2026-07 papers

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

2026-07 · 602 records

date	id	title	authors	venue	↑
2026-07-31	2607.26760	Metis: Memory Foundation Model	Zeyu Zhang et al.	arXiv	154
2026-07-31	2607.28568	Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering	Junlin Yang et al.	arXiv	150
2026-07-31	2607.28227	Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents	Hanzhang Zhou et al.	arXiv	107
2026-07-31	2607.28624	PhiZero: A World Model Built Around Physical Language	Shuyao Shang et al.	arXiv	104
2026-07-31	2607.27919	Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory	Rubin Wei et al.	arXiv	60
2026-07-31	2607.27380	VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System	Haodong Li et al.	arXiv	56
2026-07-31	2607.28595	Beacon: Knowing When and How to Perform Agentic Visual Reasoning	Qixun Wang et al.	arXiv	55
2026-07-31	2607.26497	BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms	Pengyu Wang et al.	arXiv	52
2026-07-31	2607.28625	ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine	Yukang Cao et al.	arXiv	46
2026-07-31	2607.28022	Flux-OPD: On-Policy Distillation with Evolving Contexts	Yuran Wang et al.	arXiv	45
2026-07-31	2607.27616	MPIE-Bench: Benchmarking Anatomically Plausible Multi-Person Interaction Editing	Jiajia Lin et al.	arXiv	39
2026-07-31	2607.28618	AskChem: Claim-Centered Infrastructure for Chemistry Literature Synthesis	Bing Yan et al.	arXiv	36
2026-07-31	2607.27816	Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation	Yuhang Zhu et al.	arXiv	33
2026-07-31	2607.28509	RefCaptioner: Multi-Reference Image-Grounded Video Captioning	Tengfei Liu et al.	arXiv	28
2026-07-31	2607.28582	β-OPSD: Deriving with Policy Optimization, Training with Self-Distillation	Jiawei Xu et al.	arXiv	24
2026-07-31	2607.26769	See2Think: Do Multimodal Models Really Use Intermediate Visual States?	Siyu Yan et al.	arXiv	24
2026-07-31	2607.27703	SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them	Yang Zhou et al.	arXiv	24
2026-07-31	2607.28611	Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers	Chongjian Ge et al.	arXiv	22
2026-07-31	2607.28362	ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow	Jin Cao et al.	arXiv	21
2026-07-31	2607.27958	Σ-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems	Peilin Feng et al.	arXiv	17
2026-07-31	2607.27372	Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation	Alexi Gladstone et al.	arXiv	17
2026-07-31	2607.26056	INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models	Junhan Sun et al.	arXiv	16
2026-07-31	2607.28272	MemHarness: Memory Is Reconstructed, Not Replayed	Rong Wu et al.	arXiv	16
2026-07-31	2607.28410	Can Large Language Models Execute Parent Orders?	Zane Shen et al.	arXiv	15
2026-07-31	2607.28374	LEDGERMIND: Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger	Enjun Du et al.	arXiv	13
2026-07-31	2607.26637	Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability	Sizhe Zhou et al.	arXiv	12
2026-07-31	2607.27230	Multi-Head Attention Residuals	Cheng Luo et al.	arXiv	11
2026-07-31	2607.28074	Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale	Yash Pandya et al.	arXiv	11
2026-07-31	2607.28627	ReToken: One Token to Improve Vision-Language Models for Visual Retrieval	Yao Xiao et al.	arXiv	8
2026-07-31	2607.26627	Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes	Tianyu Wang et al.	arXiv	7
2026-07-31	2607.23193	OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models	Jinsen Su et al.	arXiv	6
2026-07-31	2607.27652	Harness-G: A Graph-Structured Harness for Search Agents	Yanning Hou et al.	arXiv	5
2026-07-31	2607.28308	Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing	Huiyuan Tian et al.	arXiv	4
2026-07-31	2607.20891	Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions	Pengyu Zhu et al.	arXiv	4
2026-07-31	2607.18806	AI Tour Meeting: Group Travel Planning by LLM Agents	Daisuke Kikuta	arXiv	4
2026-07-31	2607.28319	Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations	Pere Martra et al.	arXiv	3
2026-07-31	2607.25289	AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition	Yuqi Li et al.	arXiv	2
2026-07-31	2607.16922	Pedestrian Archetypes Extension -- More Pedestrian Models for Autonomous Vehicle Safety Testing	Taorui Huang et al.	arXiv	1
2026-07-30	2607.27180	HumanCLAW: Can Vision-Language Models Act Through a Body?	Siyao Li et al.	arXiv	73
2026-07-30	2607.25675	DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space	Jiangwang Chen et al.	arXiv	65
2026-07-30	2607.27205	TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM	Hengyi Xie et al.	arXiv	57
2026-07-30	2607.25294	CLBench-V: Evaluating Multimodal Context Learning from Grounding to Knowledge Acquisition	Lai Wei et al.	arXiv	45
2026-07-30	2607.25308	CAST: Game Solvers as Turn-Level Teachers for LLM Agents	Yu Wang et al.	arXiv	41
2026-07-30	2607.25659	CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization	Bo-Wen Zhang et al.	arXiv	32
2026-07-30	2607.27146	MindForge: Teaching Small Language Models Whole-Life-Cycle Software Engineering via Source-Free Program Synthesis	Yihao Chen et al.	arXiv	28
2026-07-30	2607.26784	SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution	Zhiyuan Yao et al.	arXiv	27
2026-07-30	2607.27167	SpecFirst: Behavioral Specification Elicitation as a First-Class Step in Agent-Based Program Synthesis from Scratch	Yihao Chen et al.	arXiv	17
2026-07-30	2607.26754	StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation	Zijun Lin et al.	arXiv	17
2026-07-30	2607.27191	Can AI agents conduct open-ended AI research? Early evidence from two case studies	Peter Kirgis et al.	arXiv	16
2026-07-30	2607.27278	OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation	Kaiyu Li et al.	arXiv	14
2026-07-30	2607.27155	OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding	Jingbo Zhou et al.	arXiv	12
2026-07-30	2607.25380	Memory for Large Language Models	Sining Zhoubian et al.	arXiv	11
2026-07-30	2607.26410	Voice Memory for Agentic Speech Recognition	Chao-Han Huck Yang et al.	arXiv	10
2026-07-30	2607.26115	GPT-Red: Automated Red Teaming via Self-Play at Scale	Eric Wallace et al.	arXiv	9
2026-07-30	2607.26811	DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation	Jiaxing Li et al.	arXiv	6
2026-07-30	2607.16955	CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation	Satyam Kumar et al.	arXiv	6
2026-07-30	2607.25802	Explicit Layer Modeling for Video Object Insertion and Layer Decomposition	Kyujin Han et al.	arXiv	6
2026-07-30	2607.26055	πR^2: Reactive Real-time Flow Policies	Sungjae Park et al.	arXiv	5
2026-07-30	2607.26791	SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response	Lehan Wang et al.	arXiv	3
2026-07-30	2607.26314	StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents	Ads Dawson et al.	arXiv	3
2026-07-30	2607.24117	Grading the Narrators: An Isnad-Rijal Framework for Claim-Level Provenance in Multi-Agent Knowledge Systems	Ali Zahid Raja	arXiv	2
2026-07-29	2607.25431	CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents	Zhongming Yu et al.	arXiv	110
2026-07-29	2607.24223	A New Role for Relevance: Guiding Corpus Interaction in Agentic Search	Jiangnan Li et al.	arXiv	84
2026-07-29	2607.25895	HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone	Simple AI et al.	arXiv	61
2026-07-29	2607.25565	ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition	Jooyeol Yun et al.	arXiv	55
2026-07-29	2607.24904	Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model	Senqiao Yang et al.	arXiv	38
2026-07-29	2607.26057	Pass the Baton: Trajectory-Relayed On-Policy Distillation	Haolei Xu et al.	arXiv	30
2026-07-29	2607.24368	Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory	Ruizhe Li et al.	arXiv	30
2026-07-29	2607.25857	Shieldstral	Antonia Calvi et al.	arXiv	22
2026-07-29	2607.25537	Visual prompt engineering for video models	Robert Geirhos et al.	arXiv	19
2026-07-29	2607.26037	Wonder: Video World Model Done Better	Jiacong Xu et al.	arXiv	19
2026-07-29	2607.26004	Parallel Decoding Distillation for Fast Image and Video Generation	Neta Shaul et al.	arXiv	16
2026-07-29	2607.24957	PerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language Models	Zichao Lin et al.	arXiv	16
2026-07-29	2607.25948	MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities	Mingqiao Ye et al.	arXiv	13
2026-07-29	2607.25970	Reinforcement Learning for Code Optimization	Pierre Chambon et al.	arXiv	12
