
2026-06-30	2606.30634	One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining	Philip Zmushko et al.	arXiv	22
2026-06-30	2606.30017	Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting	Xiaobiao Du et al.	arXiv	19
2026-06-30	2606.30251	TACO: Tool-Augmented Credit Optimization for Agentic Tool Use	Mingkuan Feng et al.	arXiv	19
2026-06-30	2606.30292	DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model	Daniyel Ayupov et al.	arXiv	15
2026-06-30	2606.29814	Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis	Shufan Li et al.	arXiv	14
2026-06-30	2606.29705	GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots	Sunqi Fan et al.	arXiv	14
2026-06-30	2606.29957	SWE-Together: Evaluating Coding Agents in Interactive User Sessions	Yifan Wu et al.	arXiv	13
2026-06-30	2606.25363	TheoremGraph: Bridging Formal and Informal Mathematics	Simon Kurgan et al.	arXiv	11
2026-06-30	2606.27339	SAM2Matting: Generalized Image and Video Matting	Ruiqi Shen et al.	arXiv	9
2026-06-30	2606.30308	The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction	Yuxi Wang et al.	arXiv	9
2026-06-30	2606.26016	MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation	Yang Chen et al.	arXiv	7
2026-06-30	2606.00097	RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets	Peter Pak et al.	arXiv	6
2026-06-30	2606.27282	How Good Can Linear Models Be for Time-Series Forecasting?	Lang Huang et al.	arXiv	6
2026-06-30	2606.29225	PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents	Seongjae Kang et al.	arXiv	6
2026-06-30	2606.29308	MirrorPPR: Exemplar-Based Portrait Photo Retouching	Zhihong Liu et al.	arXiv	5
2026-06-30	2606.25621	One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications	Szu-Wei Fu et al.	arXiv	5
2026-06-30	2606.30170	Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark	Matthias Blaschke et al.	arXiv	5
2026-06-30	2606.30045	Walking in the Implicit: Interactive World Exploration via Neural Scene Representation	Zhiqi Li et al.	arXiv	5
2026-06-30	2606.30084	One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding	Chen Liu et al.	arXiv	5
2026-06-30	2606.28186	Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction	Chenguang Wang et al.	arXiv	5
2026-06-30	2606.23885	Mind the Heads: Topological Representation Alignment for Multimodal LLMs	Davide Caffagni et al.	arXiv	4
2026-06-30	2606.27708	ZooClaw-FashionSigLIP2: Distilled Fine-tuning for Robust Fashion Retrieval	Siqiao Xue et al.	arXiv	4
2026-06-30	2606.23404	ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models	Jun Zhang et al.	arXiv	4
2026-06-30	2606.26938	Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE	Haoyou Deng et al.	arXiv	4
2026-06-30	2606.27409	Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement	Igor Itkin	arXiv	3
2026-06-30	2606.27755	Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?	Guoheng Sun et al.	arXiv	3
2026-06-30	2606.29600	One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models	Xiaohao Xu et al.	arXiv	3
2026-06-30	2606.29501	Learning Transferable Dynamics Priors from Action to World Modeling	Ze Huang et al.	arXiv	3
2026-06-30	2606.22473	Interleaved Speech Language Models Latently Work In Text	Talia Sternberg et al.	arXiv	3
2026-06-30	2606.29887	SafePyramid: A Hierarchical Benchmark for In-context Policy Guardrailing	Jiacheng Zhang et al.	arXiv	3
2026-06-30	2501.18916	LLM Program Optimization via Retrieval Augmented Search	Sagnik Anupam et al.	arXiv	2
2026-06-30	2606.28525	A Gravitational Interpretation of Fine-Tuning Reversion	Samuele Poppi et al.	arXiv	2
2026-06-30	2606.22749	RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation	Yuchuan Ding et al.	arXiv	2
2026-06-30	2606.30054	Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation	Chonghuinan Wang et al.	arXiv	2
2026-06-30	2606.29655	Geometric Reliability of Neural Population Codes: Sampling Calibration and Within-Session Nonstationarity	Prashant C. Raju	arXiv	2
2026-06-30	2606.29686	PoseShield: Neural Collision Fields for Human Self-Collision Resolution	Zhengyuan Li et al.	arXiv	2
2026-06-30	2606.25393	Large-Scale Tunnel Air-Ground Collaboration With FLISP: Fast LiDAR-IMU Synchronized Path Planner	Fenghe Guo et al.	arXiv
2026-06-29	2606.28128	PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation	Peiwen Zhang et al.	arXiv	54
2026-06-29	2606.27608	Qwen-Image-2.0-RL Technical Report	Yixian Xu et al.	arXiv	53
2026-06-29	2606.27378	Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs	Fahd Seddik et al.	arXiv	49
2026-06-29	2606.28133	Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots	Sijin Chen et al.	arXiv	39
2026-06-29	2606.17846	Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models	Haoqi Yuan et al.	arXiv	34
2026-06-29	2606.18112	Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System	Jiazhao Zhang et al.	arXiv	30
2026-06-29	2606.28276	SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation	Nadun Ranawaka et al.	arXiv	16
2026-06-29	2606.20905	Vesta: A Generalist Embodied Reasoning Model	Johan Bjorck et al.	arXiv	13
2026-06-29	2606.28187	GBC: Gradient-Based Connections for Optimizing Multi-Agent Systems	Xiaocheng Yang et al.	arXiv	13
2026-06-29	2606.28057	MultiHashFormer: Hash-based Generative Language Models	Huiyin Xue et al.	arXiv	12
2026-06-29	2511.07397	Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents	Vidya Srinivas et al.	arXiv	11
2026-06-29	2606.27974	ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering	ZhengXian Wu et al.	arXiv	10
2026-06-29	2606.28277	Towards Automating Scientific Review with Google's Paper Assistant Tool	Rajesh Jayaram et al.	arXiv	10
2026-06-29	2606.22873	SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning	SingGuard Team	arXiv	9
2026-06-29	2606.26015	The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar	Ilseyar Alimova et al.	arXiv	8
2026-06-29	2606.27595	Ko-WideSearch: A Korean Breadth-Search Benchmark for Exhaustive Set Enumeration by Web Agents	Minbyul Jeong	arXiv	8
2026-06-29	2606.24893	AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents	Zheyuan Zhang et al.	arXiv	7
2026-06-29	2606.18953	Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement	Kinam Kim et al.	arXiv	7
2026-06-29	2604.20920	Simplified Sparse Attention via Gist Tokens	Yuzhen Mao et al.	arXiv	6
2026-06-29	2606.27537	MemoBench: Benchmarking World Modeling in Dynamically Changing Environments	Haoyu Chen et al.	arXiv	5
2026-06-29	2606.27978	Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation	Jiayi Xu et al.	arXiv	5
2026-06-29	2606.27163	Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)	Ilia Larchenko	arXiv	5
2026-06-29	2606.27457	Cluster, Route, Escalate: Cascaded Framework for Cost-Aware LLM Serving	Yasmin Moslem et al.	arXiv	4
2026-06-29	2606.27771	NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning	Tianlin Pan et al.	arXiv	4
2026-06-29	2606.20970	CogniRoute: Learning to Route Social Evidence in Omni-Modal Models	Yifan Shen et al.	arXiv	3
2026-06-29	2606.25610	The Galaxy's Guide to the Tokenizer: A Benchmark for Scientific Foundation Models	Sogol Sanjaripour et al.	arXiv	3
2026-06-29	2606.26979	How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring	Zhihao Lin et al.	arXiv	2
2026-06-29	2606.26978	To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair	Zhihao Lin et al.	arXiv	1
2026-06-29	2606.26519	Boundary-Aware Context Grounding for A Low-Channel EEG Agent	Zhiyuan Xu et al.	arXiv
2026-06-26	2606.27377	DanceOPD: On-Policy Generative Field Distillation	Wei Zhou et al.	arXiv	82
2026-06-26	2606.26790	OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning	Shuo Yang et al.	arXiv	59
2026-06-26	2606.26300	The Verification Horizon: No Silver Bullet for Coding Agent Rewards	Binghai Wang et al.	arXiv	55
2026-06-26	2606.26907	Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation	Zekai Zhang et al.	arXiv	53
2026-06-26	2606.26025	In-Context World Modeling for Robotic Control	Siyin Wang et al.	arXiv	39
2026-06-26	2606.18394	JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting	Lanxiang Hu et al.	arXiv	36
2026-06-26	2606.27313	ViQ: Text-Aligned Visual Quantized Representations at Any Resolution	Xumin Yu et al.	arXiv	28
2026-06-26	2606.26217	Fast LeWorldModel	Yuntian Gao et al.	arXiv	28
2026-06-26	2606.14397	Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments	Mykola Vysotskyi et al.	arXiv	20
2026-06-26	2606.26027	Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It	Yupu Hao et al.	arXiv	19
2026-06-26	2606.24551	GUI vs. CLI: Execution Bottlenecks in Screen-Only and Skill-Mediated Computer-Use Agents	Xiao Zhou et al.	arXiv	17
2026-06-26	2606.21795	Discretizing Reward Models	Vijay Viswanathan et al.	arXiv	16
2026-06-26	2606.26080	Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents	Changdae Oh et al.	arXiv	13
2026-06-26	2606.27192	LISA: Likelihood Score Alignment for Visual-condition Controllable Generation	Yanghao Wang et al.	arXiv	13
2026-06-26	2606.26875	Information-Aware KV Cache Compression for Long Reasoning	Jushi Kai et al.	arXiv	12
2026-06-26	2606.26904	Confidence-Aware Tool Orchestration for Robust Video Understanding	Yangfan He et al.	arXiv	12
2026-06-26	2606.27364	PhysiFormer: Learning to Simulate Mechanics in World Space	Yiming Chen et al.	arXiv	12
2026-06-26	2606.16613	CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies	Issa Sugiura et al.	arXiv	9
2026-06-26	2606.27326	Hallucination in World Models is Predictable and Preventable	Nicklas Hansen et al.	arXiv	9
2026-06-26	2606.26299	COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami	Tom Zahavy et al.	arXiv	7
2026-06-26	2606.23835	ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation	Anindya Mondal et al.	arXiv	5
2026-06-26	2606.21959	OpenBioRQ: Unsolved Biomedical Research Questions for Agents	Minbyul Jeong	arXiv	5
2026-06-26	2606.27288	When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models	Josef Chen	arXiv	4
2026-06-26	2606.27277	EO-WM: A Physically Informed World Model for Probabilistic Earth Observation Forecasting	Junwei Luo et al.	arXiv	3
2026-06-26	2606.16517	How Post-Training Shapes Biological Reasoning Models	Lukas Fesser et al.	arXiv	3
2026-06-25	2606.25041	Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models	Lianghua Huang et al.	arXiv	123
2026-06-25	2606.24775	Are We Ready For An Agent-Native Memory System?	Wei Zhou et al.	arXiv	99
2026-06-25	2606.26058	DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation	Nan Chen et al.	arXiv	64
2026-06-25	2606.25763	ShutterMuse: Capture-Time Photography Guidance with MLLMs	Jiayu Li et al.	arXiv	44
2026-06-25	2606.25331	Improved Large Language Diffusion Models	Shen Nie et al.	arXiv	43
2026-06-25	2606.15932	Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence	Xuanle Zhao et al.	arXiv	36
2026-06-25	2606.26087	MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation	JoungBin Lee et al.	arXiv	35
2026-06-25	2606.25473	Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models	Kaiwen Zheng et al.	arXiv	27
2026-06-25	2606.25319	V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning	Haoxiang Sun et al.	arXiv	25
2026-06-25	2606.21661	UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating	Jiehui Huang et al.	arXiv	24
2026-06-25	2606.24937	The Hitchhiker's Guide to Agentic AI: From Foundations to Systems	Haggai Roitman	arXiv	22
2026-06-25	2606.25996	Autodata: An agentic data scientist to create high quality synthetic data	Ilia Kulikov et al.	arXiv	21
2026-06-25	2606.24849	IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation	Zixuan Li et al.	arXiv	19
2026-06-25	2606.18239	EBench: Elemental Diagnosis of Generalist Mobile Manipulation Policies	Ning Gao et al.	arXiv	17
2026-06-25	2606.22565	Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do	Zhuoran Jin et al.	arXiv	8
2026-06-25	2606.24033	RoPE-Aware Bit Allocation for KV-Cache Quantization	Fengfeng Liang et al.	arXiv	7
2026-06-25	2606.24484	Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods	Xingsong Ye et al.	arXiv	6
2026-06-25	2606.25182	What Intermediate Layers Know: Detecting Jailbreaks from Entropy Dynamics	Sofiia Nikolenko et al.	arXiv	5
2026-06-25	2606.26092	TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy	Hao Sun et al.	arXiv	5
2026-06-25	2606.14740	GridVQA-X: A Framework for Evaluating Multimodal Explainability Methods	Sujay Belsare et al.	arXiv	4
2026-06-25	2606.24457	Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matching	Junpeng Jing et al.	arXiv	4
2026-06-25	2606.21710	PrivacyAlign: Contextual Privacy Alignment for LLM Agents	Manveer Singh Tamber et al.	arXiv	4
2026-06-25	2606.25605	Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints	Fangzheng Li et al.	arXiv	4
2026-06-25	2606.24083	CAVEWOMAN: How Large Language Models Behave Under Linguistic Input and Output Compression	Morayo Danielle Adeyemi et al.	arXiv	4
2026-06-25	2606.25306	Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation	Atin Pothiraj et al.	arXiv	3
2026-06-25	2606.16316	RL-Index: Reinforcement Learning for Retrieval Index Reasoning	Yongjia Lei et al.	arXiv	3
2026-06-25	2606.20023	When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents	Kaiyue Yang et al.	arXiv	3
2026-06-25	2606.11445	Forecasting Future Behavior as a Learning Task	Mosh Levy et al.	arXiv	2
2026-06-25	2606.20196	Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation	Hyun-Kurl Jang et al.	arXiv	2
2026-06-25	2606.25013	Do Thinking Tokens Help with Safety?	Narutatsu Ri et al.	arXiv	1
2026-06-25	2606.22953	Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents	Aman Mehta et al.	arXiv	1
2026-06-25	2606.23104	ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation	Chen Lin et al.	arXiv	1
2026-06-25	2606.21215	Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach	Tzu-Chieh Wei et al.	arXiv
2026-06-24	2606.24597	Qwen-AgentWorld: Language World Models for General Agents	Yuxin Zuo et al.	arXiv	165
2026-06-24	2606.24530	NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?	Yuru Wang et al.	arXiv	65
2026-06-24	2606.24855	OpenThoughts-Agent: Data Recipes for Agentic Models	Negin Raoof et al.	arXiv	49
2026-06-24	2606.19930	MobileForge: Annotation-Free Adaptation for Mobile GUI Agents with Hierarchical Feedback-Guided Policy Optimization	Guangyi Liu et al.	arXiv	44
2026-06-24	2606.19926	MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management	Guangyi Liu et al.	arXiv	42
2026-06-24	2606.24876	FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation	Orest Kupyn et al.	arXiv	26
2026-06-24	2606.23449	AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction	Shanhui Zhao et al.	arXiv	25
2026-06-24	2606.23991	Critique of Agent Model	Eric Xing et al.	arXiv	23
2026-06-24	2602.09379	LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis	Shihao Xu et al.	arXiv	23
2026-06-24	2606.23679	Semantic Browsing: Controllable Diversity for Image Generation	Sara Dorfman et al.	arXiv	18
2026-06-24	2606.24428	Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience Learning	Shiding Zhu et al.	arXiv	15
2026-06-24	2606.24133	Holistic Data Scheduler for LLM Pre-training via Multi-Objective Reinforcement Learning	Chenhao Dang et al.	arXiv	12
2026-06-24	2606.24548	Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning	Jiayi Lei et al.	arXiv	11
2026-06-24	2606.24888	DiffusionBench: On Holistic Evaluation of Diffusion Transformers	Xingjian Leng et al.	arXiv	11
2026-06-24	2606.22875	FedOT: Ownership Verification and Leakage Tracing via Watermarks for Federated LDMs	Wenlong Cheng et al.	arXiv	10
2026-06-24	2606.24742	World Value Models for Robotic Manipulation	Zhihao Wang et al.	arXiv	8
2026-06-24	2606.24526	AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning	Honglin Guo et al.	arXiv	6
2026-06-24	2606.20092	EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies	Ganlin Yang et al.	arXiv	6
2026-06-24	2606.24667	DREAM: Dense Retrieval Embeddings via Autoregressive Modeling	Yixuan Tang et al.	arXiv	6
2026-06-24	2606.24112	ReMMD: Realistic Multilingual Multi-Image Agentic Verification for Multimodal Misinformation Detection	Chenhao Dang et al.	arXiv	5
2026-06-24	2606.23997	ChartWalker: Benchmarking the Cross-Chart RAG Task	Ning Tang et al.	arXiv	4
2026-06-24	2606.24595	MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery	Enze Ma et al.	arXiv	3
2026-06-24	2606.23543	VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct	Haoling Li et al.	arXiv	3
2026-06-24	2606.20027	QG-MIL: A Gated Transformer Aggregator for Domain-Agnostic Multiple Instance Learning in Medical Imaging	Luca Zedda et al.	arXiv	3
2026-06-24	2606.22197	Multi4D: High-Fidelity Dynamic Gaussian Splatting via Multi-Level Competitive Allocation	Rui Wang et al.	arXiv	2
2026-06-24	2606.24231	FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning	Xirui Li et al.	arXiv	2
2026-06-24	2606.24874	FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation	Haorui Ji et al.	arXiv	2
2026-06-24	2606.24884	InSight: Self-Guided Skill Acquisition via Steerable VLAs	Maggie Wang et al.	arXiv	1
2026-06-24	2606.12345	An Efficient Method for the Optimal Control of Microgrids Under Uncertainties using Local Reduction	Edoardo Scaccia et al.	arXiv
2026-06-23	2606.23050	Unlimited OCR Works	Youyang Yin et al.	arXiv	103
2026-06-23	2606.22388	PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool Ecosystems	Jiayu Liu et al.	arXiv	92
2026-06-23	2606.23654	EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions	Jincheng Zhong et al.	arXiv	81
2026-06-23	2606.20945	Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention	Vishesh Tripathi et al.	arXiv	66
2026-06-23	2606.20781	World Action Models: A Survey	Qiuhong Shen et al.	arXiv	59
2026-06-23	2606.22807	KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking	Xinping Zhao et al.	arXiv	50
2026-06-23	2606.22883	CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents	Zhanbo Hua et al.	arXiv	38
2026-06-23	2606.21649	EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory	Chang Nie et al.	arXiv	34
2026-06-23	2606.21906	Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding	Xuanming Zhang et al.	arXiv	27
2026-06-23	2606.22138	BioMatrix: Towards a Comprehensive Biological Foundation Model Spanning the Modality Matrix of Sequences, Structures, and Language	Qizhi Pei et al.	arXiv	26
2026-06-23	2606.19409	OpenRath: Session-Centered Runtime State for Agent Systems	Fukang Wen et al.	arXiv	24
2026-06-23	2606.21337	DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams	Cong Wan et al.	arXiv	21
2026-06-23	2606.20636	SkillHarness: Harnessing Safe Skills for Computer-Use Agents	Yurun Chen et al.	arXiv	20
2026-06-23	2606.23525	Self-Compacting Language Model Agents	Tianjian Li et al.	arXiv	19
2026-06-23	2606.23049	Training Open Models for Agentic Phone Use	Zhengyang Tang et al.	arXiv	18
2026-06-23	2606.23321	Tmax: A simple recipe for terminal agents	Hamish Ivison et al.	arXiv	17
2026-06-23	2606.20097	HydraHead: From Head-Level Functional Heterogeneity to Specialized Attention Hybridization	Zhentao Tan et al.	arXiv	17
2026-06-23	2606.18648	Deep Research in Physical Sciences: A Multi-Agent Framework and Comprehensive Benchmark	Yigeng Jiang et al.	arXiv	16
2026-06-23	2606.11897	Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills	Shi Liu et al.	arXiv	15
2026-06-23	2606.23085	Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents	Haoran Zhang et al.	arXiv	14
2026-06-23	2606.12871	DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks	Jingxuan Han et al.	arXiv	14
2026-06-23	2606.21139	PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning	Youngjoon Jeong et al.	arXiv	13
2026-06-23	2606.18844	Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation	Zhilin Huang et al.	arXiv	13
2026-06-23	2606.23610	Vera: A Layered Diffusion Model for Content-Preserving Video Editing	Hongkai Zheng et al.	arXiv	12
2026-06-23	2606.23670	Tapered Language Models	Reza Bayat et al.	arXiv	11
2026-06-23	2606.20002	Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning	Yanxi Chen et al.	arXiv	11
2026-06-23	2606.11075	Exploring the Design Space of Reward Backpropagation for Flow Matching	Ruoyu Wang et al.	arXiv	11
2026-06-23	2606.18831	Beyond Reward Engineering: A Data Recipe for Long-Context Reinforcement Learning	Xiaoyue Xu et al.	arXiv	8
2026-06-23	2606.21638	Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs	Charbel El Feghali et al.	arXiv	8
2026-06-23	2606.21627	Counsel: A Meta-Evaluation Dataset for Agentic Tasks	Sashank Pisupati et al.	arXiv	8
2026-06-23	2606.23608	Causal Discovery in the Era of Agents	Yujia Zheng et al.	arXiv	8
2026-06-23	2606.23557	Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views	Jiho Choi et al.	arXiv	7
2026-06-23	2606.23267	Safe Few-Step Generation via Velocity Editing	Yujin Choi et al.	arXiv	7
2026-06-23	2606.23688	Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild	Yehonathan Litman et al.	arXiv	6
2026-06-23	2606.23514	Arbor: Explicit Geometric Conditioning for Controllable 3D Asset Generation	Jan-Niklas Dihlmann et al.	arXiv	5
2026-06-23	2606.23489	MeshFlow: Mesh Generation with Equivariant Flow Matching	Qi Sun et al.	arXiv	5
2026-06-23	2606.22540	PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models	Xianghui Wang et al.	arXiv	5
2026-06-23	2606.21777	CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks	Ashwin Vinod et al.	arXiv	5
2026-06-23	2606.19603	Comparing Linear Probes with Mahalanobis Cosine Similarity	Zhuofan Josh Ying et al.	arXiv	4
2026-06-23	2606.20891	Go-with-the-Track: Video Compositing and Motion Control with Point Tracking	Koichi Namekata et al.	arXiv	4
2026-06-23	2606.20980	Robusto-2: Benchmarking Humans & VLMs for Autonomous Driving in Lima & New York City	Adrian Cespedes et al.	arXiv	4
2026-06-23	2606.16246	Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining	Michael K. Chen et al.	arXiv	4
2026-06-23	2606.14971	FastMix: Fast Data Mixture Optimization via Gradient Descent	Haoru Tan et al.	arXiv	4
2026-06-23	2606.19750	Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models	Darrien McKenzie et al.	arXiv	4
2026-06-23	2606.21884	A Verifiable Search Is Not a Learnable Chain-of-Thought	Harsh Patel	arXiv	3
2026-06-23	2606.22778	HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions	Yuichi Tateno	arXiv	3
2026-06-23	2606.23503	UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation	Yohann Perron et al.	arXiv	3
2026-06-23	2606.22936	When Agents Commit Too Soon: Diagnosing Premature Commitment in LLM Agents	Aman Mehta	arXiv	2
2026-06-23	2606.22708	Libretto: Giving LLM Agents a Sense of Musical Structure	Yichen Xu	arXiv	2
2026-06-23	2606.23189	Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?	Anmol Goel et al.	arXiv	2
2026-06-23	2606.21670	Improving Text-to-Music Generation with Human Preference Rewards	Yonghyun Kim et al.	arXiv	2
2026-06-23	2606.23496	TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization	Matan Ben-Tov et al.	arXiv	1
2026-06-23	2606.23152	ShotcreteDepth: A Bi-modal Dataset for Robust Robotic Depth Perception in Shotcrete Construction Environments	Jakub Gregorek et al.	arXiv	1
2026-06-23	2606.21171	An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game	Jan Wunderlich et al.	arXiv	1
2026-06-23	2505.23878	AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining	Jing Ma et al.	arXiv	1
2026-06-23	2606.20886	Toward Parking Spot Occupancy Recognition: A Self-Supervised Approach	Luan Marko Kujavski et al.	arXiv
2026-06-22	2606.19534	PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models	Yueyi Sun et al.	arXiv	63
2026-06-22	2606.17162	MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision	Ye Jin et al.	arXiv	34
2026-06-22	2606.18508	MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval	Amirhossein Abaskohi et al.	arXiv	21
2026-06-22	2606.18381	SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG	Amirhossein Abaskohi et al.	arXiv	19
2026-06-22	2606.18829	GateMem: Benchmarking Memory Governance in Multi-Principal Shared-Memory Agents	Zhe Ren et al.	arXiv	18
2026-06-22	2606.16700	Multi-Turn Reflective Masking Elicits Reasoning in Mask Diffusion Models	Yanming Zhang et al.	arXiv	14
2026-06-22	2606.19651	BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation	Max Van Puyvelde et al.	arXiv	10
2026-06-22	2606.15641	Distilling Examples into Task Instructions: Enhanced In-Context Learning for Real-World B2B Conversations	Guy Rotman et al.	arXiv	6
2026-06-22	2606.18847	WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents	Yehang Zhang et al.	arXiv	6
2026-06-22	2606.15659	SpatialAvatar-0: High-Quality 4D Head Avatar with Multi-Stage Reconstruction	Yiran Wang et al.	arXiv	5
2026-06-22	2606.20527	StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs	Shaghayegh Kolli et al.	arXiv	4
2026-06-22	2606.19827	When, Where, and How: Adaptive Binning for Tabular Self-Supervised Learning	Daehwan Kim et al.	arXiv	3
2026-06-22	2606.19468	Characterizing Narrative Content in Web-scale LLM Pretraining Data	Teagan Johnson et al.	arXiv	3
2026-06-22	2606.17480	GeneralVLA-2: Geometry-Aware Reconstruction and Governed Memory for Robot Planning	Haoyu Wang et al.	arXiv	3
2026-06-19	2606.19195	Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance	Kangsheng Duan et al.	arXiv	66
2026-06-19	2606.20517	Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages	Maria Ivanova et al.	arXiv	60
2026-06-19	2606.19419	Playful Agentic Robot Learning	Junyi Zhang et al.	arXiv	49
2026-06-19	2606.19704	Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents	Dhaval C. Patel et al.	arXiv	42
2026-06-19	2606.20515	S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence	Yalun Dai et al.	arXiv	41
2026-06-19	2606.15133	DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects	Tianshan Zhang et al.	arXiv	33
2026-06-19	2604.13416	DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis	Cheng-You Lu et al.	arXiv	33
2026-06-19	2606.20506	FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining	Jinghong Lan et al.	arXiv	26
2026-06-19	2606.19531	ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?	Yuyang Zhang et al.	arXiv	25
2026-06-19	2606.20404	FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows	Daniel Gilo et al.	arXiv	21
2026-06-19	2606.20563	JanusMesh: Fast and Zero-Shot 3D Visual Illusion Generation via Cross-Space Denoising	Siang-Ling Zhang et al.	arXiv	20