2026-07-29	2607.23514	Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking	Haorui He et al.	arXiv	12
2026-07-29	2607.25669	OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs	Haoyang Huang et al.	arXiv	6
2026-07-29	2607.25091	Towards Robust Reinforcement Learning for Small-Scale Language Model Agents	Md Rezwanul Haque et al.	arXiv	6
2026-07-29	2607.17674	Uncovering Latent Reasoning Strategies in Language Models	Awni Altabaa et al.	arXiv	4
2026-07-29	2607.25236	VisualPatchWorld: Code World Models as Latent Structured Representations for Planning	Jiaxin Bai et al.	arXiv	4
2026-07-29	2607.25337	Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control	Jiaxin Bai et al.	arXiv	4
2026-07-29	2607.24882	Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents	Bowen Qin et al.	arXiv	3
2026-07-29	2607.24176	Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization	Alexey Gavrilov et al.	arXiv	3
2026-07-29	2607.25310	Human-in-the-Loop Signature Bootstrapping for UAV Hyperspectral PFM-1 Mine Detection	Sagar Lekhak et al.	arXiv	2
2026-07-29	2607.19712	How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF	Venkata Naga Sai Vishnu Rohit Pulipaka et al.	arXiv	2
2026-07-29	2607.25572	Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion	Cédric Bonhomme et al.	arXiv	2
2026-07-29	2607.25108	OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis	Zihan Li et al.	arXiv	1
2026-07-29	2607.22135	GLI-AL: A Multi-Modal Glioma MRI Label Resource with Unified Anatomy-Lesion Labels	Xingyu Xiang et al.	arXiv	1
2026-07-29	2607.22117	Projection Pursuit CPCANet for Domain Generalization	Yu-Hsi Chen et al.	arXiv
2026-07-29	2607.12544	Edge-Aware Thermal Infrared UAV Swarm Tracking	Yu-Hsi Chen	arXiv
2026-07-28	2607.24653	Kimi K3: Open Frontier Intelligence	Kimi Team et al.	arXiv	526
2026-07-28	2607.23588	JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents	Yunlong Lin et al.	arXiv	84
2026-07-28	2607.24280	From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search	Junlin Liu et al.	arXiv	81
2026-07-28	2607.21655	Progress Reward Modeling for Robotic Learning: A Comprehensive Survey	Jianshu Zhang et al.	arXiv	78
2026-07-28	2607.22798	StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents	Yan Yang et al.	arXiv	62
2026-07-28	2607.24731	Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation	Bingnan Li et al.	arXiv	44
2026-07-28	2607.24027	Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification	Haopeng Li et al.	arXiv	38
2026-07-28	2607.24744	Data Pyramid for Embodied Manipulation	Yifan Ye et al.	arXiv	36
2026-07-28	2607.21694	Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On	Yong Liu et al.	arXiv	28
2026-07-28	2607.24720	The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation	Tianyi Men et al.	arXiv	27
2026-07-28	2607.23855	OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation	Jun Zhan et al.	arXiv	27
2026-07-28	2607.24743	ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding	Hangjie Yuan et al.	arXiv	12
2026-07-28	2607.21936	Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models	Gabeen Kim et al.	arXiv	11
2026-07-28	2607.22148	dRAE: Representation Autoencoder with Hyper-Spherical Codes	Tianren Ma et al.	arXiv	10
2026-07-28	2607.23518	Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed Sampling	Hengyuan Cao et al.	arXiv	8
2026-07-28	2607.23909	WorldDiT: A Unified Diffusion Architecture for World and Action Modeling	Sen Wang et al.	arXiv	7
2026-07-28	2607.23402	Characterizing Warp Divergence from Pascal to Blackwell	Alpin Dale	arXiv	7
2026-07-28	2607.22098	Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reasoning Models	Junlin Fang et al.	arXiv	7
2026-07-28	2607.22561	Codifying the Judge: Scalable Evaluation via Program Distillation	Tzu-Heng Huang et al.	arXiv	7
2026-07-28	2607.23806	A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever	Sietse Schelpe	arXiv	7
2026-07-28	2607.24516	DecoupleMix: Decoupled Ratio Search and Convex Allocation for Scalable VLM Data Recipes	Jiahao Xie et al.	arXiv	7
2026-07-28	2607.23687	GNM Head: A Generative aNthropometric Model of the human head	Stylianos Ploumpis et al.	arXiv	6
2026-07-28	2607.24241	FilmBench: A Film-Grade Benchmark for Cinematic Video Generation	Shengyi Wang et al.	arXiv	6
2026-07-28	2607.23373	UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models	Ioannis Maniadis Metaxas et al.	arXiv	5
2026-07-28	2607.22682	A Vocabulary for Multi-Agent Automated Research Systems	Bardiya Akhbari	arXiv	5
2026-07-28	2607.22639	TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs	Sai Shruthi Sistla et al.	arXiv	4
2026-07-28	2607.23370	Bitcoin Price Direction Prediction via Regime-Aware Multi-Modal Fusion of Social Sentiment and Technical Features	Muhammad Abdullah Haroon	arXiv	3
2026-07-28	2607.24651	Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels	Zhuchenyang Liu et al.	arXiv	3
2026-07-28	2607.23242	IndicTalk: A Large-Scale Persona-Based Multilingual Conversational Corpus for Indic Languages	Sahil Deepak Gawande et al.	arXiv	3
2026-07-28	2607.21606	TILT: Improving Compositional Generation in Diffusion Models with a Model-Intrinsic Reward	Debottam Dutta et al.	arXiv	2
2026-07-28	2607.23822	DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification	Yuhang Wang et al.	arXiv	2
2026-07-27	2607.20465	DataPrep-Bench: Benchmarking LLMs as Training Data Preparators	Hao Liang et al.	arXiv	53
2026-07-27	2607.22529	Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills	Siyuan Huang et al.	arXiv	45
2026-07-27	2607.21653	Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning	Jian Hu et al.	arXiv	33
2026-07-27	2607.21503	Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems	Gaurav Dadhich	arXiv	28
2026-07-27	2607.22043	Scaling Native Multimodal Pre-Training From Scratch	Haoyuan Wu et al.	arXiv	28
2026-07-27	2607.22042	LAMAR: An Open Language-Aware Multilingual Alignment Reranker	Seongtae Hong et al.	arXiv	17
2026-07-27	2607.18198	Three-Body Scattering for Generative Modeling	Peng Sun et al.	arXiv	14
2026-07-27	2607.22830	ID-V2V: Identity-Preserving Video Restylization	Yuancheng Xu et al.	arXiv	10
2026-07-27	2607.14277	Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making	Amirhosein Ghasemabadi et al.	arXiv	9
2026-07-27	2607.22375	IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation	Varun Gumma et al.	arXiv	9
2026-07-27	2607.21848	Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering	Wenchao Ma et al.	arXiv	8
2026-07-27	2607.18314	Interactive Training 2: Auditable Control Plane for Live Model Training	Wentao Zhang et al.	arXiv	7
2026-07-27	2607.22393	SceneActBench: Can Agents Act on the 3D Scenes They See?	Yifei Zhao et al.	arXiv	7
2026-07-27	2607.22091	Spectral Prior for Reducing Exposure Bias in Diffusion Models	Yuya Kobayashi et al.	arXiv	5
2026-07-27	2607.12756	VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression	Yupeng Zheng et al.	arXiv	3
2026-07-27	2607.18142	O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning	Mei Yuan et al.	arXiv	2
2026-07-27	2607.19636	Multimodal Speaker Verification as a Threat to Speaker Anonymization	Ashi Garg et al.	arXiv	1
2026-07-24	2607.21461	AREX: Towards a Recursively Self-Improving Agent for Deep Research	Shuqi Lu et al.	arXiv	95
2026-07-24	2605.09635	K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs	Hao Liang et al.	arXiv	55
2026-07-24	2607.21556	Visual Contrastive Self-Distillation	Yijun Liang et al.	arXiv	47
2026-07-24	2607.20061	ReferTrack: Referring Then Tracking for Embodied Visual Tracking	Hanjing Ye et al.	arXiv	46
2026-07-24	2607.21553	SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation	Junsong Chen et al.	arXiv	38
2026-07-24	2607.20709	NVIDIA-labs OO Agents: Native Python Object-Oriented Agents	Paul Furgale et al.	arXiv	35
2026-07-24	2607.20734	LLMs Get Lost in Evolving User Intent	Jihoon Tack et al.	arXiv	22
2026-07-24	2607.20911	Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction	Tencent WorkBuddy Bench Team et al.	arXiv	22
2026-07-24	2607.21576	Self-Supervised Learning of Structured Dynamics from Videos	Lukas Knobel et al.	arXiv	20
2026-07-24	2607.21072	Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text	Xu Wang et al.	arXiv	19
2026-07-24	2607.21051	Sample-Efficient Learning from Agent Experience	Chenhui Gou et al.	arXiv	18
2026-07-24	2607.12746	Color Pass-Through via Camera-Display Coupling	Ruikang Li et al.	arXiv	18