2026-06-19	2606.20545	Current World Models Lack a Persistent State Core	Jinpeng Lu et al.	arXiv	18
2026-06-19	2606.17053	Context-Aware RL for Agentic and Multimodal LLMs	Peiyang Xu et al.	arXiv	15
2026-06-19	2606.19980	ENPIRE: Agentic Robot Policy Self-Improvement in the Real World	Wenli Xiao et al.	arXiv	15
2026-06-19	2606.20521	HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining	Juncheng Ma et al.	arXiv	13
2026-06-19	2606.20083	Holo-World: Unified Camera, Object and Weather Control for Video World Model	Xiangchen Yin et al.	arXiv	11
2026-06-19	2606.20536	The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation	Nicolas Dufour et al.	arXiv	10
2026-06-19	2606.20381	Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 Recipe	Qian Zhao et al.	arXiv	9
2026-06-19	2606.19605	FAPO: Fully Autonomous Prompt Optimization of Multi-Step LLM Pipelines	Paul Kassianik et al.	arXiv	9
2026-06-19	2606.19334	Freeing the Law with LOCUS: A Local Ordinance Corpus for the United States	Denis Peskoff et al.	arXiv	8
2026-06-19	2606.16817	Understanding the Behaviors of Environment-aware Information Retrieval	Ruifeng Yuan et al.	arXiv	7
2026-06-19	2606.16122	Thinking with Visual Grounding	Junkai Zhang et al.	arXiv	7
2026-06-19	2606.19495	LooseControlVideo: Directorial Video Control using Spatial Blocking	Shariq Farooq Bhat et al.	arXiv	7
2026-06-19	2606.20529	LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents	Md Nayem Uddin et al.	arXiv	6
2026-06-19	2606.16429	Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation	Zhongzhu Zhou et al.	arXiv	4
2026-06-19	2606.19830	JAMER: Project-Level Code Framework Dataset and Benchmark on Professional Game Engines	Jianwen Sun et al.	arXiv	4
2026-06-19	2606.18021	LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI	Lalit Yadav et al.	arXiv	3
2026-06-19	2606.16827	No Resource, No Benchmarks, No Problem? Evaluating and Improving LLMs for Code Generation in No-Resource Languages	Alessandro Giagnorio et al.	arXiv	3
2026-06-19	2606.18231	Adaptive Volumetric Mechanical Property Fields Invariant to Resolution	Rishit Dagli et al.	arXiv	3
2026-06-19	2603.24624	ReSyn: A Generalized Recursive Regular Expression Synthesis Framework	Seongmin Kim et al.	arXiv	2
2026-06-19	2606.15760	The Data Manifold under the Microscope	Marios Koulakis et al.	arXiv	2
2026-06-19	2603.11273	Duration Aware Scheduling for ASR Serving Under Workload Drift	Darshan Makwana et al.	arXiv	2
2026-06-19	2606.15527	Selective Synergistic Learning for Video Object-Centric Learning	WonJun Moon et al.	arXiv	2
2026-06-19	2606.19602	Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why	Osman Alperen Çinar-Koraş et al.	arXiv	1
2026-06-18	2606.18558	MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction	Jianing Zhang et al.	arXiv	53
2026-06-18	2606.19338	Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games	Shengyuan Ding et al.	arXiv	50
2026-06-18	2606.16533	Kairos: A Native World Model Stack for Physical AI	Kairos Team et al.	arXiv	41
2026-06-18	2606.18363	Guava: An Effective and Universal Harness for Embodied Manipulation	Haowen Liu et al.	arXiv	27
2026-06-18	2606.17682	From Trainee to Trainer: LLM-Designed Training Environment for RL with Multi-Agent Reasoning	Chao Chen et al.	arXiv	26
2026-06-18	2606.19162	The Reward Was in Your Data All Along: Correcting Flow Matching with Discriminator-Guided RL	Nicolas Beltran-Velez et al.	arXiv	21
2026-06-18	2606.19341	Native Active Perception as Reasoning for Omni-Modal Understanding	Zhenghao Xing et al.	arXiv	20
2026-06-18	2606.18967	EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts	Minseo Kim et al.	arXiv	15
2026-06-18	2606.18322	SAE Interventions are Unreliable: Post-Intervention Recovery of Suppressed Behavior	Mingyue Cui et al.	arXiv	15
2026-06-18	2606.17539	Reinforcing Dual-Path Reasoning in Spatial Vision Language Models	Yatai Ji et al.	arXiv	14
2026-06-18	2606.17800	MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model	Lichen Bai et al.	arXiv	12
2026-06-18	2606.18375	PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation	Yuhang Huang et al.	arXiv	12
2026-06-18	2606.15872	SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks	Jingru Guo et al.	arXiv	11
2026-06-18	2606.19005	Sumi: Open Uniform Diffusion Language Model from Scratch	Mengyu Ye et al.	arXiv	11
2026-06-18	2606.14024	ViT-Up: Faithful Feature Upsampling for Vision Transformers	Krispin Wandel et al.	arXiv	9
2026-06-18	2606.05985	Beyond Alignment: Value Diversity as a Collective Property in Multicultural Agent Systems	Shaoyang Xu et al.	arXiv	9
2026-06-18	2606.18543	CEO-Bench: Can Agents Play the Long Game?	Haozhe Chen et al.	arXiv	8
2026-06-18	2606.16748	MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents	Lawrence Keunho Jang et al.	arXiv	6
2026-06-18	2606.18874	Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness	Zijian Wang et al.	arXiv	6
2026-06-18	2606.19236	STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability	Haipeng Luo et al.	arXiv	5
2026-06-18	2606.18101	Trust the Right Teacher: Quality-Aware Self-Distillation for GUI Grounding	Jingyuan Huang et al.	arXiv	5
2026-06-18	2606.09764	iOSWorld: A Benchmark for Personally Intelligent Phone Agents	Lawrence Keunho Jang et al.	arXiv	4
2026-06-18	2606.19047	RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use Agents	Ruishan Fang et al.	arXiv	4
2026-06-18	2606.14383	IndustryBench-MIPU: Benchmarking Multi-Image Attribute Value Extraction for Industrial Products	Haonan Qi et al.	arXiv	4
2026-06-18	2606.18943	Physics-IQ Verified	Tim Rädsch et al.	arXiv	4
2026-06-18	2606.18531	When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?	Xuanfei Ren et al.	arXiv	3
2026-06-18	2606.18717	Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish	Tolga Şakar	arXiv	3
2026-06-18	2606.19808	Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning	Sajib Acharjee Dip et al.	arXiv	2
2026-06-18	2606.18910	REVES: REvision and VErification--Augmented Training for Test-Time Scaling	Yuanxin Liu et al.	arXiv	2
2026-06-18	2606.19336	Learning User Simulators with Turing Rewards	Yingshan Susan Wang et al.	arXiv	2
2026-06-18	2606.06614	Re-Centering Humans in LLM Personalization	Lechen Zhang et al.	arXiv	1
2026-06-18	2606.13898	HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing	Haoran You et al.	arXiv	1
2026-06-18	2606.12629	The Signs Were Always There: Training-Free Detection and Control in Raw Transformer Dimensions	Varun Reddy Nalagatla et al.	arXiv	1
2026-06-18	2606.13802	A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets	Tejas Agrawal et al.	arXiv	1
2026-06-18	2606.11877	LLM-Enabled NWDAF: A Step Toward AI-Native 6G Network Intelligence	Henok Daniel et al.	arXiv	1
2026-06-18	2606.15514	Reinforcement Learning-Guided Retrieval with Soft Fusion for Robust Multimodal Imitation Learning under Missing Modalities	Hassan Ismkhan et al.	arXiv
2026-06-18	2606.19120	Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation	Sihan Wang et al.	arXiv
2026-06-17	2606.18023	LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling	Jian Yang et al.	arXiv	154
2026-06-17	2606.18216	Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients	Byung-Kwan Lee et al.	arXiv	64
2026-06-17	2606.17861	GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?	Tongxu Luo et al.	arXiv	58
2026-06-17	2606.17200	ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining	Hao Li et al.	arXiv	54
2026-06-17	2606.18208	Looped World Models	Hongyuan Adam Lu et al.	arXiv	51
2026-06-17	2606.16428	LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching	Jaward Sesay et al.	arXiv	40
2026-06-17	2606.18195	Learning from the Self-future: On-policy Self-distillation for dLLMs	Yifu Luo et al.	arXiv	38
2026-06-17	2606.17628	OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation	Guibin Zhang et al.	arXiv	29
2026-06-17	2606.09030	TRIAGE: Dialectical LLM Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series	Hyeongwon Jang et al.	arXiv	27
2026-06-17	2606.15236	Show the Signal, Hide the Noise: Spectral Forcing for Pixel-Space Diffusion	Weichen Fan et al.	arXiv	21
2026-06-17	2606.15378	Rethinking the Role of Efficient Attention in Hybrid Architectures	Ziqing Qiao et al.	arXiv	20
2026-06-17	2606.16767	Text-Vision Co-Instructed Image Editing	Chenxi Xie et al.	arXiv	18
2026-06-17	2606.18180	EgoCS-400K: An Egocentric Gameplay Dataset for World Models	Rongjin Guo et al.	arXiv	17
2026-06-17	2606.15345	Beyond Monolingual Deep Research: Evaluating Agents and Retrievers with Cross-Lingual BrowseComp-Plus	Yuheng Lu et al.	arXiv	16
2026-06-17	2606.13929	Self-Evolving Visual Questioner	Yijun Liang et al.	arXiv	15
2026-06-17	2606.18249	Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification	Wujian Peng et al.	arXiv	14
2026-06-17	2606.18246	Variable-Width Transformers	Zhaofeng Wu et al.	arXiv	13
2026-06-17	2606.14885	Dr-DCI: Scaling Direct Corpus Interaction via Dynamic Workspace Expansion	Yi Lu et al.	arXiv	12
2026-06-17	2606.17321	ProCUA-SFT Technical Report	Jaehun Jung et al.	arXiv	10
2026-06-17	2606.17730	ActWorld: From Explorable to Interactive World Model via Action-Aware Memory	Zhexiao Xiong et al.	arXiv	9
2026-06-17	2606.15158	RefGC-SR^2: Reference-guided Generated Content Super-Resolution and Refinement	Jeahun Sung et al.	arXiv	8
2026-06-17	2606.17905	ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions	Peixian Zhou et al.	arXiv	7
2026-06-17	2606.16905	Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences	Mingyang Li et al.	arXiv	6
2026-06-17	2606.15231	Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning	Zhengbo Zhang et al.	arXiv	4
2026-06-17	2606.17168	RepSelect: Robust LLM Unlearning via Representation Selectivity	Filip Sondej et al.	arXiv	4
2026-06-17	2606.15142	MotionVLA: Vision-Language-Action Model for Humanoid Motion	Nonghai Zhang et al.	arXiv	4
2026-06-17	2606.13811	Aligning Quantum Operators with Large Language Models	Rogerio Feris et al.	arXiv	3
2026-06-17	2606.15134	Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings	Shubhang Bhatnagar et al.	arXiv	2
2026-06-17	2606.16154	A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization	Prasanth YSS et al.	arXiv	2
2026-06-17	2606.17081	The Price of Anarchy in Disaggregated Inference	Athos Georgiou	arXiv	1
2026-06-17	2606.17182	Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems	Sajjad Khan	arXiv
2026-06-16	2606.14777	JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence	Dingyu Yao et al.	arXiv	213
2026-06-16	2606.16140	VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models	Sen Xu et al.	arXiv	128
2026-06-16	2606.17046	Geometric Action Model for Robot Policy Learning	Jisang Han et al.	arXiv	115
2026-06-16	2606.11176	Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories	Kevin Qinghong Lin et al.	arXiv	92
2026-06-16	2606.15079	Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale	Ang Li et al.	arXiv	81
2026-06-16	2606.14066	FastContext: Training Efficient Repository Explorer for Coding Agents	Shaoqiu Zhang et al.	arXiv	77
2026-06-16	2606.16993	DreamX-World 1.0: A General-Purpose Interactive World Model	DreamX Team et al.	arXiv	53
2026-06-16	2606.17030	Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation	Jie Zhang et al.	arXiv	48
2026-06-16	2606.16281	Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models	Heecheol Yun et al.	arXiv	32
2026-06-16	2606.17049	BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering	Yi-Ruei Liu et al.	arXiv	28
2026-06-16	2606.16295	VisualClaw: A Real-Time, Personalized Agent for the Physical World	Haoqin Tu et al.	arXiv	26
2026-06-16	2606.15007	Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning	NVIDIA et al.	arXiv	19
2026-06-16	2606.14667	Memento: Reconstruct to Remember for Consistent Long Video Generation	Xuan Wei et al.	arXiv	18
2026-06-16	2606.16838	OneRank: Unified Transformer-Native Ranking Architecture for Multi-Task Recommendation	Jiakai Tang et al.	arXiv	18
2026-06-16	2606.14958	MVEB: Massive Video Embedding Benchmark	Adnan El Assadi et al.	arXiv	16
2026-06-16	2606.16519	BadWorld: Adversarial Attacks on World Models	Linghui Shen et al.	arXiv	16
2026-06-16	2606.15631	Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time	Jeongeun Park et al.	arXiv	16
2026-06-16	2606.17016	TokenPilot: Cache-Efficient Context Management for LLM Agents	Buqiang Xu et al.	arXiv	15
2026-06-16	2606.16396	SP^3: Spherical Priors for Plug-and-Play Restoration	Sean Man et al.	arXiv	14
2026-06-16	2606.16255	UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer	Shuai Wang et al.	arXiv	14
2026-06-16	2606.15956	You Don't Need Strong Assumptions: Visual Representation Learning via Temporal Differences	Ninad Daithankar et al.	arXiv	12
2026-06-16	2606.15673	Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking	Jiwan Chung et al.	arXiv	12
2026-06-16	2606.15534	Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks	Feng Qiao et al.	arXiv	11
2026-06-16	2606.16771	GD^2PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization	Haotian Liu et al.	arXiv	11
2026-06-16	2606.14832	PhoneHarness: Harnessing Phone-Use Agents through Mixed GUI, CLI, and Tool Actions	Chenxin Li et al.	arXiv	11