2026-07-24	2607.21594	Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers	Sicheng Mo et al.	arXiv	13
2026-07-24	2607.21557	OpenForgeRL: Train Harness-native Agents in Any Environment	Xiao Yu et al.	arXiv	11
2026-07-24	2607.04763	Multi-Turn On-Policy Distillation with Prefix Replay	Baohao Liao et al.	arXiv	11
2026-07-24	2607.20785	Robostral Navigate	Arjun Majumdar et al.	arXiv	11
2026-07-24	2607.21580	GraphVid: Interactive Graph-Controllable Video Generation	Vedant Shah et al.	arXiv	9
2026-07-24	2607.10848	Predictive Divergence Masks for LLM RL	Xiangxin Zhou et al.	arXiv	9
2026-07-24	2607.19238	FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents	Xianfu Cheng et al.	arXiv	7
2026-07-24	2607.21485	Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation	Hyunmin Cho et al.	arXiv	7
2026-07-24	2607.21017	TableVerse: A Large-scale Tabletop Dataset with Real-world Grounded Layouts for Generalizable Manipulation	Boyuan Wang et al.	arXiv	6
2026-07-24	2607.16859	Dataset Distillation by Influence Matching	Haoru Tan et al.	arXiv	3
2026-07-23	2607.20145	SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD	Dongfang Li et al.	arXiv	66
2026-07-23	2607.19747	Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking	Kailin Jiang et al.	arXiv	28
2026-07-23	2607.20368	Self Gradient Forcing: Native Long Video Extrapolation	Junhao Zhuang et al.	arXiv	27
2026-07-23	2607.16165	An Exam for Active Observers	Jiarui Zhang et al.	arXiv	26
2026-07-23	2607.19604	Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models	Nischay Dhankhar et al.	arXiv	18
2026-07-23	2607.13429	Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment	Dwip Dalal et al.	arXiv	14
2026-07-23	2607.10169	Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization	Zhicheng Cai et al.	arXiv	13
2026-07-23	2607.21217	ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders	Zhongyuan Peng et al.	arXiv	8
2026-07-23	2607.20417	ATSplat: Compact Feed-forward 3D Gaussian Splatting with Adaptive Token Expansion	Cho In et al.	arXiv	8
2026-07-23	2607.19865	DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations	Jiazhen Jiang et al.	arXiv	7
2026-07-23	2607.16190	FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation	Hao Liu et al.	arXiv	7
2026-07-23	2607.20379	Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations	Hiskias Dingeto	arXiv	6
2026-07-23	2607.19691	SLPO: Scaling Latent Reasoning via a Surrogate Policy	Runyang You et al.	arXiv	6
2026-07-23	2607.17699	SLAM in Low-Light Environments: Project Report	Oleh Basystyi et al.	arXiv	4
2026-07-23	2607.19790	Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning	Md Tanvirul Alam	arXiv	4
2026-07-23	2607.18149	Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices	Shyamal Y. Dharia et al.	arXiv	3
2026-07-23	2607.18789	Moving Alphabet: A Controlled Study of Training Data for Text-to-Video Generation	Amber Yijia Zheng et al.	arXiv	3
2026-07-23	2607.19942	G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection	Yechan Kim et al.	arXiv	3
2026-07-23	2607.20207	SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments	Yang Xu et al.	arXiv	3
2026-07-23	2607.20092	ENTRAP-VL: A Taxonomic Probe for Dual Contextual Entrainment in Vision-Language Models	Karan Goyal et al.	arXiv	2
2026-07-22	2607.16617	DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines	Runming He et al.	arXiv	87
2026-07-22	2607.19191	ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU	Fan Jiang et al.	arXiv	84
2026-07-22	2607.18703	Generative World Renderer at the Speed of Play	Guixu Lin et al.	arXiv	83
2026-07-22	2607.19064	Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing	Xinjie Zhang et al.	arXiv	76
2026-07-22	2607.19139	Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers	Maohua Li et al.	arXiv	73
2026-07-22	2607.18367	AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report	AlayaWorld Team et al.	arXiv	61
2026-07-22	2607.18722	Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning	Junyao Yang et al.	arXiv	33
2026-07-22	2607.01774	Subliminal Clocks: Latent Time Modelling in Diffusion Language Models	Maximo Eduardo Rulli et al.	arXiv	32
2026-07-22	2607.18754	AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents	Kunlun Zhu et al.	arXiv	24
2026-07-22	2607.18091	SciForma: Structure-Faithful Generation of Scientific Diagrams	Yuxuan Luo et al.	arXiv	24
2026-07-22	2607.18839	HPD-Parsing: Hierarchical Parallel Document Parsing	Shu Wei et al.	arXiv	13
2026-07-22	2607.18603	AutoIndex: Learning Representation Programs for Retrieval	Sam O'Nuallain et al.	arXiv	11
2026-07-22	2607.19322	Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness	Xilun Chen et al.	arXiv	10
2026-07-22	2607.19343	Masked Visual Actions for Unified World Modeling	Hadi Alzayer et al.	arXiv	9
2026-07-22	2607.18955	H^2SD: Hybrid Hindsight Self-Distillation	Qiye Cai et al.	arXiv	8
2026-07-22	2607.19331	ISO: An RLVR-Native Optimization Stack	Hanqing Zhu et al.	arXiv	7
2026-07-22	2607.15491	Trajectory-aware Cross-view Geo-localization with Sequential Observations	Tianyi Gao et al.	arXiv	7
2026-07-22	2607.20058	Reading and Steering Representations of Materials-Science Mechanisms in an Open-Weight Language Model	Markus J. Buehler	arXiv	5
2026-07-22	2607.18934	Transcription Policy as a Latent Variable: Activating Controllable Verbatim ASR with Word-Level Timing	Laurin Wagner et al.	arXiv	5
2026-07-22	2607.19058	Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training	Nuemaan Malik	arXiv	5
2026-07-22	2607.18529	EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration	Jia-Kai Dong et al.	arXiv	5
2026-07-22	2607.19069	Delineate Anything v2: A Global Foundation Model for Field Delineation	Mykola Lavreniuk et al.	arXiv	4
2026-07-22	2607.19011	Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges	Tuo Liang et al.	arXiv	3
2026-07-22	2607.19344	Appearance Pointers -- Multimodal Region Control of Diffusion Transformers	Rahul Sajnani et al.	arXiv	3
2026-07-22	2607.17599	ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning	Ting Huang et al.	arXiv	2
2026-07-21	2607.07820	DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment	Xinyu Geng et al.	arXiv	94
2026-07-21	2607.17250	EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World	Qing Zong et al.	arXiv	87
2026-07-21	2607.17423	TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs	Yuhan Zhu et al.	arXiv	80
2026-07-21	2607.14183	Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning	Zishuo Li et al.	arXiv	66
2026-07-21	2607.17977	RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model	Kehan Li et al.	arXiv	54
2026-07-21	2607.18227	FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry	Dingyun Zhang et al.	arXiv	52
2026-07-21	2607.18217	HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enchancement	Yiyang Cai et al.	arXiv	51
2026-07-21	2607.18213	SWE-Pruner Pro: The Coder LLM Already Knows What to Prune	Yuhang Wang et al.	arXiv	46
2026-07-21	2607.10387	GigaChat Audio: Time-aware Large Audio Language Model	Aleksandr Kutsakov et al.	arXiv	37
2026-07-21	2607.10371	GigaAM Multilingual: Foundation Model for Underrepresented Languages	Andrei Kuzmenko et al.	arXiv	35
2026-07-21	2607.16850	Group Entropy-Controlled Policy Optimization	Guangran Cheng et al.	arXiv	29
2026-07-21	2607.16401	Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence	Runmao Yao et al.	arXiv	25
2026-07-21	2607.09759	ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams	Xiaokang Ma et al.	arXiv	25
2026-07-21	2607.15550	SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction	Xue Yu et al.	arXiv	20
2026-07-21	2607.16900	Environment-free Synthetic Data Generation for API-Calling Agents	Seanie Lee et al.	arXiv	20
2026-07-21	2607.13365	DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation	Eungjune Shim et al.	arXiv	19
2026-07-21	2607.14186	NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs	Jiarong Zhao et al.	arXiv	18
2026-07-21	2607.18110	LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks	Tianzhu Ye et al.	arXiv	16
2026-07-21	2607.18144	Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints	Thomas MacDougall et al.	arXiv	15
2026-07-21	2607.17097	HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis	Lingwei Dang et al.	arXiv	12
2026-07-21	2607.17247	Distilled Reinforcement Learning for LLM Post-training	Chen Wang et al.	arXiv	12