2026-06-16	2606.17043	Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes	Tongyan Fang et al.	arXiv	9
2026-06-16	2606.06302	Tangram: Unlocking Non-Uniform KV Cache Compression for Efficient Multi-turn LLM Serving	Hyungmin Kim et al.	arXiv	9
2026-06-16	2606.15300	CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?	Yuxin Zhang et al.	arXiv	9
2026-06-16	2602.21103	Prompt-Level Distillation: A Non-Parametric Alternative to Model Fine-Tuning for Efficient Reasoning	Sanket Badhe et al.	arXiv	8
2026-06-16	2606.12138	Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders	Gleb Gerasimov et al.	arXiv	7
2026-06-16	2606.17024	ExpRL: Exploratory RL for LLM Mid-Training	Violet Xiang et al.	arXiv	6
2026-06-16	2606.16449	PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory	Shuai Yang et al.	arXiv	6
2026-06-16	2606.16673	MMDiff: Extending Diffusion Transformers for Multi-Modal Generation	Yagmur Akarken et al.	arXiv	5
2026-06-16	2606.15708	Artificial Intelligence Index Report 2026	Sha Sajadieh et al.	arXiv	5
2026-06-16	2606.15768	LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies	Jialei Chen et al.	arXiv	3
2026-06-16	2606.16011	Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs	Nafiseh Nikeghbal et al.	arXiv	3
2026-06-16	2606.17054	Human Universal Grasping	Kevin Yuanbo Wu et al.	arXiv	2
2026-06-16	2606.16202	EgoPhys: Learning Generalizable Physics Models of Deformable Objects from Egocentric Video	Hyunjin Kim et al.	arXiv	2
2026-06-16	2606.14142	Implicit Reasoning for Large Language Model-based Generative Recommendation	Yinhan He et al.	arXiv	2
2026-06-16	2505.14608	Attacks on Machine-Text Detectors Retain Stylistic Fingerprints	Rafael Rivera Soto et al.	arXiv	1
2026-06-16	2606.14819	Selective Control under Noisy Perception: Governance Failures Hidden by Aggregate Metrics in Modular Networks	Igor Itkin	arXiv	1
2026-06-16	2606.17006	TuneJury: An Open Metric for Improving Music Generation Preference Alignment	Yonghyun Kim et al.	arXiv	1
2026-06-16	2606.16852	The Ghosts of Polymarket: When Off-Chain Matches Meet On-Chain Reverts	Yiming Shen et al.	arXiv
2026-06-15	2606.06036	Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents	Shuo Ji et al.	arXiv	76
2026-06-15	2606.14502	From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI	Yongheng Zhang et al.	arXiv	62
2026-06-15	2606.13432	OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data	Jiwen Liu et al.	arXiv	54
2026-06-15	2606.14249	HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry	Tingyang Chen et al.	arXiv	52
2026-06-15	2606.12384	APPO: Agentic Procedural Policy Optimization	Xucong Wang et al.	arXiv	49
2026-06-15	2606.13707	Orchestra-o1: Omnimodal Agent Orchestration	Fan Zhang et al.	arXiv	48
2026-06-15	2606.12291	Measuring Epistemic Resilience of LLMs Under Misleading Medical Context	Hongjian Zhou et al.	arXiv	39
2026-06-15	2606.12683	From AGI to ASI	Tim Genewein et al.	arXiv	39
2026-06-15	2606.13141	Rethinking RAG in Long Videos: What to Retrieve and How to Use It?	Yuho Lee et al.	arXiv	34
2026-06-15	2606.14702	OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains	Xinyue Cai et al.	arXiv	32
2026-06-15	2605.30789	Smaller Models are Natural Explorers for Policy-Level Diversity in GRPO	Yiming Ren et al.	arXiv	25
2026-06-15	2606.06574	Skip a Layer or Loop It? Learning Program-of-Layers in LLMs	Ziyue Li et al.	arXiv	25
2026-06-15	2606.14061	LLM Agents Can See Code Repositories	Dongjian Ma et al.	arXiv	20
2026-06-15	2606.10813	RedAct: Redacting Agent Capability Traces for Procedural Skill Protection	Shuwen Xu et al.	arXiv	17
2026-06-15	2606.14700	RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space	Xichen Pan et al.	arXiv	17
2026-06-15	2606.13652	World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible	Hao Zhang et al.	arXiv	16
2026-06-15	2606.14409	Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack	He Zhang et al.	arXiv	15
2026-06-15	2606.12594	Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean Formalisation	Joshua Ong Jun Leang et al.	arXiv	14
2026-06-15	2606.09813	iMaC: Translating Actions into Motion and Contact Images for Embodied World Models	Zhenyu Wu et al.	arXiv	12
2026-06-15	2606.10747	The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment	Filippo Tonini et al.	arXiv	11
2026-06-15	2606.00793	MBench: A Comprehensive Benchmark on Memory Capability for Video World Models	Shengjun Zhang et al.	arXiv	11
2026-06-15	2606.13044	No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions	Xu Yang et al.	arXiv	10
2026-06-15	2606.13769	μ_0: A Scalable 3D Interaction-Trace World Model	Seungjae Lee et al.	arXiv	10
2026-06-15	2606.06309	RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling	Chensheng Dai et al.	arXiv	8
2026-06-15	2606.13872	Avatar V: Scaling Video-Reference Avatar Video Generation	Benjamin Liang et al.	arXiv	8
2026-06-15	2606.11599	When is Your LLM Steerable?	Chenrui Fan et al.	arXiv	8
2026-06-15	2606.12883	The Hidden Power of Scaling Factor in LoRA Optimization	Zicheng Zhang et al.	arXiv	7
2026-06-15	2604.18401	StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning	Daoyu Wang et al.	arXiv	6
2026-06-15	2606.14579	VISTA: View-Consistent Self-Verified Training for GUI Grounding	Xinyu Qiu et al.	arXiv	6
2026-06-15	2606.14600	LoSoNA: A Benchmark for Local Social Norm Adaptation in Group Conversations	Mateusz Winiarek et al.	arXiv	5
2026-06-15	2606.12736	Benchmarking AI Agents for Addressing Scientific Challenges Across Scales	Tianyu Liu et al.	arXiv	5
2026-06-15	2606.14697	ClinHallu: A Benchmark for Diagnosing Stage-Wise Hallucinations in Medical MLLM Reasoning	Sicheng Yang et al.	arXiv	5
2026-06-15	2606.01462	An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models	Mingzhong Sun et al.	arXiv	4
2026-06-15	2606.08952	AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models	Shouwei Ruan et al.	arXiv	4
2026-06-15	2606.11152	P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning	Yikang Yang et al.	arXiv	4
2026-06-15	2606.14240	AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties	Yifan Jiang et al.	arXiv	3
2026-06-15	2606.13657	Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation	Guo Yu et al.	arXiv	3
2026-06-15	2606.14732	Steady-Forcing: Balancing Spatial Persistence and Motion Continuity in Long-Horizon Nature Video Diffusion	Matiur Rahman Minar et al.	arXiv	2
2026-06-15	2606.01708	Two-Fidelity Best-Action Identification for Stochastic Minimax Tree	Peter Chen et al.	arXiv	2
2026-06-15	2606.05308	Statistically Reliable LLM-Based Ranking Evaluation via Prediction-Powered Inference	Abhishek Divekar	arXiv	2
2026-06-15	2606.12366	APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies	Kechun Xu et al.	arXiv	2
2026-06-15	2606.06194	ActiveMimic: Egocentric Video Pretraining with Active Perception	Xingyao Lin et al.	arXiv	2
2026-06-15	2606.14694	AdaSR: Adaptive Streaming Reasoning with Hierarchical Relative Policy Optimization	Junlong Tong et al.	arXiv	2
2026-06-15	2606.01008	FVSpec: Real-World Property-Based Tests as Lean Challenges	Quinn Dougherty et al.	arXiv	1
2026-06-15	2606.12476	Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics	Igor Itkin	arXiv	1
2026-06-15	2606.14346	Squeeze-Release: Iterative Pruning with Exact Structural Minimization	Roman Denkin et al.	arXiv	1
2026-06-15	2606.08670	WaveDiT: Distribution-Aware Wavelet Flow Matching for Efficient 3D Brain MRI Synthesis	Danilo Danese et al.	arXiv	1
2026-06-15	2606.02641	CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive Driving	Yifan Wang	arXiv
2026-06-12	2606.13392	MiniMax Sparse Attention	Xunhao Lai et al.	arXiv	169
2026-06-12	2606.13681	EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments	Jundong Xu et al.	arXiv	143
2026-06-12	2606.13673	SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning	Seokju Cho et al.	arXiv	115
2026-06-12	2606.13473	MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling	Jiacheng Chen et al.	arXiv	97
2026-06-12	2606.13578	LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories	Baochang Ren et al.	arXiv	64
2026-06-12	2606.09426	WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces	Wanli Li et al.	arXiv	46
2026-06-12	2606.12087	FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents	Jia Deng et al.	arXiv	39
2026-06-12	2606.12243	VIA-SD: Verification via Intra-Model Routing for Speculative Decoding	Yuchen Xian et al.	arXiv	36
2026-06-12	2606.13679	InterleaveThinker: Reinforcing Agentic Interleaved Generation	Dian Zheng et al.	arXiv	34
2026-06-12	2606.12303	From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion	Yuchen Xian et al.	arXiv	33
2026-06-12	2606.08063	Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?	Jiaqi Tang et al.	arXiv	32
2026-06-12	2606.13289	HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers	Guozhen Zhang et al.	arXiv	31
2026-06-12	2606.13662	EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery	Amy Xin et al.	arXiv	30
2026-06-12	2606.13106	Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning	Jiayu Yang et al.	arXiv	23
2026-06-12	2606.13364	VideoMDM: Towards 3D Human Motion Generation From 2D Supervision	Amir Mann et al.	arXiv	22
2026-06-12	2606.10768	N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy Optimization	Xukun Zhu et al.	arXiv	22
2026-06-12	2606.13376	MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold	Yang Zhou et al.	arXiv	17
2026-06-12	2606.06113	Where, What, Why, and Importance: Structured Defect Grounding for Text-to-Image Feedback	Huaisong Zhang et al.	arXiv	16
2026-06-12	2606.12882	HarnessBridge: Learnable Bidirectional Controller for LLM Agent Harness	Xiaoxuan Wang et al.	arXiv	15
2026-06-12	2606.12575	High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End Distillation	Dongyang Liu et al.	arXiv	12
2026-06-12	2606.11409	Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models	Malikeh Ehghaghi et al.	arXiv	10
2026-06-12	2606.11662	TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search	Zhuofan Shi et al.	arXiv	8
2026-06-12	2606.10896	Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering	Gal Bloch et al.	arXiv	8
2026-06-12	2606.13644	Surflo: Consistent 3D Surface Flow Model with Global State	Antoine Guédon et al.	arXiv	8
2026-06-12	2606.12730	Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior	Rafal Kocielnik et al.	arXiv	7
2026-06-12	2606.13594	See What I See, Know What I Think: Dense Latent Communication Across Heterogeneous Agents	Siyi Chen et al.	arXiv	6
2026-06-12	2606.08039	MuJoCo-Drones-Gym: A GPU-Accelerated Multi-Drone Simulator for Control and Reinforcement Learning	Manan Tayal	arXiv	6
2026-06-12	2606.12674	Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents	Kushal Raj Bhandari et al.	arXiv	6
2026-06-12	2606.13174	Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents	Yujun Zhou et al.	arXiv	4
2026-06-12	2606.13120	EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge	Yunhan Wang et al.	arXiv	4
2026-06-12	2606.08788	MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training	Lianyu Pang et al.	arXiv	4
2026-06-12	2606.10423	WebChallenger: A Reliable and Efficient Generalist Web Agent	Jayoo Hwang et al.	arXiv	3
2026-06-12	2606.07867	The Cold-Start Safety Gap in LLM Agents	Chung-En Sun et al.	arXiv	3
2026-06-12	2606.08103	Revisiting Articulated Parts Perception in Robot Manipulation	Xiaoqian Wu et al.	arXiv	3
2026-06-12	2606.13672	WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation	Arnav Kumar Jain et al.	arXiv	3
2026-06-12	2606.12451	ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs	Ashutosh Hathidara et al.	arXiv	2
2026-06-12	2606.12488	A Stationary (and Therefore Compatible) Representation is All You Need	Niccolò Biondi et al.	arXiv	2
2026-06-12	2606.13572	ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages	Tanmoy Kanti Halder et al.	arXiv	2
2026-06-12	2606.11096	IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder	Yitong Chen et al.	arXiv	2
2026-06-12	2606.09290	Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning	Haoran Xu et al.	arXiv	2
2026-06-12	2606.00467	On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance	Etienne Casanova et al.	arXiv	1
2026-06-12	2606.09446	Leveraging Morphology for Historical Script Metrological Analysis	Malamatenia Vlachou Efstathiou et al.	arXiv	1
2026-06-12	2606.12282	PianoKontext: Expressive Performance Rendering from Deadpan Context	Dmitrii Gavrilev	arXiv	1
2026-06-12	2606.09304	SG-OPD: Sign-Gated On-Policy Distillation via Sign-Consistency Gating and Phased Teacher Sampling	Haoran Xu et al.	arXiv	1
2026-06-11	2606.11926	Toward Generalist Autonomous Research via Hypothesis-Tree Refinement	Jiajie Jin et al.	arXiv	79
2026-06-11	2606.12191	Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application	Jiachun Li et al.	arXiv	71
2026-06-11	2606.09076	Beyond Scalar Rewards by Internalizing Reasoning into Score Distributions	Xin Jin et al.	arXiv	61
2026-06-11	2606.09323	TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders	Wei Pang et al.	arXiv	54
2026-06-11	2606.12397	Redesign Mixture-of-Experts Routers with Manifold Power Iteration	Songhao Wu et al.	arXiv	49
2026-06-11	2606.10728	DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch	Jiale Zhao et al.	arXiv	37
2026-06-11	2606.12344	Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks	Mengyu Zheng et al.	arXiv	35
2026-06-11	2606.11324	Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models	Yifu Yuan et al.	arXiv	28
2026-06-11	2606.11683	Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning	Chaofan Ma et al.	arXiv	26
2026-06-11	2606.12364	On Subquadratic Architectures: From Applications to Principles	Anamaria-Roberta Hartl et al.	arXiv	25
2026-06-11	2606.12195	InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning	Ziang Yan et al.	arXiv	24
2026-06-11	2606.11119	TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning	Heming Zou et al.	arXiv	21
2026-06-11	2606.12412	Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models	Cheng-Yu Yang et al.	arXiv	20
2026-06-11	2606.11289	i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models	Boya Zeng et al.	arXiv	19
2026-06-11	2606.11817	Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code	Yitong Zhang et al.	arXiv	18
2026-06-11	2606.12370	Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling	Yucheng Li et al.	arXiv	18
2026-06-11	2606.12403	World Pilot: Steering Vision-Language-Action Models with World-Action Priors	Zefu Lin et al.	arXiv	18
2026-06-11	2606.10479	ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics	Shunkai Zhang et al.	arXiv	17
2026-06-11	2606.08035	DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning	Hangui Lin et al.	arXiv	15
2026-06-11	2606.12072	World Model Self-Distillation: Training World Models to Solve General Tasks	Sebastian Stapf et al.	arXiv	15
2026-06-11	2606.03108	EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning	Guhong Chen et al.	arXiv	12
2026-06-11	2606.11722	ICA Lens: Interpreting Language Models Without Training Another Dictionary	Sida Liu et al.	arXiv	10
2026-06-11	2605.11212	ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction	Amirhossein Abaskohi et al.	arXiv	7
2026-06-11	2606.12373	Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization	Hao Xiang et al.	arXiv	7
2026-06-11	2606.13674	RepWAM: World Action Modeling with Representation Visual-Action Tokenizers	Junke Wang et al.	arXiv	6
2026-06-11	2606.07881	Breaking the Bubble: Asynchronous Pipeline Parallel Training with Bounded Weight Inconsistency	Itay Elam et al.	arXiv	6
2026-06-11	2606.12385	Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs	Sanjay Adhikesaven et al.	arXiv	5
2026-06-11	2606.04511	SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference	Yaosheng Fu et al.	arXiv	5
2026-06-11	2606.11482	Building Social World Models with Large Language Models	Haofei Yu et al.	arXiv	4
2026-06-11	2606.11854	Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training	Michal Chudoba et al.	arXiv	4
2026-06-11	2606.07943	POISE: Position-Aware Undetectable Skill Injection on LLM Agents	Haochang Hao et al.	arXiv	4
2026-06-11	2606.04261	Can Generalist Agents Automate Data Curation?	Feiyang Kang et al.	arXiv	3
2026-06-11	2606.05758	DRIFT: A Residual Flow Adapter for Decoding Continuous Outputs in Vision-Language Models	Zhuoming Liu et al.	arXiv	3
2026-06-11	2606.11990	Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation	Amir El-Ghoussani et al.	arXiv	3
2026-06-11	2606.03437	Large Language Models Are Overconfident in Their Own Responses	Mario Sanz-Guerrero et al.	arXiv	3
2026-06-11	2605.30861	Distilling LLM Feedback for Lean Theorem Proving	Gaetan Narozniak et al.	arXiv	3
2026-06-11	2606.10587	Towards Diverse Scientific Hypothesis Search with Large Language Models	Haorui Wang et al.	arXiv	2
2026-06-11	2606.12203	Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models	Changyue Wang et al.	arXiv	2
2026-06-11	2606.10156	τ-Rec: A Verifiable Benchmark for Agentic Recommender Systems	Bharath Sivaram Narasimhan et al.	arXiv	2
2026-06-11	2601.05212	FlowLet: Conditional 3D Brain MRI Synthesis using Wavelet Flow Matching	Danilo Danese et al.	arXiv	2
2026-06-11	2606.11786	Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay	Joanito Agili Lopo et al.	arXiv	2
2026-06-11	2606.11553	APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations	Swadhin Pradhan et al.	arXiv	1
2026-06-10	2606.09967	ABot-Earth 0.5: Generative 3D Earth Model	Ming Qian et al.	arXiv	139
2026-06-10	2606.10651	Kwai Keye-VL-2.0 Technical Report	Kwai Keye Team et al.	arXiv	57
2026-06-10	2606.09730	SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research	Pu Ning et al.	arXiv	55
2026-06-10	2606.10804	SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning	Wenhao Yan et al.	arXiv	54
2026-06-10	2606.11025	Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models	Bowen Ping et al.	arXiv	42
2026-06-10	2606.07512	MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism	Cong Chen et al.	arXiv	40
2026-06-10	2606.05922	Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts	Wenbo Pan et al.	arXiv	36
2026-06-10	2606.11180	Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization	Paul Hyunbin Cho et al.	arXiv	36
2026-06-10	2606.09821	Rethinking the Divergence Regularization in LLM RL	Jiarui Yao et al.	arXiv	34
2026-06-10	2606.11129	WorldOlympiad: Can Your World Model Survive a Triathlon?	Yuke Zhao et al.	arXiv	33
2026-06-10	2606.10917	Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution	Xucong Wang et al.	arXiv	32
2026-06-10	2606.11188	ARM: An AutoRegressive Large Multimodal Model with Unified Discrete Representations	Junke Wang et al.	arXiv	27
2026-06-10	2606.11042	Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields	Liya Zhu et al.	arXiv	24
2026-06-10	2606.11182	EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents	Weixian Xu et al.	arXiv	21
2026-06-10	2606.10572	One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA	Zhi Zheng et al.	arXiv	18
2026-06-10	2606.11052	Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It	Xinyu Zhou et al.	arXiv	16
2026-06-10	2606.10029	Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders	Nikita Koriagin et al.	arXiv	12
2026-06-10	2606.04391	Online Skill Learning for Web Agents via State-Grounded Dynamic Retrieval	Jiaxi Li et al.	arXiv	12
2026-06-10	2606.02540	SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction	Yuting Ning et al.	arXiv	10
2026-06-10	2606.10650	Dynamic Linear Attention	Xin Wang et al.	arXiv	9
2026-06-10	2606.11187	Next Forcing: Causal World Modeling with Multi-Chunk Prediction	Gangwei Xu et al.	arXiv	8
2026-06-10	2606.10646	How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs	Zhichen Dong et al.	arXiv	8
2026-06-10	2606.09056	MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation	Ishaan Preetam Chandratreya et al.	arXiv	8
2026-06-10	2606.09707	BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling	Gianluca Barmina et al.	arXiv	7
2026-06-10	2606.07689	Struct-Searcher: Agentic Structural Thinking Advances Multimodal Deep Information Seeking	Fan Zhang et al.	arXiv	7
2026-06-10	2606.09032	Bridging the Agent-World Gap: Text World Models for LLM-based Agents	Yixia Li et al.	arXiv	7
2026-06-10	2606.09697	PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models	Gianluca Barmina et al.	arXiv	6
2026-06-10	2606.07379	Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests	Thanawat Lodkaew et al.	arXiv	5
2026-06-10	2606.09068	Emergent Misalignment Can Be Induced by Sycophancy and Reversed via Alignment Gating	Sicheng Wang et al.	arXiv	5
2026-06-10	2606.05304	What Should Agents Say? Action-state Communication for Efficient Multi-Agent Systems	Chen Huang et al.	arXiv	5
2026-06-10	2606.10968	Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning	Renjie Mao et al.	arXiv	4
2026-06-10	2606.10662	Decentralized Multi-Agent Systems with Shared Context	Yuzhen Mao et al.	arXiv	4
2026-06-10	2606.11131	UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors	Zhiwen Yang et al.	arXiv	4
2026-06-10	2606.11032	U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training	Zhiwen Yang et al.	arXiv	4
2026-06-10	2606.11087	Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning	Zhiyuan Zhou et al.	arXiv	4
2026-06-10	2606.08857	PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf	Jiarui Liu et al.	arXiv	3
2026-06-10	2606.11173	The Role of Feedback Alignment in Self-Distillation	Semih Kara et al.	arXiv	3
2026-06-10	2606.06098	IR3DE: A Linear Router for Large Language Models	Eros Fanì et al.	arXiv	3
2026-06-10	2606.09131	Late-Layer Fusion is Enough: Dual-Path Vision Token Routing for Multimodal Large Language Models under Visual Saturation	Siyuan Liu et al.	arXiv	3
2026-06-10	2606.10740	When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning Models	Sai Kartheek Reddy Kasu et al.	arXiv	2
2026-06-10	2606.12071	On the Limits of LLM-as-Judge for Scientific Novelty Assessment	Soumitra Sinhahajari et al.	arXiv	1
2026-06-10	2606.08044	When Behavioral Safety Evaluation Fails: A Representation-Level Perspective	Enyi Jiang et al.	arXiv	1
2026-06-10	2606.10061	BenSyc: Benchmarking Conversational Sycophancy and Human Alignment in LLMs for Bengali Contexts	Kazi Noshin et al.	arXiv	1
2026-06-10	2606.06458	In-Context Multiple Instance Learning	Alexander Möllers et al.	arXiv
2026-06-10	2606.10671	FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion	Yu Lu et al.	arXiv
2026-06-09	2606.05405	Agents' Last Exam	Yiyou Sun et al.	arXiv	273
2026-06-09	2606.07297	SWE-Explore: Benchmarking How Coding Agents Explore Repositories	Shaoqiu Zhang et al.	arXiv	121
2026-06-09	2606.07082	On the Geometry of On-Policy Distillation	Zhennan Shen et al.	arXiv	75
2026-06-09	2606.09079	FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention	Yan Wang et al.	arXiv	68
2026-06-09	2606.06087	LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents	Aofan Yu et al.	arXiv	65
2026-06-09	2606.09828	Latent Spatial Memory for Video World Models	Weijie Wang et al.	arXiv	65
2026-06-09	2606.09669	SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks	Hongcheng Gao et al.	arXiv	50
2026-06-09	2606.08415	CoVEBench: Can Video Editing Models Handle Complex Instructions?	Jiangtao Wu et al.	arXiv	47
2026-06-09	2509.10078	Human Psychometric Questionnaires Mischaracterize LLM Behavior	Woojung Song et al.	arXiv	35
2026-06-09	2606.09803	Echo-Memory: A Controlled Study of Memory in Action World Models	Wayne King et al.	arXiv	33
2026-06-09	2606.09659	End-to-End Context Compression at Scale	Ang Li et al.	arXiv	28
2026-06-09	2606.07436	Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial Reasoning	Haoyuan Li et al.	arXiv	27
2026-06-09	2606.06735	A Geometric Account of Activation Steering through Angle-Norm Decomposition	Georgii Aparin et al.	arXiv	26
2026-06-09	2605.25077	WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models	Bohai Gu et al.	arXiv	21
2026-06-09	2606.09826	OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics	Mingxian Lin et al.	arXiv	19
2026-06-09	2606.09516	SwiftVR: Real-Time One-Step Generative Video Restoration	Jiaqi Yan et al.	arXiv	18
2026-06-09	2605.27130	DEI: Diversity in Evolutionary Inference for Quality-Diversity Search	John Donaghy et al.	arXiv	16
2026-06-09	2606.08348	Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses	Xiaojun Wu et al.	arXiv	16
2026-06-09	2606.09811	AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing	Jisong Cai et al.	arXiv	15
2026-06-09	2606.07473	Whisper Hallucination Detection and Mitigation via Hidden Representation Steering and Sparse AutoEncoders	Georgii Aparin et al.	arXiv	14
2026-06-09	2606.08572	OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning	Jiahao Wang et al.	arXiv	13
2026-06-09	2606.08242	Light-WAM: Efficient World Action Models with State-Fusion Action Decoding	Ziang Li et al.	arXiv	12
2026-06-09	2606.03715	Text-to-Image Models Need Less from Text Encoders Than You Think	Nurit Spingarn et al.	arXiv	11
2026-06-09	2606.09380	Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short	Han Zhou et al.	arXiv	10
2026-06-09	2606.04662	Why Muon Outperforms Adam: A Curvature Perspective	Shuche Wang et al.	arXiv	10
2026-06-09	2606.07299	DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning	Lingyong Yan et al.	arXiv	9
2026-06-09	2606.07547	Liberating LLM Capabilities in Full-Duplex Speech Models	Luoyuan Zhang et al.	arXiv	8
2026-06-09	2606.01000	Trust Functions: Near-Lossless Weak-to-Strong Generalization by Learning When to Trust the Weak Teacher	Arda Uzunoglu et al.	arXiv	7
2026-06-09	2606.05633	Answer Presence Drives RAG Rewriting Gains	Yuejie Li et al.	arXiv	7
2026-06-09	2606.06523	Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory	Ruida Wang et al.	arXiv	7
2026-06-09	2606.07723	VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation	Siyi Chen et al.	arXiv	6
2026-06-09	2606.07074	SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating	Zequn Xie et al.	arXiv	6
2026-06-09	2606.08432	Trajectory-Refined Distillation	Li Jiang et al.	arXiv	6
2026-06-09	2606.05597	AsyncWebRL: Efficient Multi-Step RL for Visual Web Agents	Hao Bai et al.	arXiv	5
2026-06-09	2606.00440	SDR: Set-Distance Rewards for Radiology Report Generation	Halil Ibrahim Gulluk et al.	arXiv	5