2026-07-21	2607.18171	FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications	Krish Agarwal et al.	arXiv	7
2026-07-21	2607.17972	DiFA: Inference-Time Forward-Process Alignment for Diffusion Models	Shigui Li et al.	arXiv	7
2026-07-21	2607.16204	Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL	Darshan Deshpande	arXiv	6
2026-07-21	2607.17675	ShotPlan: Cinematic Video Generation with Learnable Planning Token	Su Guo et al.	arXiv	6
2026-07-21	2607.17524	Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift	Zitong Huang et al.	arXiv	6
2026-07-21	2607.16609	Can Multimodal Large Language Models Understand OCT?	Baochen Fu et al.	arXiv	5
2026-07-21	2607.17146	The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture	Zhihua Liang	arXiv	5
2026-07-21	2607.18084	WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting	Zhaokai Wang et al.	arXiv	5
2026-07-21	2607.16074	JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models	Haoran Sun et al.	arXiv	5
2026-07-21	2607.16530	Nonuniformity Principle in Human-AI Coworking	An Luo et al.	arXiv	4
2026-07-21	2607.15434	Coercion and Deception in AI-to-AI Management: An Agentic Benchmark of Unprompted Escalation	Jasmine Brazilek et al.	arXiv	4
2026-07-21	2607.17790	ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video	Xiaozhong Lyu et al.	arXiv	4
2026-07-21	2607.07050	Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy Distillation	Jiabin Shen et al.	arXiv	4
2026-07-21	2607.17986	Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?	Yimeng Chen et al.	arXiv	4
2026-07-21	2607.09655	OpenLongTail: Generative Scaling of Long-Tail Driving Data	Lulin Liu et al.	arXiv	4
2026-07-21	2607.06306	UI2App: Benchmarking Visual Interaction Inference in Executable Web Application Generation	Grace Man Chen et al.	arXiv	3
2026-07-20	2607.11683	RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM	Mikhail Komarov et al.	arXiv	148
2026-07-20	2606.29538	RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources	Yijia Fan et al.	arXiv	88
2026-07-20	2607.15330	Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories	Xiaomi Robotics Team et al.	arXiv	70
2026-07-20	2607.14530	xHC: Expanded Hyper-Connections	Xiangdong Zhang et al.	arXiv	53
2026-07-20	2607.16051	Loop the Loopies!	Zitian Gao et al.	arXiv	51
2026-07-20	2607.15314	Cura 1T: Specialized Model for Agentic Healthcare	actAVA AI et al.	arXiv	50
2026-07-20	2607.15161	On-Policy Delta Distillation	Byeongho Heo et al.	arXiv	35
2026-07-20	2607.11699	Qwen-Music Technical Report	Jin Xu et al.	arXiv	33
2026-07-20	2607.16097	Understanding Reasoning from Pretraining to Post-Training	Jingyan Shen et al.	arXiv	27
2026-07-20	2607.15591	RecGPT-V3 Technical Report	Bowen Zheng et al.	arXiv	26
2026-07-20	2607.13196	From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality	Suzhen Zhong et al.	arXiv	25
2026-07-20	2607.15524	Recursive Harness Self-Improvement	Hyunin Lee et al.	arXiv	24
2026-07-20	2607.09082	REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation	Mantha Sai Gopal et al.	arXiv	23
2026-07-20	2607.16169	When Does Muon Help Agentic Reinforcement Learning?	Kai Ruan et al.	arXiv	14
2026-07-20	2607.14614	Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization	Weiwen Xu et al.	arXiv	11
2026-07-20	2607.15686	S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation	Jiahao Zhao et al.	arXiv	10
2026-07-20	2607.14088	VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders	Zhihao Xie et al.	arXiv	9
2026-07-20	2607.15901	DSWorld: A Data Science World Model for Efficient Autonomous Agents	Zherui Yang et al.	arXiv	9
2026-07-20	2607.16107	Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos	Sreyan Ghosh et al.	arXiv	9
2026-07-20	2607.15263	Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents	Paul Kassianik et al.	arXiv	6
2026-07-20	2607.11498	See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models	Byungkun Lee et al.	arXiv	5
2026-07-20	2607.07690	Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning	Vladislav Beliaev	arXiv	5
2026-07-20	2607.10966	SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning	Mingyuan Wu et al.	arXiv	4
2026-07-20	2607.06815	Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies	Barkha Rani	arXiv	4
2026-07-20	2607.13918	Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings	Jiangang Han	arXiv	2
2026-07-20	2607.11915	Benchmarking Sensor Robustness in Plasma Diagnostic Models: A Systematic Evaluation on TokaMark	Neerav Gupta	arXiv	2
2026-07-17	2607.14935	VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding	Xinhao Li et al.	arXiv	108
2026-07-17	2607.14777	SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning	Jinyang Wu et al.	arXiv	104
2026-07-17	2607.14952	LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget	Changhai Zhou et al.	arXiv	76
2026-07-17	2607.15257	SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration	Yuyao Zhang et al.	arXiv	69
2026-07-17	2607.15207	BadWAM: When World-Action Models Dream Right but Act Wrong	Qi Li et al.	arXiv	43
2026-07-17	2607.14202	KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation	Yuqi Tang et al.	arXiv	41
2026-07-17	2607.14076	From Pixels to States: Rethinking Interactive World Models as Game Engines	Zhen Li et al.	arXiv	31
2026-07-17	2607.14189	MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation	Xiaohan Zhang et al.	arXiv	30
2026-07-17	2607.14187	RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination	Haotian Liang et al.	arXiv	29
2026-07-17	2607.12800	UniVR: Thinking in Visual Space for Unified Visual Reasoning	Zhongwei Ren et al.	arXiv	29
2026-07-17	2607.13188	Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes	Minh-Quan Le et al.	arXiv	26
2026-07-17	2607.15038	Video = World + Event Stream	Lianghua Huang et al.	arXiv	22
2026-07-17	2607.13399	Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations	Rui Wang et al.	arXiv	17
2026-07-17	2607.15275	RoboTTT: Context Scaling for Robot Policies	Yunfan Jiang et al.	arXiv	17
2026-07-17	2607.13491	DeepLoop: Depth Scaling for Looped Transformers	Shuzhen Li et al.	arXiv	14
2026-07-17	2607.14749	WanSong v1.0 Technical Report	Binghui Chen et al.	arXiv	14
2026-07-17	2607.15273	MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators	Yushi Huang et al.	arXiv	12
2026-07-17	2607.12227	Rethinking the Evaluation of Harness Evolution for Agents	Yike Wang et al.	arXiv	8
2026-07-17	2607.03065	Spectral Rewiring for Exploration, Purification, and Model Merging	Zhilong Zhang et al.	arXiv	8
2026-07-17	2607.15278	Hierarchical Denoising For Multi-Step Visual Reasoning	Zezhong Qian et al.	arXiv	7
2026-07-17	2607.10995	AsySplat: Efficient Asymmetric 3D Gaussian Splatting for Long-Sequence Scene Modeling	Yingji Zhong et al.	arXiv	5
2026-07-17	2607.14660	VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance	Yunfeng Liu et al.	arXiv	5
2026-07-17	2607.10463	GRASP: GRanularity-Aware Search Policy for Agentic RAG	Varun Gandhi et al.	arXiv	5
2026-07-17	2607.14431	Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel	Sietse Schelpe	arXiv	5
2026-07-17	2607.14387	Chat2Scenic: An Iterative RAG-Based Framework for Scenario Generation in Autonomous Driving	Yuan Gao et al.	arXiv	4
2026-07-17	2607.14106	Token Time Continuous Diffusion for Language Modeling	Parikshit Bansal et al.	arXiv	4
2026-07-17	2607.15058	SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment	Saad Ejaz et al.	arXiv	4
2026-07-17	2607.15277	Partition, Prompt, Aggregate: Statistical Self-Consistency in Language Models	Patrik Wolf et al.	arXiv	4
2026-07-17	2607.09061	On Locality and Length Generalization in Visual Reasoning	Pulkit Madan et al.	arXiv	3
2026-07-16	2607.13125	Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget	Guoxuan Chen et al.	arXiv	125
2026-07-16	2607.13285	Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable	Ruhan Wang et al.	arXiv	115
2026-07-16	2607.12395	Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning	Xinyu Tang et al.	arXiv	90
2026-07-16	2607.12625	KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill	Yunxin Li et al.	arXiv	54
2026-07-16	2607.13639	OvisOCR2 Technical Report	Shiyin Lu et al.	arXiv	52
2026-07-16	2607.13705	AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities	Zichen Ding et al.	arXiv	39
2026-07-16	2607.13104	Self-Improvements in Modern Agentic Systems: A Survey	Zhe Ren et al.	arXiv	31
2026-07-16	2607.12000	MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors	Yufei Cai et al.	arXiv	30
2026-07-16	2607.13960	GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch	GigaWorld Team et al.	arXiv	25
2026-07-16	2605.16147	Registers Matter for Pixel-Space Diffusion Transformers	Nikita Starodubcev et al.	arXiv	18
2026-07-16	2607.12747	Tracing Agentic Failure from the Flow of Success	Samuel Yeh et al.	arXiv	16
2026-07-16	2607.13431	Discrete Diffusion Models: A Unified Framework from Tokenization to Generation	Ye Yuan et al.	arXiv	14
2026-07-16	2607.13124	ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation	Qingyu Zhang et al.	arXiv	14
2026-07-16	2607.12752	Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation	Hongbo Wang et al.	arXiv	13
2026-07-16	2607.13027	PalmClaw: A Native On-Device Agent Framework for Mobile Phones	Hongru Cai et al.	arXiv	8
2026-07-16	2607.11523	Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos	Gong Sitong et al.	arXiv	8
2026-07-16	2607.07702	From Noisy Traces to Root Causes: Structural Trajectory Analysis and Causal Extraction for Agent Optimization	Ying Chang et al.	arXiv	6
2026-07-16	2607.09786	Length Penalties Make Chain-of-Thought Less Monitorable	Bryce Little	arXiv	5
2026-07-16	2607.06701	SPEAR: A Simulator for Photorealistic Embodied AI Research	Mike Roberts et al.	arXiv	5
2026-07-16	2607.12477	Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence	Zhishan Zou et al.	arXiv	5
2026-07-16	2607.13921	Generative Compilation: On-the-Fly Compiler Feedback as AI Generates Code	Niels Mündler-Sasahara et al.	arXiv	4
2026-07-16	2605.10834	From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World	Pedro Conde et al.	arXiv	3
2026-07-16	2607.05910	PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails	Mingyang Song et al.	arXiv	3
2026-07-16	2607.13250	AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow	Salah Eddine Bekhouche et al.	arXiv	2
2026-07-15	2607.10400	SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding	Abhigya Verma et al.	arXiv	67
2026-07-15	2607.11886	Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation	Runhui Huang et al.	arXiv	57
2026-07-15	2607.05382	Search Beyond What Can Be Taught: Evolving the Knowledge Boundary in Agentic Visual Generation	Haozhe Wang et al.	arXiv	47
2026-07-15	2607.12463	Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models	Yubo Wang et al.	arXiv	41
2026-07-15	2607.11562	MonkeyOCRv2: A Visual-Text Foundation Model for Document AI	Yuliang Liu et al.	arXiv	34
2026-07-15	2607.08317	Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models	Matteo Santelmo et al.	arXiv	30
2026-07-15	2607.10522	Towards Autonomous and Auditable Medical Imaging Model Development	Shengyuan Liu et al.	arXiv	15
2026-07-15	2607.08168	MuScriptor: An Open Model for Multi-Instrument Music Transcription	Simon Rouard et al.	arXiv	14
2026-07-15	2607.11111	Know Before Fix: QA-Driven Repository Knowledge Acquisition for Software Issue Resolution	Haotian Lin et al.	arXiv	13
2026-07-15	2603.28583	Navigating the Mirage: A Dual-Path Agentic Framework for Robust Misleading Chart Question Answering	Yanjie Zhang et al.	arXiv	8
2026-07-15	2607.07769	Principled Analysis of Deep Reinforcement Learning Evaluation and Design Paradigms	Ezgi Korkmaz	arXiv	8
2026-07-15	2607.12450	Let RGB Be the Language of Vision	Timing Yang et al.	arXiv	6
2026-07-15	2607.08046	What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness	Raphaël Sarfati et al.	arXiv	5
2026-07-15	2607.11079	Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists	Chuhan Shi et al.	arXiv	4
2026-07-15	2607.11594	MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models	Tsz Hei Fan et al.	arXiv	3
2026-07-14	2607.05394	Weak-to-Strong Generalization via Direct On-Policy Distillation	Shiyuan Feng et al.	arXiv	143
2026-07-14	2607.10383	ABot-N1: Toward a General Visual Language Navigation Foundation Model	Ruiyan Gong et al.	arXiv	87
2026-07-14	2607.10350	ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory	Jiayi Tian et al.	arXiv	71
2026-07-14	2607.09125	4D Human-Scene Reconstruction from Low-Overlap Captures	Minhyuk Hwang et al.	arXiv	50
2026-07-14	2607.11487	LightMem-Ego: Your AI Memory for Everyday Life	Yijun Chen et al.	arXiv	44
2026-07-14	2607.11643	Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model	Xinghang Li et al.	arXiv	38
2026-07-14	2607.11849	AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification	Lingkai Kong et al.	arXiv	28
2026-07-14	2607.11881	Metacognition in LLMs: Foundations, Progress, and Opportunities	Gabrielle Kaili-May Liu et al.	arXiv	25
2026-07-14	2607.11505	Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals	Daocheng Fu et al.	arXiv	11
2026-07-14	2607.09701	EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos	Yifan Zhong et al.	arXiv	10
2026-07-14	2607.07470	A Theory of Contrastive Learning with Natural Images	Antonio Torralba et al.	arXiv	9
2026-07-14	2607.10623	LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow	Hang Long et al.	arXiv	9
2026-07-14	2607.11250	Multi-Agent LLMs Fail to Explore Each Other	Hyeong Kyu Choi et al.	arXiv	8
2026-07-14	2607.11736	MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning	Ayoung Lee et al.	arXiv	8
2026-07-14	2607.11644	Motion4Motion: Motion Transfer Across Subjects at Inference	Ling-Hao Chen et al.	arXiv	7
2026-07-14	2607.00397	NeuroCogMap Reveals Cognitive Organization of Large Language Models	Zhongxiang Sun et al.	arXiv	7
2026-07-14	2607.09362	CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation	Seungyong Lee et al.	arXiv	6
2026-07-14	2607.11885	Latent-Identity Tuning in Text-to-Image Personalization Models	Daniel Garibi et al.	arXiv	5
2026-07-14	2607.11862	Evidence-Backed Video Question Answering	Shijie Wang et al.	arXiv	4
2026-07-13	2607.09024	Video Generation Models are General-Purpose Vision Learners	Letian Wang et al.	arXiv	81
2026-07-13	2607.08964	Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading	Zongxia Li et al.	arXiv	72
2026-07-13	2607.09657	Scalable Visual Pretraining for Language Intelligence	Yiming Zhang et al.	arXiv	55
2026-07-13	2607.04751	Trust Region Policy Distillation	Zhengpeng Xie et al.	arXiv	34
2026-07-13	2607.07964	KronQ: LLM Quantization via Kronecker-Factored Hessian	Donghyun Lee et al.	arXiv	27
2026-07-13	2607.06553	From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models	Zanyi Wang et al.	arXiv	14
2026-07-13	2607.08393	Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning	Lu Dai et al.	arXiv	13
2026-07-13	2607.09415	Self-Guided Test-Time Training for Long-Context LLMs	Xinyu Zhu et al.	arXiv	12
2026-07-13	2607.09661	PanoWorld: Real-World Panoramic Generation	Haoyuan Li et al.	arXiv	11
2026-07-13	2607.09424	A Sovereign, Open-Source Foundation Model for German and English	The Soofi-Team et al.	arXiv	10
2026-07-13	2607.06957	Flow-ERD: Agent-type Aware Flow Matching with Entropy-Regularized Distillation for Diverse Traffic Simulation	Seulbin Hwang et al.	arXiv	8
2026-07-13	2607.07673	MedPMC: A Systematic Framework for Scaling High-Fidelity Medical Multimodal Data for Foundation Models	Hyunjae Kim et al.	arXiv	7
2026-07-13	2607.06374	VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery	Jiazi Wang et al.	arXiv	4
2026-07-13	2607.09020	Phone Segmentation and Recognition through Phonological Activation Mapping	Shikhar Bharadwaj et al.	arXiv	4
2026-07-10	2607.03118	Vidu S1: A Real-Time Interactive Video Generation Model	Jintao Zhang et al.	arXiv	146
2026-07-10	2603.29616	Video-Oasis: Rethinking Evaluation of Video Understanding	Geuntaek Lim et al.	arXiv	64
2026-07-10	2601.16211	Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition	Geo Ahn et al.	arXiv	47
2026-07-10	2607.08758	Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation	Yifan Zhou et al.	arXiv	37
2026-07-10	2607.08768	UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks	Zhekai Chen et al.	arXiv	34
2026-07-10	2607.08770	LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models	Cheng-De Fan et al.	arXiv	33
2026-07-10	2607.07740	Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE	Haozhan Tang et al.	arXiv	24
2026-07-10	2607.08763	OpenCoF: Learning to Reason Through Video Generation	Xinyan Chen et al.	arXiv	24
2026-07-10	2607.08765	Enhancing In-context Panoramic Generation via Geometric-aware Pretraining	Haoran Feng et al.	arXiv	21
2026-07-10	2607.08404	DrugGen 2: A disease-aware language model for enhancing drug discovery	Ali Motahharynia et al.	arXiv	17