2026-06-09	2606.07217	Robotic Policy Adaptation via Weight-Space Meta-Learning	Christian Bianchi et al.	arXiv	5
2026-06-09	2606.09585	Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text	Yutong Bian et al.	arXiv	5
2026-06-09	2606.09809	Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting	Avijit Ghosh et al.	arXiv	5
2026-06-09	2605.28207	Pruning and Distilling Mixture-of-Experts into Dense Language Models	Junhyuck Kim et al.	arXiv	4
2026-06-09	2606.08132	Phase Marginalization for Patch-Grid Instability in Vision Transformers	Oğuzhan Ercan	arXiv	4
2026-06-09	2606.09365	Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory	Haoran Sun et al.	arXiv	4
2026-06-09	2606.03980	Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill	Tao Chen et al.	arXiv	4
2026-06-09	2606.08548	OASIS: From Simulation Data Collection to Real-World Humanoid Loco-Manipulation	Zehao Yu et al.	arXiv	3
2026-06-09	2606.08362	EmpiriGraph-Psy: A Dataset and LLM Pipeline for Extracting Empirical Relation Graphs from Psychology Abstracts	Danqin Zhao et al.	arXiv	2
2026-06-09	2606.08960	Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops	Ziqian Zhong et al.	arXiv	2
2026-06-09	2606.05122	Self-Evaluation Is Already There: Eliciting Latent Judge Calibration in Base LLMs with Minimal Data	XiuYu Zhang et al.	arXiv	2
2026-06-09	2605.30837	Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense	Shuhao Zhang et al.	arXiv	1
2026-06-09	2606.07271	Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path	Thomas Sesmat et al.	arXiv	1
2026-06-09	2606.08327	Chiaroscuro Attention: Spending Compute in the Dark	Prateek Kumar Sikdar	arXiv	1
2026-06-09	2606.05753	Cosine Misleads: Auxiliary Losses Reshape Vision Language Models, Not Their Latents	XiuYu Zhang et al.	arXiv	1
2026-06-09	2606.08481	PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems	Suraj Ranganath et al.	arXiv	1
2026-06-09	2605.29463	Honest Lying: Understanding Memory Confabulation in Reflexive Agents	Prakhar Dixit et al.	arXiv	1
2026-06-09	2606.09376	Precision Is Not Faithfulness: Coverage-Aware Evaluation of Grounded Generation with a Complete Oracle	Juan S. Santillana	arXiv
2026-06-09	2606.07098	SigmaScale: LLM Compression with SVD-based Low-Rank Decomposition and Learned Scaling Matrices	Ernests Lavrinovics et al.	arXiv
2026-06-09	2606.03782	Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?	Renhao Pei et al.	arXiv
2026-06-09	2606.05011	CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimation	Yurim Jeon et al.	arXiv
2026-06-09	2606.09348	PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment	Yang Tian et al.	arXiv
2026-06-09	2605.24047	EMMA: Extracting Multiple physical parameters from Multimodal Data	Farhat Shaikh et al.	arXiv
2026-06-09	2606.08324	Set-Based Transformer for Atmospheric Compensation in Standoff LWIR Hyperspectral Imaging	Fabian Perez et al.	arXiv
2026-06-08	2606.07591	ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research	Wanghan Xu et al.	arXiv	106
2026-06-08	2606.07502	Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings	Songhao Wu et al.	arXiv	54
2026-06-08	2606.07229	MMAE: A Massive Multitask Audio Editing Benchmark	Ziyang Ma et al.	arXiv	45
2026-06-08	2606.04525	GENEB: Why Genomic Models Are Hard to Compare	Daria Ledneva et al.	arXiv	43
2026-06-08	2606.05563	SoCRATES: Towards Reliable Automated Evaluation of Proactive LLM Mediation across Domains and Socio-cognitive Variations	Taewon Yun et al.	arXiv	40
2026-06-08	2606.06556	Robots Need More than VLA and World Models	Elis Karcini et al.	arXiv	31
2026-06-08	2606.07326	AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization	Yu Li et al.	arXiv	30
2026-06-08	2606.06741	OpenSkill: Open-World Self-Evolution for LLM Agents	Zhiling Yan et al.	arXiv	29
2026-06-08	2606.06601	Direct 3D-Aware Object Insertion via Decomposed Visual Proxies	Jingbo Gong et al.	arXiv	26
2026-06-08	2606.06622	UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs	Amirhossein Abaskohi et al.	arXiv	23
2026-06-08	2606.03988	Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models	Mahtab Bigverdi et al.	arXiv	22
2026-06-08	2606.05806	When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents	Dongsheng Zhu et al.	arXiv	22
2026-06-08	2606.07433	Watch, Remember, Reason: Human-View Video Understanding with MLLMs	Jiahao Meng et al.	arXiv	20
2026-06-08	2606.05972	LLM Explainability with Counterfactual Chains and Causal Graphs	Nirit Nussbaum-Hoffer et al.	arXiv	19
2026-06-08	2606.05761	SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents	Wenxuan Wang et al.	arXiv	19
2026-06-08	2605.27276	SIA: Self Improving AI with Harness & Weight Updates	Prannay Hebbar et al.	arXiv	17
2026-06-08	2606.07080	dots.tts Technical Report	Shi Lian et al.	arXiv	16
2026-06-08	2606.06476	Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators	Chenming Zhu et al.	arXiv	15
2026-06-08	2606.07514	UniSHARP: Universal Sharp Monocular View Synthesis	Meixi Song et al.	arXiv	15
2026-06-08	2606.06953	LIMMT: Less is More for Motion Tracking	Yu Guan et al.	arXiv	14
2026-06-08	2606.07454	PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams	Fuqiang Wang et al.	arXiv	14
2026-06-08	2606.07412	Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills	Chuan Xiao et al.	arXiv	13
2026-06-08	2606.05531	Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models	Mohammad Mahdi Abootorabi et al.	arXiv	8
2026-06-08	2606.01779	HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems	Mingju Chen et al.	arXiv	8
2026-06-08	2605.23898	SPACENUM: Revisiting Spatial Numerical Understanding in VLMs	Jianshu Zhang et al.	arXiv	7
2026-06-08	2606.04291	A Cookbook of 3D Vision: Data, Learning Paradigms, and Application	Hongyang Du et al.	arXiv	6
2026-06-08	2606.06880	Towards Retrieving Interaction Spaces for Agentic Search	Shengyao Zhuang et al.	arXiv	6
2026-06-08	2606.06361	Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them	Woojung Han et al.	arXiv	6
2026-06-08	2605.28742	CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning	Linas Nasvytis et al.	arXiv	5
2026-06-08	2606.06891	Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors	Hanxun Yu et al.	arXiv	5
2026-06-08	2606.05152	Reinforcement Learning from Rich Feedback with Distributional DAgger	Rishabh Agrawal et al.	arXiv	4
2026-06-08	2606.07207	Entropy as a Structural Prior: How a Log-Barrier on DiT Belief Space Drives Musical Diversity and Development	Zixi Li et al.	arXiv	4
2026-06-08	2606.06538	WorldBench: A Challenging and Visually Diverse Multimodal Reasoning Benchmark	Yida Yin et al.	arXiv	4
2026-06-08	2605.22737	The Distillation Game: Adaptive Attacks & Efficient Defenses	Youssef Allouah et al.	arXiv	3
2026-06-08	2605.29430	Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation	Zixuan Jiang et al.	arXiv	3
2026-06-08	2606.05988	Compress-Distill: Reasoning Trace Compression for Efficient Knowledge Distillation	Maxime Griot et al.	arXiv	3
2026-06-08	2606.06712	Data-Efficient Autoregressive-to-Diffusion Language Models via On-Policy Distillation	Xingyu Su et al.	arXiv	2
2026-06-08	2606.07508	Streaming Video Generation with Streaming Force Control	Hanhui Wang et al.	arXiv	2
2026-06-08	2606.07895	TBD-VLA: Temporal Block Diffusion Vision Language Action Model	Sung-Wook Lee et al.	arXiv	1
2026-06-08	2606.06843	Empirical Study on the Characteristics and Evolution of AI-usage in GitHub Repositories: Evidence from Code Comments	Abdullah Al Mujahid et al.	arXiv	1
2026-06-08	2606.04767	Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms	Chong Zhang et al.	arXiv	1
2026-06-08	2606.01838	LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models	Prateek Kumar Sikdar	arXiv	1
2026-06-08	2606.07334	How Far Can Chord-Symbol Time-Series Adaptation Carry Genre Identity? Capabilities and Boundaries in Multi-Genre Chord-Symbol Modeling	Jinju Lee	arXiv	1
2026-06-08	2606.00590	Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback	Md Zarif Ul Alam et al.	arXiv	1
2026-06-08	2603.16142	Parametric Social Identity Injection and Diversification in Public Opinion Simulation	Hexi Wang et al.	arXiv	1
2026-06-08	2605.26046	When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judges	Parth Darshan et al.	arXiv	1
2026-06-08	2603.20990	ECI_{sem}: Semantic Residual Effective Contrastive Information for Evaluating Hard Negatives	Aarush Sinha et al.	arXiv
2026-06-08	2605.28640	Augmenting Attention with Exponentially Decaying Memory Improves Query-Aware KV Sparsity	Xiuying Wei et al.	arXiv
2026-06-05	2606.06492	Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution	Liliana Hotsko et al.	arXiv	96
2026-06-05	2606.05553	ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?	Woojung Song et al.	arXiv	49
2026-06-05	2606.04743	TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration	Soyeong Jeong et al.	arXiv	47
2026-06-05	2606.05622	AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints	Jiayu Liu et al.	arXiv	44
2026-06-05	2606.05259	VideoKR: Towards Knowledge- and Reasoning-Intensive Video Understanding	Lin Fu et al.	arXiv	32
2026-06-05	2606.04703	Rethinking Continual Experience Internalization for Self-Evolving LLM Agents	Jingwen Chen et al.	arXiv	26
2026-06-05	2606.06428	Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation	Hanxu Hu et al.	arXiv	25
2026-06-05	2605.27079	Trust Region Q Adjoint Matching	Yonghoon Dong et al.	arXiv	24
2026-06-05	2606.06042	LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing	Jianzong Wu et al.	arXiv	24
2026-06-05	2606.06473	MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery	Shangheng Du et al.	arXiv	23
2026-06-05	2606.05275	Personal AI Agent for Camera Roll VQA	Thao Nguyen et al.	arXiv	19
2026-06-05	2606.06155	AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding	Qize Yu et al.	arXiv	18
2026-06-05	2606.03312	RobotValues: Evaluating Household Robots When Human Values Conflict	Jongwook Han et al.	arXiv	18
2026-06-05	2606.04811	Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?	Rui Zhao et al.	arXiv	17
2026-06-05	2606.06477	Complexity-Balanced Diffusion Splitting	Noam Issachar et al.	arXiv	17
2026-06-05	2606.02956	The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset	Richard Schwarzkopf et al.	arXiv	15
2026-06-05	2606.06416	Unsupervised Skill Discovery for Agentic Data Analysis	Zhisong Qiu et al.	arXiv	12
2026-06-05	2606.05979	World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis	Yi Yang et al.	arXiv	10
2026-06-05	2606.04880	MAOAM: Unified Object and Material Selection with Vision-Language Models	Jaden Park et al.	arXiv	9
2026-06-05	2606.06294	Towards One-to-Many Temporal Grounding	Qi Xu et al.	arXiv	8
2026-06-05	2606.06447	Latent Reasoning with Normalizing Flows	Guancheng Tu et al.	arXiv	8
2026-06-05	2606.06021	OPRD: On-Policy Representation Distillation	Shenzhi Yang et al.	arXiv	8
2026-06-05	2606.06286	LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs	Gianluca Barmina et al.	arXiv	7
2026-06-05	2605.30159	Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents	Ziyan Liu et al.	arXiv	7
2026-06-05	2606.04465	SePO: Self-Evolving Prompt Agent for System Prompt Optimization	Wangcheng Tao et al.	arXiv	7
2026-06-05	2606.03092	The Shadow Price of Reasoning: Economic Perspective on Optimal Budget Allocation for LLMs	Xu Wan et al.	arXiv	7
2026-06-05	2606.05254	Flash-WAM: Modality-Aware Distillation for World Action Models	Arman Akbari et al.	arXiv	7
2026-06-05	2606.05769	Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction	Tianxiang Jiang et al.	arXiv	7
2026-06-05	2606.03645	The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models	Liuyuan Wen et al.	arXiv	6
2026-06-05	2606.02569	AdaCodec: A Predictive Visual Code for Video MLLMs	Haowen Hou et al.	arXiv	6
2026-06-05	2606.01886	Absorbing Complexity: An Interaction-Native Knowledge Harness for Financial LLM Agents	Ailiya Borjigin et al.	arXiv	5
2026-06-05	2606.03940	SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction	Dan Jacobellis et al.	arXiv	5
2026-06-05	2606.06462	Benchmark Everything Everywhere All at Once	Shiyun Xiong et al.	arXiv	4
2026-06-05	2605.30794	MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding	Qian Kou et al.	arXiv	4
2026-06-05	2606.05846	Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs	Gio Paik et al.	arXiv	4
2026-06-05	2606.03841	EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management	Zherui Yang et al.	arXiv	4
2026-06-05	2606.04351	Video2LoRA: Parametric Video Internalization for Vision-Language Models	Manan Suri et al.	arXiv	4
2026-06-05	2606.05515	BRepCLIP: Contrastive Multimodal Pretraining on BRep Primitives for CAD Understanding	Muhammad Usama et al.	arXiv	3
2026-06-05	2606.05833	Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models	Haibo Wang et al.	arXiv	3
2026-06-05	2605.31058	Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination	Jiasheng Zheng et al.	arXiv	3
2026-06-05	2606.01317	SABER: Benchmarking Operational Safety of LLM Coding Agents in Stateful Project Workspaces	Qi Hu et al.	arXiv	2
2026-06-05	2606.06443	Revising Context, Shifting Simulated Stance: Auditing LLM-Based Stance Simulation in Online Discussions	Xinnong Zhang et al.	arXiv	2