2026-07-10	2607.03803	CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation	Xuyao Huang et al.	arXiv	16
2026-07-10	2607.07953	Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing	Tommaso Cerruti et al.	arXiv	14
2026-07-10	2607.08716	Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents	Yifan Wu et al.	arXiv	13
2026-07-10	2607.08741	ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation	Kaifeng Zhao et al.	arXiv	10
2026-07-10	2607.04461	Flash-BoN: Instant Drafts for Inference-Time Scaling in Diffusion Models	Ruchit Rawal et al.	arXiv	9
2026-07-10	2607.06987	UP: Unbounded Positive Asymmetric Optimization for Breaking the Exploration-Stability Dilemma	Chongyu Fan et al.	arXiv	8
2026-07-10	2607.08688	SAM-MT: Real-Time Interactive Multi-Target Video Segmentation	Ruiqi Shen et al.	arXiv	7
2026-07-10	2607.06238	PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution	Lihua Wei et al.	arXiv	6
2026-07-10	2607.08093	CausalDS: Benchmarking Causal Reasoning in Data-Science Agents	Andrej Leban et al.	arXiv	5
2026-07-10	2607.07816	A Sparse and Truncated State Vector Simulator for Peaked Circuits	Diogo R. Ferreira	arXiv	3
2026-07-10	2607.08526	A Quantized Native Runtime for On-Device Semantic Audio Generation	Matteo Spanio et al.	arXiv	2
2026-07-10	2607.03936	Can Dialects Be Steered Like Languages? Sparse Neurons and Distributed Directions in Arabic LLMs	Kareem Elozeiri et al.	arXiv	2
2026-07-10	2607.04690	PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection	Md. Shakhoyat Rahman Shujon et al.	arXiv
2026-07-09	2607.07708	Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning	Chen Tang et al.	arXiv	81
2026-07-09	2607.07675	Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence	Shuailei Ma et al.	arXiv	62
2026-07-09	2607.07608	Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation	Hongyu Qu et al.	arXiv	55
2026-07-09	2607.07534	Infinite Worlds with Versatile Interactions	Zelin Gao et al.	arXiv	46
2026-07-09	2607.07508	Single-Rollout Asynchronous Optimization for Agentic Reinforcement Learning	Zhenyu Hou et al.	arXiv	33
2026-07-09	2607.04434	RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies	Tianxing Chen et al.	arXiv	16
2026-07-09	2606.30111	Automating the Design of Embodied Agent Architectures	Jian Zhou et al.	arXiv	14
2026-07-09	2607.06838	WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence	Xiangyu Han et al.	arXiv	13
2026-07-09	2607.07386	Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity	Loïc Cabannes et al.	arXiv	12
2026-07-09	2607.06624	AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation	Andrey Podivilov et al.	arXiv	10
2026-07-09	2607.08766	OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators	Hongyu Liu et al.	arXiv	7
2026-07-09	2607.06018	RoboTALES: Learning Reasoning-Guided Robot Policies via Task-Aligned Simulated Futures	Hanan Gani et al.	arXiv	4
2026-07-09	2607.03949	TESSERA v2: Scaling Pixel-wise Earth Foundation Models	Zhengpeng Feng et al.	arXiv	4
2026-07-09	2607.03723	OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies	Kelin Yu et al.	arXiv	4
2026-07-09	2607.04939	Teaching LLMs a Low-Resource Language: Enhancing Code Completion in Pharo	Kilian Kier et al.	arXiv	4
2026-07-09	2607.05966	Imagined Rollouts are Kinematic, Not Dynamic: A Diagnosis of Long-Horizon World-Model Failure	Finn Rasmus Schäfer et al.	arXiv	3
2026-07-09	2607.06309	Token-Based Dual-view Fusion and Adaptation of Large Vision Models for Breast Cancer Classification	Aysan Ghayouri Pirsoltan et al.	arXiv	2
2026-07-09	2607.00302	Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs	Yoonhyung Park et al.	arXiv	1
2026-07-08	2607.02980	Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling	Xiang Hu et al.	arXiv	82
2026-07-08	2607.02770	Gemma 4 Technical Report	Gemma Team et al.	arXiv	78
2026-07-08	2607.06291	AlayaWorld: Long-Horizon and Playable Video World Generation	AlayaWorld Team et al.	arXiv	70
2026-07-08	2607.05147	DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation	Xin Cheng et al.	arXiv	52
2026-07-08	2607.06559	RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation	Haoyu Zhao et al.	arXiv	39
2026-07-08	2607.04412	LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL	Yujin Kim et al.	arXiv	36
2026-07-08	2607.03451	SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe	Yifei Shen et al.	arXiv	35
2026-07-08	2607.06560	Vision as Unified Multimodal Generation	Xiaoyang Han et al.	arXiv	33
2026-07-08	2607.02963	Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning	Wenzheng Zeng et al.	arXiv	26
2026-07-08	2607.06558	RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation	Haoyu Zhao et al.	arXiv	24
2026-07-08	2607.05511	Light-Omni: Reflex over Reasoning in Agentic Video Understanding with Long-Term Memory	Chang Nie et al.	arXiv	21
2026-07-08	2607.05804	TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training	Yuhang Zhou et al.	arXiv	20
2026-07-08	2607.06403	From Foundation to Application: Improving VLA Models in Practice	Wei Wu et al.	arXiv	19
2026-07-08	2607.02515	PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation	Haofei Xu et al.	arXiv	19
2026-07-08	2607.03509	Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model	Xinyin Ma et al.	arXiv	14
2026-07-08	2606.28070	JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications	Oxygen AIIC et al.	arXiv	13
2026-07-08	2607.03530	MentalThink: Shaping Thoughts in Mental SVG World	Kangheng Lin et al.	arXiv	13
2026-07-08	2607.05465	CanvasAgent: Enabling Complex Image Creation and Editing via Visual Tool Orchestration	Hairui Zhu et al.	arXiv	12
2026-07-08	2607.05722	Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding	Yonggan Fu et al.	arXiv	11
2026-07-08	2607.06065	SWE-Review: Closing the Loop on Issue Resolution with Agentic Code Review	Ruoyu Wang et al.	arXiv	10
2026-07-08	2607.04884	HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better	Gengluo Li et al.	arXiv	10
2026-07-08	2607.03738	Attending to Multimodal Generation One Token at a Time	Varun Gupta et al.	arXiv	9
2026-07-08	2607.05339	TREK: Distill to Explore, Reinforce to Refine	Yuanda Xu et al.	arXiv	9
2026-07-08	2607.03819	CGGS: Consistency-Augmented Geometric Gaussian Splatting for Ego-centric 3D Scene Generation	Zhenyu Sun et al.	arXiv	8
2026-07-08	2607.05803	Quantifying and Expanding the Theoretical Capacity of Late-Interaction Retrieval Models	Julian Killingback et al.	arXiv	8
2026-07-08	2606.31329	3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance	Dongyoon Hwang et al.	arXiv	7
2026-07-08	2607.01897	Rank-Then-Act: Reward-Free Control from Frame-Order Progress	Yuriy Maksyuta et al.	arXiv	6
2026-07-08	2607.05992	PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages	Daryna Dementieva et al.	arXiv	6
2026-07-08	2606.30026	MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs	Yuxuan Fan et al.	arXiv	5
2026-07-08	2607.04540	SceneFrom3D: Geometry-Conditioned Outdoor 3D Scene Generation via View Scheduling with Object-Level Control	Geonung Kim et al.	arXiv	4
2026-07-08	2607.05435	Bibby AI: An Editor-Native Agentic Platform for Academic Research, Writing, and Publishing	Nilesh Jain	arXiv	4
2026-07-08	2607.00394	When Classic Cache Policies Fail: Learning-Augmented Replacement for Semantic Retrieval Buffers	Yushi Sun et al.	arXiv	4
2026-07-08	2607.06442	SIEVE: Structure-Aware Data Selection for Imitation Learning with VLA Models	Changti Wu et al.	arXiv	4
2026-07-08	2607.01232	Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training	Zijian Zhang et al.	arXiv	3
2026-07-08	2607.05765	Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator	Zihan Wang et al.	arXiv	3
2026-07-08	2606.32020	Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teachers	Anh Nguyen et al.	arXiv	2
2026-07-08	2607.01293	RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules	Ádám Kovács et al.	arXiv	2
2026-07-08	2607.05691	Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES	Hunter Heidenreich	arXiv	2
2026-07-08	2607.02920	Layer-wise Cross-Lingual Depression Detection from Speech: Analysis with Contrastive Alignment	Anisha Pattanayak et al.	arXiv	2
2026-07-08	2604.17248	VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech	Yi-Cheng Lin et al.	arXiv
2026-07-08	2607.04044	SiamJEPA: On the Role of Siamese Student Encoders in JEPA	Makoto Yamada	arXiv