2026-06-05	2606.00125	Multimodal Music Recommendation System using LLMs	Srikar Prabhas Kandagatla et al.	arXiv	2
2026-06-05	2606.05172	Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing	Yixuan Ding et al.	arXiv	2
2026-06-05	2606.05645	Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning	Ziyang Yao et al.	arXiv	2
2026-06-05	2606.06486	Regret Minimization with Adaptive Opponents in Repeated Games	Mingyang Liu et al.	arXiv	1
2026-06-05	2606.05557	AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents	Yang Li et al.	arXiv	1
2026-06-05	2606.00644	ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment	Qiuyu Tian et al.	arXiv	1
2026-06-05	2606.01753	Quality-Guided Semi-Supervised Learning for Medical Image Segmentation	Kumar Abhishek et al.	arXiv	1
2026-06-05	2605.30848	LLM Anonymization Against Agentic Re-Identification	Ziwen Li et al.	arXiv
2026-06-04	2606.02800	Cosmos 3: Omnimodal World Models for Physical AI	Aditi et al.	arXiv	142
2026-06-04	2606.05121	Audio Interaction Model	Zhifei Xie et al.	arXiv	88
2026-06-04	2606.02060	Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories	Jiaming Wang et al.	arXiv	58
2026-06-04	2606.04923	Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning	Xuekang Wang et al.	arXiv	42
2026-06-04	2606.03746	Qwen-Image-Flash: Beyond Objective Design	Tianhe Wu et al.	arXiv	37
2026-06-04	2606.03890	OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs	Yifei Li et al.	arXiv	31
2026-06-04	2606.05080	AutoLab: Can Frontier Models Solve Long-Horizon Auto Research and Engineering Tasks?	Zhangchen Xu et al.	arXiv	31
2026-06-04	2606.05158	Streaming Communication in Multi-Agent Reasoning	Zhen Yang et al.	arXiv	29
2026-06-04	2606.04527	Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation	Yuxuan Bian et al.	arXiv	28
2026-06-04	2606.04036	Self-Distilled Policy Gradient	Yifeng Liu et al.	arXiv	27
2026-06-04	2605.27492	Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems	Yipeng Ouyang et al.	arXiv	25
2026-06-04	2606.05008	M^3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks	Jie Huang et al.	arXiv	25
2026-06-04	2606.03503	ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning	Ziyan Liu et al.	arXiv	24
2026-06-04	2606.05102	ZipSplat: Fewer Gaussians, Better Splats	Alexander Veicht et al.	arXiv	22
2026-06-04	2606.03773	KletterMix: Climbing Toward High-Quality German Pretraining Data	Maurice Kraus et al.	arXiv	20
2026-06-04	2606.03197	MemTrain: Self-Supervised Context Memory Training	Ziheng Li et al.	arXiv	18
2026-06-04	2606.04513	MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation	Deguo Xia et al.	arXiv	17
2026-06-04	2606.02684	Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation	Yuying Li et al.	arXiv	16
2026-06-04	2606.01993	MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills?	Xinyu Che et al.	arXiv	16
2026-06-04	2606.03577	Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline Matching	Hao Zhong et al.	arXiv	14
2026-06-04	2606.03972	AAD-1: Asymmetric Adversarial Distillation for One-Step Autoregressive Video Generation	Haobo Li et al.	arXiv	13
2026-06-04	2606.04075	Large Language Models Hack Rewards, and Society	Wei Liu et al.	arXiv	10
2026-06-04	2606.02859	Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions	Zhenting Qi et al.	arXiv	10
2026-06-04	2606.03220	WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts	Yuxin Meng et al.	arXiv	10
2026-06-04	2605.30257	Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement Learning	Ciara Rowles et al.	arXiv	9
2026-06-04	2606.05160	GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors	Tianyi Xie et al.	arXiv	9
2026-06-04	2606.02993	Neural Networks Provably Learn Spectral Representations for Group Composition	Jianliang He et al.	arXiv	6
2026-06-04	2606.05009	DAR: Deontic Reasoning with Agentic Harnesses	Guangyao Dou et al.	arXiv	6
2026-06-04	2606.04688	MeshWeaver: Sparse-Voxel-Guided Surface Weaving for Autoregressive Mesh Generation	Jiale Xu et al.	arXiv	6
2026-06-04	2606.03031	AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification	Yan Wang et al.	arXiv	5
2026-06-04	2606.01166	BraveGuard: From Open-World Threats to Safer Computer-Use Agents	Yunhao Feng et al.	arXiv	5
2026-06-04	2606.01286	BenchEvolver: Frontier Task Synthesis via Solution-Centric Evolution	Yangzhen Wu et al.	arXiv	5
2026-06-04	2606.03712	When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models	Ding Zhang et al.	arXiv	3
2026-06-04	2606.03895	Agent libOS: A Library-OS-Inspired Runtime for Long-Running, Capability-Controlled LLM Agents	Yingqi Zhang	arXiv	3
2026-06-04	2605.31148	SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes	Tianhui Liu et al.	arXiv	3
2026-06-04	2605.30792	OpenSTBench: Beyond Semantic Evaluation for Speech Translation	Yanjie An et al.	arXiv	3
2026-06-04	2606.05165	STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations	Rishit Dagli et al.	arXiv	3
2026-06-04	2605.29489	Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging	Yuanyi Wang et al.	arXiv	3
2026-06-04	2606.01804	SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing	Hanlin Zhang et al.	arXiv	2
2026-06-04	2606.00825	SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory	Samiul Alam et al.	arXiv	2
2026-06-04	2605.31559	Functional Attention: From Pairwise Affinities to Functional Correspondences	Jiefang Xiao et al.	arXiv	2
2026-06-04	2606.05112	Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases	Cheng Liang et al.	arXiv	2
2026-06-04	2606.00188	PaintBench: Deterministic Evaluation of Precise Visual Editing	Kai Xu et al.	arXiv	2
2026-06-04	2606.04048	Unlocking Feature Learning in Gated Delta Networks at Scale	Yifeng Liu et al.	arXiv	2
2026-06-04	2606.01090	Measuring the Symmetry--Data Exchange Rate	Ahmed M. Adly	arXiv	1
2026-06-04	2605.31498	Scalable Inference-Time Annealing with Surrogate Likelihood Estimators	Daniel Peñaherrera et al.	arXiv	1
2026-06-04	2606.04978	Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game	Chensong Huang et al.	arXiv	1
2026-06-04	2606.00558	Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain	Yuan Yao et al.	arXiv	1
2026-06-04	2606.00477	Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs	Xin Gao et al.	arXiv	1
2026-06-04	2606.00377	Score-Control for Hallucination Reduction in Diffusion Models	Mahesh Bhosale et al.	arXiv	1
2026-06-04	2606.03965	Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning	Yu Xia et al.	arXiv
2026-06-04	2606.04056	Token Budgets: An Empirical Catalog of 63 LLM-Agent Budget-Overrun Incidents, with an Affine-Typed Rust Mitigation as a Case Study	Sajjad Khan	arXiv
2026-06-04	2606.03792	Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting	Georgios Tsoumplekas et al.	arXiv
2026-06-04	2606.05131	Deep Embedded Multiplicative DMD for Algebra-Preserving Koopman Learning	Kelan Gray et al.	arXiv
2026-06-03	2606.00683	OCC-RAG: Optimal Cognitive Core for Faithful Question Answering	Maksim Savkin et al.	arXiv	102
2026-06-03	2606.03458	KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks	Lorenz K. Muller et al.	arXiv	61
2026-06-03	2605.23895	From Activation to Causality: Discovery of Causal Visual Representations in the Human Brain	Yuval Golbari et al.	arXiv	52
2026-06-03	2606.03920	Benchmarking Visual State Tracking in Multimodal Video Understanding	Sihyun Yu et al.	arXiv	52
2026-06-03	2606.01249	Trust Region On-Policy Distillation	Xingrun Xing et al.	arXiv	46
2026-06-03	2606.03985	Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking	Zekun Qi et al.	arXiv	41
2026-06-03	2606.03979	Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories	Ali Behrouz et al.	arXiv	28
2026-06-03	2606.03603	World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning	Yucheng Zhou et al.	arXiv	27
2026-06-03	2606.03748	Ultralytics YOLO26: Unified Real-Time End-to-End Vision Models	Glenn Jocher et al.	arXiv	25
2026-06-03	2606.03264	PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training	Zelun Zhang et al.	arXiv	25
2026-06-03	2606.02398	A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL	Lei Yang et al.	arXiv	25
2026-06-03	2606.01955	WALL-WM: Carving World Action Modeling at the Event Joints	Shalfun Li et al.	arXiv	23
2026-06-03	2605.30288	MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection	Haowen Wang et al.	arXiv	21
2026-06-03	2606.01961	AutoMedBench: Towards Medical AutoResearch with Agentic AI Models	Junqi Liu et al.	arXiv	21
2026-06-03	2606.03159	NVIDIA OmniDreams: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation	NVIDIA et al.	arXiv	21
2026-06-03	2606.03911	Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching	Yoad Tewel et al.	arXiv	19
2026-06-03	2605.30039	Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning	Tong Ye et al.	arXiv	18
2026-06-03	2606.01717	Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging	Minsik Choi et al.	arXiv	18
2026-06-03	2606.01599	TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL	Tianze Yang et al.	arXiv	15
2026-06-03	2606.01048	Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation	Ziyue Lin et al.	arXiv	12
2026-06-03	2606.03102	Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling	Runpeng Dai et al.	arXiv	12
2026-06-03	2606.02754	Ψ-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues	Peixuan Han et al.	arXiv	12
2026-06-03	2606.01770	Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams	Zewen Liu et al.	arXiv	10
2026-06-03	2606.01788	PlatonicNav: Unveiling Semantic Correspondence in Navigation with Platonic Topological Maps	Junlin Long et al.	arXiv	10
2026-06-03	2606.04433	Stateful Visual Encoders for Vision-Language Models	Zirui Wang et al.	arXiv	7
2026-06-03	2606.01476	OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification	Yuhang Zhou et al.	arXiv	7
2026-06-03	2605.29288	Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces	Chen He et al.	arXiv	7
2026-06-03	2606.02461	AgentCL: Toward Rigorous Evaluation of Continual Learning in Language Agents	Yiheng Shu et al.	arXiv	5
2026-06-03	2606.00386	αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion	Xiang Zhang et al.	arXiv	5
2026-06-03	2605.27346	MERIT: Learning Disentangled Music Representations for Audio Similarity	Abhinaba Roy et al.	arXiv	5
2026-06-03	2606.03928	Value-Aware Stochastic KV Cache Eviction for Reasoning Models	Ting-Yun Chang et al.	arXiv	5
2026-06-03	2606.03029	Conditional Hypothesis Generation for LLM-Based Text Analysis with Researcher-Specified Covariates	Paiheng Xu et al.	arXiv	4
2026-06-03	2606.02578	Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling	Seojeong Park et al.	arXiv	4
2026-06-03	2606.04455	The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?	Xinyu Lu et al.	arXiv	3
2026-06-03	2606.04889	GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards	Tej Deep Pala et al.	arXiv	2
2026-06-03	2606.00138	A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics Problems	Titu Ranjan Sarker et al.	arXiv	2
2026-06-03	2606.01494	ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree	Vincent Koc et al.	arXiv	2
2026-06-03	2606.03348	SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation	Junxiao Yang et al.	arXiv	1
2026-06-03	2605.30581	Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes	Chenxi Tao et al.	arXiv	1
2026-06-03	2606.03287	BA-T: An Iterative Transformer for Two-View Bundle Adjustment	Ganlin Zhang et al.	arXiv	1
2026-06-03	2606.02775	AURA: Action-Gated Memory for Robot Policies at Constant VRAM	Josef Chen	arXiv
2026-06-03	2605.27958	Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations	Sachin Kumar	arXiv
2026-06-02	2606.02437	On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters	Mind Lab et al.	arXiv	103
2026-06-02	2605.28556	A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks	Tomer Keren et al.	arXiv	73
2026-06-02	2605.29707	Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding	Jianuo Huang et al.	arXiv	62
2026-06-02	2606.00408	Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism	Haoxiang Zhang et al.	arXiv	61
2026-06-02	2606.02404	K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts	Nahyun Lee et al.	arXiv	56
2026-06-02	2605.30611	Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs	Haozhe Zhao et al.	arXiv	49
2026-06-02	2606.02373	Harness-1: Reinforcement Learning for Search Agents with State-Externalizing Harnesses	Pengcheng Jiang et al.	arXiv	44
2026-06-02	2605.29343	Draft-OPD: On-Policy Distillation for Speculative Draft Models	Haodi Lei et al.	arXiv	33
2026-06-02	2606.01311	SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories	Zhuoyun Yu et al.	arXiv	32
2026-06-02	2605.24956	NITP: Next Implicit Token Prediction for LLM Pre-training	Xiangdong Zhang et al.	arXiv	32
2026-06-02	2606.02482	X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding	Peiwen Sun et al.	arXiv	31
2026-06-02	2606.01247	Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?	Liyang Li et al.	arXiv	26
2026-06-02	2606.02564	VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization	Junhao Cheng et al.	arXiv	25
2026-06-02	2605.30351	VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion	Hidir Yesiltepe et al.	arXiv	21
2026-06-02	2606.02031	OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents	Rui Yang et al.	arXiv	20
2026-06-02	2605.28132	Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models	Haozhan Shen et al.	arXiv	20
2026-06-02	2606.02553	LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation	Qixin Hu et al.	arXiv	17
2026-06-02	2605.24202	When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs	Yifan Zeng et al.	arXiv	17
2026-06-02	2605.29860	ESPO: Early-Stopping Proximal Policy Optimization	Zihang Li et al.	arXiv	17
2026-06-02	2606.02470	MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation	Wenhao Wang et al.	arXiv	13
2026-06-02	2605.30723	Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents	Jianxiang Yu et al.	arXiv	13
2026-06-02	2605.25659	StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration	Linrui Tian et al.	arXiv	13
2026-06-02	2606.01528	Joint Agent Memory and Exploration Learning via Novelty Signals	Shizuo Tian et al.	arXiv	12
2026-06-02	2606.02320	TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation	Xinkai Ma et al.	arXiv	11
2026-06-02	2605.29588	Brain-IT-VQA: From Brain Signals to Answers	Roman Beliy et al.	arXiv	11
2026-06-02	2605.30931	MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft	Tianjie Ju et al.	arXiv	9
2026-06-02	2606.01414	Agent Skills Should Go Beyond Text: The Case for Visual Skills	Binxiao Xu et al.	arXiv	8
2026-06-02	2605.30126	PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding	Selim Kuzucu et al.	arXiv	8
2026-06-02	2605.30501	Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs	Zhihao Wu et al.	arXiv	7
2026-06-02	2606.00828	RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes	Leyi Wu et al.	arXiv	7
2026-06-02	2605.30852	Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism	Yijiong Yu et al.	arXiv	7
2026-06-02	2606.02551	AFUN: Towards an Affordance Foundation Model for Functionality Understanding	Zhaoning Wang et al.	arXiv	6
2026-06-02	2605.26248	Unified Neural Scaling Laws	Ethan Caballero et al.	arXiv	6
2026-06-02	2605.31529	SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence	Yulu Pan et al.	arXiv	5
2026-06-02	2606.02388	Policy and World Modeling Co-Training for Language Agents	Ning Lu et al.	arXiv	5
2026-06-02	2605.31597	SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models	Olaf Dünkel et al.	arXiv	5
2026-06-02	2606.00660	FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search	James Xu Zhao et al.	arXiv	5
2026-06-02	2605.29992	Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation	M. Ali Bayram et al.	arXiv	5
2026-06-02	2606.01682	Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning	Atoosa Chegini et al.	arXiv	5
2026-06-02	2606.01533	Multi-Agent Computer Use	Jing Yu Koh et al.	arXiv	5
2026-06-02	2606.01057	3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code	Yipeng Gao et al.	arXiv	5
2026-06-02	2605.24614	Measuring the Depth of LLM Unlearning via Activation Patching	Jaeung Lee et al.	arXiv	4
2026-06-02	2606.00240	MindZero: Learning Online Mental Reasoning With Zero Annotations	Shunchi Zhang et al.	arXiv	3
2026-06-02	2605.31057	LVSA: Training-Free Sparse Attention for Long Video Diffusion	Gael Glorian et al.	arXiv	3
2026-06-02	2606.02580	Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models	Guangzhao He et al.	arXiv	3
2026-06-02	2606.01336	LongAttnComp: Cross-Family Context Compression for Long-Context Reasoning	Mengmeng Ji et al.	arXiv	3
2026-06-02	2606.02277	RoboSemanticBench: Diagnosing Semantic Grounding in Action Prediction for VLA Models	Bin Yu et al.	arXiv	3
2026-06-02	2605.29318	FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes	Donglai Xiang et al.	arXiv	2
2026-06-02	2605.09156	Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan	Ahan Chatterjee et al.	arXiv	2
2026-06-02	2605.21102	ACL-Verbatim: hallucination-free question answering for research	Gábor Recski et al.	arXiv	2
2026-06-02	2605.16745	EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers	Zongyuan Yang et al.	arXiv	2
2026-06-02	2606.01348	ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats	Shangpin Peng et al.	arXiv	2
2026-06-02	2605.25381	Not only where, But when: Temporal Scheduling for RLVR	Jinghao Zhang et al.	arXiv	2
2026-06-02	2606.01132	HakushoBench: A Japanese Chart and Table VQA Benchmark from Governmental White Papers	Issa Sugiura et al.	arXiv	2
2026-06-02	2606.01666	DOT-MoE: Differentiable Optimal Transport for MoEfication	Udbhav Bamba et al.	arXiv	1
2026-06-02	2605.29084	Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG	Yubo Li et al.	arXiv	1
2026-06-02	2605.29087	The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure	Yubo Li et al.	arXiv	1
2026-06-02	2606.01027	τ_0-WM: A Unified Video-Action World Model for Robotic Manipulation	Pengfei Zhou et al.	arXiv	1
2026-06-02	2605.28897	Review Arcade: On the Human Alignment and Gameability of LLM Reviews	Hans Ole Hatzel et al.	arXiv	1
2026-06-02	2606.02255	Who Annotates in NLP? A Large-scale Assessment of Human Annotation Reporting between 2018 and 2025	Maria Kunilovskaya et al.	arXiv	1
2026-06-02	2606.01356	A Formally Verified Library of Mathematical Finance in Lean 4	Raphael Coelho	arXiv	1
2026-06-02	2605.28983	The Hamilton-Jacobi Theory of Deep Learning	Jose Marie Antonio Miñoza et al.	arXiv	1
2026-06-02	2606.00761	Confidence-Adaptive SwiGLU for Mixture-of-Experts	Shaohua Li et al.	arXiv	1
2026-06-02	2606.00090	Silent Failures in Physical AI: A Literature Review of Runtime Action Authorization for Autonomous Systems	Barak Or	arXiv	1
2026-06-02	2606.00089	Can Predicted Dynamics Exist in the Physical World?	Barak Or	arXiv	1
2026-06-02	2606.00267	StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement	Junwon Seo et al.	arXiv	1
2026-06-02	2605.27921	Show, Don't TELL: Explainable AI-Generated Text Detection	Aldan Creo et al.	arXiv
2026-06-02	2605.30608	Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures	Varsha Suresh et al.	arXiv
2026-06-02	2606.00285	Model-Based Quality Assessment for Massively Multilingual Parallel Data	Abdelaziz M. A. Ibrahim et al.	arXiv
2026-06-02	2605.28255	AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering?	Maharshi Gor et al.	arXiv
2026-06-02	2606.02248	Geometric Latent Reasoning Induces Shorter Generations in LLMs	Shashi Kumar et al.	arXiv
2026-06-02	2605.28615	Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization	Zhuohan Liu et al.	arXiv
2026-06-01	2605.31264	COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation	Tianyi Zhou et al.	arXiv	123
2026-06-01	2605.31159	Trust-Region Behavior Blending for On-Policy Distillation	Daniil Plyusov et al.	arXiv	64
2026-06-01	2605.31604	Representation Forcing for Bottleneck-Free Unified Multimodal Models	Yuqing Wang et al.	arXiv	61
2026-06-01	2605.29307	GrepSeek: Training Search Agents for Direct Corpus Interaction	Alireza Salemi et al.	arXiv	58
2026-06-01	2605.31268	Mellum2 Technical Report	Marko Kojic et al.	arXiv	55
2026-06-01	2605.30993	SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue	Ruiqi Li et al.	arXiv	54
2026-06-01	2605.31039	GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration	Xiangtao Kong et al.	arXiv	43
2026-06-01	2605.31075	Task-Focused Memorization for Multimodal Agents	Tao Zou et al.	arXiv	39
2026-06-01	2605.31584	LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards	Nianyi Lin et al.	arXiv	39
2026-06-01	2605.30409	SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer	Yuyang Zhao et al.	arXiv	38
2026-06-01	2605.30819	Function2Scene: 3D Indoor Scene Layout from Functional Specifications	Ruiqi Wang et al.	arXiv	38
2026-06-01	2605.30940	Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer	Ke Lei et al.	arXiv	33
2026-06-01	2605.30876	dMoE: dLLMs with Learnable Block Experts	Sicheng Feng et al.	arXiv	31
2026-06-01	2605.28618	Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios	Changhao Pan et al.	arXiv	28
2026-06-01	2605.31433	SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks	Wai-Chung Kwan et al.	arXiv	24
2026-06-01	2605.30561	VLM3: Vision Language Models Are Native 3D Learners	Zhipeng Cai et al.	arXiv	24
2026-06-01	2605.26844	Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation	Yuanyi Wang et al.	arXiv	22
2026-06-01	2605.30621	Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents	Minhua Lin et al.	arXiv	21
2026-06-01	2605.30407	Exploring Autonomous Agentic Data Engineering for Model Specialization	Yujie Luo et al.	arXiv	21
2026-06-01	2605.29796	SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search	Yunbo Tang et al.	arXiv	18
2026-06-01	2605.30434	LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis	Kewei Xu et al.	arXiv	18
2026-06-01	2605.31029	PEEK: Picking Essential frames via Efficient Knowledge distillation	Killian Steunou et al.	arXiv	16
2026-06-01	2605.31042	From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors	Jiejun Tan et al.	arXiv	16
2026-06-01	2605.02772	Linearizing Vision Transformer with Test-Time Training	Yining Li et al.	arXiv	15
2026-06-01	2605.31336	DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory	Zhenhao Yang et al.	arXiv	10
2026-06-01	2605.17543	HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos	Jeongeun Park et al.	arXiv	9
2026-06-01	2605.31598	Linear Scaling Video VLMs for Long Video Understanding	Cristobal Eyzaguirre et al.	arXiv	9
2026-06-01	2605.30834	Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring	Seongheon Park et al.	arXiv	8
2026-06-01	2605.31170	Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight Evasion	Stine Lyngsø Beltoft et al.	arXiv	7
2026-06-01	2605.30557	Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?	Yue Zhang et al.	arXiv	7
2026-06-01	2605.30846	Count Anything	Mengqi Lei et al.	arXiv	7
2026-06-01	2605.31577	SurGe: Improved Surface Geometry in Point Maps	Karim Knaebel et al.	arXiv	6
2026-06-01	2605.28657	DEMON: Diffusion Engine for Musical Orchestrated Noise	Ryan Fosdick	arXiv	6
2026-06-01	2605.26112	From Model Scaling to System Scaling: Scaling the Harness in Agentic AI	Shangding Gu	arXiv	5
2026-06-01	2605.30888	The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement	Xiaobo Wang et al.	arXiv	5
2026-06-01	2605.23657	OpenSkillEval: Automatically Auditing the Open Skill Ecosystem for LLM Agents	Jiahao Ying et al.	arXiv	5
2026-06-01	2605.23458	One-Forcing: Towards Stable One-Step Autoregressive Video Generation	Jiaqi Feng et al.	arXiv	4
2026-06-01	2605.31535	RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video	Ulrich Prestel et al.	arXiv	4
2026-06-01	2605.29398	GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models	Xiaohang Tang et al.	arXiv	4
2026-06-01	2605.30329	SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?	Sy-Tuyen Ho et al.	arXiv	4
2026-06-01	2605.31455	DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization	Jian Mu et al.	arXiv	4
2026-06-01	2605.29447	Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents	Tianpeng Bu et al.	arXiv	4
2026-06-01	2605.30011	VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies	Mingjian Gao et al.	arXiv	3
2026-06-01	2605.31096	iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning	Chang-Bin Zhang et al.	arXiv	3
2026-06-01	2605.29488	AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling	Yiheng Li et al.	arXiv	3
2026-06-01	2605.30514	MAAT: Multi-phase Adapter-Aware Targeted Unlearning	Suryash Yagnik et al.	arXiv	3
2026-06-01	2605.31158	Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models	Jiacheng Lu et al.	arXiv	3
2026-06-01	2605.31603	Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models	Jiazheng Xing et al.	arXiv	3
2026-06-01	2605.29429	One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation	Sanghyun Jo et al.	arXiv	2
2026-06-01	2605.31503	How can embedding models bind concepts?	Arnas Uselis et al.	arXiv	2
2026-06-01	2605.24442	Benchmarking Composed Image Retrieval for Applied Earth Observation	Bill Psomas et al.	arXiv	2
2026-06-01	2605.28992	FRAPPE: Full Input, Residual Output Autoencoding with Projection Pursuit Encoder	Dan Jacobellis et al.	arXiv	2
2026-06-01	2605.28730	AlphaTransit: Learning to Design City-scale Transit Routes	Bibek Poudel et al.	arXiv	1
2026-06-01	2605.28181	When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language Models	Jungwon Park et al.	arXiv	1
2026-06-01	2605.26562	Beyond Holistic Models: Systematic Component-level Benchmarking of Deep Multivariate Time-Series Forecasting	Shuang Liang et al.	arXiv	1
2026-06-01	2605.21625	Flat-Pack Bench: Evaluating Spatio-Temporal Understanding in Large Vision-Language Models through Furniture Assembly	Aditya Chetan et al.	arXiv	1
2026-06-01	2605.29411	The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction	Shu Wan et al.	arXiv	1
2026-06-01	2605.28969	Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization	Aarik Gulaya	arXiv
2026-06-01	2605.29198	Guidance Contrastive Token Credit Assignment for Discrete Policy Optimization	Shufan Li et al.	arXiv
2026-06-01	2605.30571	Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM Decode	Josef Chen	arXiv
2026-06-01	2605.15779	A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking	Jianlin Ye et al.	arXiv
2026-06-01	2605.27919	Frequency-Guided Action Diffusion via Sub-Frequency Manifold Traversal	Junlin Wang	arXiv