2026-07-07	2607.04425	UI-MOPD: Multi-Platform On-Policy Distillation for Continual GUI Agent Learning	Niu Lian et al.	arXiv	63
2026-07-07	2607.04439	ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes	Qihao Zhao et al.	arXiv	59
2026-07-07	2607.04438	ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog	Lingao Xiao et al.	arXiv	56
2026-07-07	2607.04033	OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers	Siyuan Li et al.	arXiv	49
2026-07-07	2607.03973	MANCE: Manifold Aware Concept Erasure	Matan Avitan et al.	arXiv	43
2026-07-07	2607.05247	Vision Pretraining for Dense Spatial Perception	Zelin Fu et al.	arXiv	42
2026-07-07	2607.04443	Wan-Streamer v0.2: Higher Resolution, Same Latency	Lianghua Huang et al.	arXiv	41
2026-07-07	2607.03748	Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process	Zican Hu et al.	arXiv	39
2026-07-07	2607.05373	PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space	Sensen Gao et al.	arXiv	39
2026-07-07	2607.02642	GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation	GigaWorld Team et al.	arXiv	39
2026-07-07	2607.04988	InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization	Haoxiang Ma et al.	arXiv	26
2026-07-07	2607.02646	EVA-Client: A Unified Data Collection, Inference, and Deployment Framework for Embodied Policies on Real Robots	Heqing Yang et al.	arXiv	25
2026-07-07	2607.05352	Multiplayer Interactive World Models with Representation Autoencoders	Anthony Hu et al.	arXiv	25
2026-07-07	2607.00597	Multi-Turn Agentic Scientific Literature Search via Workflow Induction	Jisen Li et al.	arXiv	23
2026-07-07	2607.02403	ACID: Action Consistency via Inverse Dynamics for Planning with World Models	Gawon Seo et al.	arXiv	21
2026-07-07	2607.05196	Unified Audio Intelligence Without Regressing on Text Intelligence	Zhifeng Kong et al.	arXiv	21
2026-07-07	2607.05061	KVpop -- Key-Value Cache Compression with Predictive Online Pruning	Lukas Hauzenberger et al.	arXiv	20
2026-07-07	2607.04605	Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval	Suhyeong Park et al.	arXiv	19
2026-07-07	2607.03751	Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models	Xinyi Xie et al.	arXiv	17
2026-07-07	2607.04428	dOPSD: On-Policy Self-Distillation for Diffusion Language Models	Phuong Tuan Dat et al.	arXiv	17
2026-07-07	2607.05391	LLM-as-a-Verifier: A General-Purpose Verification Framework	Jacky Kwok et al.	arXiv	17
2026-07-07	2607.03524	Perceptual Flow Matching for Few-Step Generative Modeling	Chuyang Zhao et al.	arXiv	16
2026-07-07	2607.05155	EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments	Deyao Zhu et al.	arXiv	15
2026-07-07	2607.05390	Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models	Hongyu Li et al.	arXiv	9
2026-07-07	2607.05376	MV-Forcing: Long Multi-View Video Generation via 4D-Grounded Spatio-Temporal Self-Forcing	Gal Fiebelman et al.	arXiv	7
2026-07-07	2606.31145	SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference	Amirhossein Abaskohi et al.	arXiv	6
2026-07-07	2606.23993	Learning to Trigger: Reinforcement Learning at the Large Hadron Collider	Zixin Ding et al.	arXiv	6
2026-07-07	2607.01764	Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction	Mingzhe Du et al.	arXiv	6
2026-07-07	2607.05369	GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks	Kaiyuan Chen et al.	arXiv	5
2026-07-07	2602.11688	GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving	Alessio Ricci Toniolo et al.	arXiv	5
2026-07-07	2607.02881	PraMem: Practice-derived Experiential Memory for Long-horizon Behavior Prediction	Zhuoqun Li et al.	arXiv	5
2026-07-07	2607.01793	Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification	Yunhao Feng et al.	arXiv	5
2026-07-07	2607.05392	SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion	Paul Engstler et al.	arXiv	4
2026-07-07	2607.02998	CONFLUX: A Latent Diffusion Model for 3D Chest-CT Synthesis with RL Post-Training	Max Van Puyvelde et al.	arXiv	4
2026-07-07	2606.28393	Transition-Aware best-of-N sampling for Longitudinal Chest X-ray Reports	Halil Ibrahim Gulluk et al.	arXiv	3
2026-07-07	2607.04410	AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes	Matteo Fasulo et al.	arXiv	3
2026-07-07	2607.03296	Taste-aware music retrieval from audio embeddings	Matteo Spanio et al.	arXiv	2
2026-07-07	2607.03068	PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation	Ebenezer Tarubinga	arXiv	2
2026-07-07	2607.02904	Speaker-Aware Temporal Aggregation Strategies on Segment Representations for Depression Detection in Dyadic Interaction: A Benchmark Study	Anisha Pattanayak et al.	arXiv	1
2026-07-07	2607.04064	Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization	Ryota Komatsu et al.	arXiv	1
2026-07-06	2607.02501	Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots	Ling Xu et al.	arXiv	53
2026-07-06	2606.28551	DataComp-VLM: Improved Open Datasets for Vision-Language Models	Matteo Farina et al.	arXiv	47
2026-07-06	2606.29526	The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning	Jing Liang et al.	arXiv	40
2026-07-06	2607.02461	OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers	Donghyun Lee et al.	arXiv	36
2026-07-06	2607.01804	VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon	Yi Pan et al.	arXiv	27
2026-07-06	2607.01233	Measuring the Gap Between Human and LLM Research Ideas	Ziyu Chen et al.	arXiv	19
2026-07-06	2606.31227	Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming	Yong Yang et al.	arXiv	12
2026-07-06	2607.01420	MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answering	Dang Quang Thien Tran et al.	arXiv	7
2026-07-06	2606.31036	Teaching LLMs to Recommend and Defer in Underrepresented Epilepsy Care	Shreyas Rajesh et al.	arXiv	6
2026-07-06	2606.31959	AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer	Xinyu Hou et al.	arXiv	5
2026-07-06	2607.00052	AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation	Bao Long Nguyen Huu et al.	arXiv	4
2026-07-06	2405.03650	Generated Contents Enrichment	Mahdi Naseri et al.	arXiv	3
2026-07-06	2607.02471	Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment	Ziyao Wang et al.	arXiv	2
2026-07-03	2607.02512	Program-as-Weights: A Programming Paradigm for Fuzzy Functions	Wentao Zhang et al.	arXiv	88
2026-07-03	2607.02255	AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents	Xiangchen Cheng et al.	arXiv	66
2026-07-03	2606.30562	Morphing into Hybrid Attention Models	Disen Lan et al.	arXiv	49
2026-07-03	2607.02440	EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments	Zhilin Wang et al.	arXiv	48
2026-07-03	2607.01642	Multi-Resolution Flow Matching: Training-Free Diffusion Acceleration via Staged Sampling	Xingyu Zheng et al.	arXiv	38
2026-07-03	2607.01647	AgenticDataBench: A Comprehensive Benchmark for Data Agents	Zhaoyan Sun et al.	arXiv	35
2026-07-03	2607.02517	WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory	Hanlin Wang et al.	arXiv	30
2026-07-03	2606.31825	Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning	Junha Jung et al.	arXiv	24
2026-07-03	2607.01874	SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use	Jiayin Zhu et al.	arXiv	19
2026-07-03	2607.01224	AutoMem: Automated Learning of Memory as a Cognitive Skill	Shengguang Wu et al.	arXiv	18
2026-07-03	2607.02032	PACE: A Proxy for Agentic Capability Evaluation	Yueqi Song et al.	arXiv	17
2026-07-03	2607.02291	Optimizing Visual Generative Models via Distribution-wise Rewards	Ruihang Li et al.	arXiv	16
2026-07-03	2607.01002	Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads	Aryo Pradipta Gema et al.	arXiv	15
2026-07-03	2607.02271	AGVBench: A Reliability-Oriented Benchmark of Data Augmentation for Vein Recognition	Haiyang Li et al.	arXiv	14
2026-07-03	2607.02508	From SRA to Self-Flow: Data Augmentation or Self-Supervision?	Dengyang Jiang et al.	arXiv	12
2026-07-03	2606.27669	When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search	Yiling Tao et al.	arXiv	11
2026-07-03	2607.02375	Representation Distribution Matching for One-Step Visual Generation	Lan Feng et al.	arXiv	10
2026-07-03	2606.31924	InstanceControl: Controllable Complex Image Generation without Instance Labeling	Xiaoyu Liu et al.	arXiv	9
2026-07-03	2607.01686	WARP: Weight-Space Analysis for Recovering Training Data Portfolios	Tzu-Heng Huang et al.	arXiv	8
2026-07-03	2606.29961	DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation	Peyman Hosseini et al.	arXiv	7
2026-07-03	2607.01436	Discrete Diffusion Language Models for Interactive Radiology Report Drafting	Max Van Puyvelde et al.	arXiv	6
2026-07-03	2607.02466	Learning to Move Before Learning to Do: Task-Agnostic pretraining for VLAs	Junhao Shi et al.	arXiv	6
2026-07-03	2607.01763	Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training	Meng Wang et al.	arXiv	6
2026-07-03	2607.02269	AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models	Rintaro Otsubo et al.	arXiv	6
2026-07-03	2606.25178	Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR	Yongjin Yang et al.	arXiv	4
2026-07-03	2607.01283	Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions	Matthew J Liu et al.	arXiv	2
2026-07-03	2606.27821	Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting	Kuo-Chung Peng et al.	arXiv	2
2026-07-02	2606.28322	PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception	Yana Wei et al.	arXiv	41
2026-07-02	2606.19271	TurboServe: Serving Streaming Video Generation Efficiently and Economically	Youhe Jiang et al.	arXiv	34
2026-07-02	2607.00248	Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity	Bytedance Seed	arXiv	30
2026-07-02	2607.00461	Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning	Shijie Li et al.	arXiv	25
2026-07-02	2607.01071	MemSyco-Bench: Benchmarking Sycophancy in Agent Memory	Zhishang Xiang et al.	arXiv	25
2026-07-02	2607.00466	ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving	Sangjin Choi et al.	arXiv	24
2026-07-02	2607.00272	ASPIRE: Agentic /Skills Discovery for Robotics	Runyu Lu et al.	arXiv	24
2026-07-02	2607.00666	Domain Arithmetic: One-Shot VLA Adaptation under Environmental Shifts	Taewook Kang et al.	arXiv	23
2026-07-02	2607.01104	CausalMix: Data Mixture as Causal Inference for Language Model Training	Zinan Tang et al.	arXiv	19
2026-07-02	2606.31551	AutoTrainess: Teaching Language Models to Improve Language Models Autonomously	Zhaojian Yu et al.	arXiv	18
2026-07-02	2607.00678	ABot-M0.5: Unified Mobility-and-Manipulation World Action Model	Ronghan Chen et al.	arXiv	16
2026-07-02	2607.01191	Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual Reasoning	Hongxing Li et al.	arXiv	15
2026-07-02	2607.01211	Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?	Zhi Chen et al.	arXiv	11
2026-07-02	2607.00917	Valdi: Value Diffusion World Models	Christopher Lindenberg et al.	arXiv	11
2026-07-02	2607.00115	PixelEyes: Decoupling Perception and Reasoning for Pinpoint Visual Evidence Seeking	Dengxian Gong et al.	arXiv	9
2026-07-02	2607.01218	The State-Prediction Separation Hypothesis	Giovanni Monea et al.	arXiv	9
2026-07-02	2606.20997	BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery	Jieyi Wang et al.	arXiv	9
2026-07-02	2607.00924	Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination	Subhadeep Pal et al.	arXiv	8
2026-07-02	2607.00152	GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity	Yong Yi Bay et al.	arXiv	7
2026-07-02	2606.32029	When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors	Yuqing Yang et al.	arXiv	7
2026-07-02	2606.31179	HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents	Qianchu Liu et al.	arXiv	6
2026-07-02	2606.28430	Building to the Test: Coding Agents Deliver What You Check, Not What You Requested	Yanuo Ma et al.	arXiv	5
2026-07-02	2607.01131	Autonomous Scientific Discovery via Iterative Meta-Reflection	Bingchen Zhao et al.	arXiv	5
2026-07-02	2606.31292	AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report Evaluation	Yuan Wang et al.	arXiv	5
2026-07-02	2606.28661	When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling	Yong Yi Bay et al.	arXiv	4
2026-07-02	2606.29464	Rank-Aware Hyperbolic Alignment for Vision-Language Dataset Distillation	Jongoh Jeong et al.	arXiv	4
2026-07-02	2606.30124	SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation	Zhiyuan Ma et al.	arXiv	4
2026-07-02	2606.30030	CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion	Pan Wang et al.	arXiv	4
2026-07-02	2606.26040	AI translation of literary texts is "fine", but readers still prefer human translations	Yves Ferstler et al.	arXiv	4
2026-07-02	2607.00407	Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising	Tianci Liu et al.	arXiv	4
2026-07-02	2607.00529	NoPA: Non-Parametric Online 3D Scene Graph Generation	Qi Xun Yeo et al.	arXiv	4
2026-07-02	2606.31719	Seeing Is Not Sharing: Some Vision-Language Models Overestimate Common Ground in Asymmetric Dialogue	Nan Li et al.	arXiv	3
2026-07-02	2607.00553	Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks	MD Azizul Hakim et al.	arXiv	3
2026-07-01	2606.30534	Orca: The World is in Your Mind	Yihao Wang et al.	arXiv	193
2026-07-01	2606.30626	DOPD: Dual On-policy Distillation	Xinlei Yu et al.	arXiv	114
2026-07-01	2606.28436	Dockerless: Environment-Free Program Verifier for Coding Agents	Wenhao Zeng et al.	arXiv	78
2026-07-01	2606.19297	Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models	Nikita Kachaev et al.	arXiv	77
2026-07-01	2606.29513	Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views	Mijin Yoo et al.	arXiv	51
2026-07-01	2606.31315	BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding	Hao Zhang et al.	arXiv	48
2026-07-01	2606.29082	Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks	Young-Jun Lee et al.	arXiv	42
2026-07-01	2606.29215	Multi-Block Diffusion Language Models	Yijie Jin et al.	arXiv	40
2026-07-01	2606.30406	MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training	Wenhan Ma et al.	arXiv	29
2026-07-01	2606.32032	Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs	Gabrielle Kaili-May Liu et al.	arXiv	28
2026-07-01	2606.31734	MemLearner: Learning to Query Context memory for Video World Models	Jiwen Yu et al.	arXiv	27
2026-07-01	2606.30968	PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising	Koorosh Roohi et al.	arXiv	25
2026-07-01	2607.00446	VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement	Seohyun Lee et al.	arXiv	24
2026-07-01	2606.31537	DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation	Siyu Yan et al.	arXiv	24
2026-07-01	2606.23127	Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation	Julia Belikova et al.	arXiv	22
2026-07-01	2606.31410	Xiaomi-GUI-0 Technical Report	Wanxia Cao et al.	arXiv	18
2026-07-01	2606.08671	SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History	Zhiwei Li et al.	arXiv	17
2026-07-01	2606.26428	Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?	Tyler Ga Wei Lum et al.	arXiv	15
2026-07-01	2606.32039	GEAR: Guided End-to-End AutoRegression for Image Synthesis	Bin Lin et al.	arXiv	15
2026-07-01	2606.30062	Little Brains, Big Feats: Exploring Compact Language Models	Dari Baturova et al.	arXiv	15
2026-07-01	2606.29985	Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning	Sangmook Lee et al.	arXiv	11
2026-07-01	2606.30673	PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation	Chunshi Wang et al.	arXiv	11
2026-07-01	2606.32034	QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents	Sergio Hernández-Gutiérrez et al.	arXiv	9
2026-07-01	2606.31811	MuSViT: A Foundation Vision Model for Sheet Music Representation	Carlos Penarrubia et al.	arXiv	9
2026-07-01	2606.30319	BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language	Haitao Wu et al.	arXiv	9
2026-07-01	2606.32017	TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning	Yuanda Xu et al.	arXiv	8
2026-07-01	2606.30573	SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions	Mohit Raghavendra et al.	arXiv	7
2026-07-01	2606.30599	Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing	Sen Liang et al.	arXiv	7
2026-07-01	2606.32033	SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE	Or Hirschorn et al.	arXiv	6
2026-07-01	2606.29667	Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature	Subham Ghosh et al.	arXiv	5
2026-07-01	2606.30811	AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation	Kien T. Pham et al.	arXiv	5
2026-07-01	2606.26968	RedVox: Safety and Fairness Gaps in Speech Models Across Languages	Beatrice Savoldi et al.	arXiv	4
2026-07-01	2606.31029	TerraDiT-Ω: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive	Brian Wei et al.	arXiv	4
2026-07-01	2607.01213	RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue	Zhihao Lin et al.	arXiv	3
2026-07-01	2606.29315	Hierarchical Experimentalist Agents	Abhranil Chandra et al.	arXiv	3
2026-07-01	2606.30697	LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents	Yogeswar Reddy Thota	arXiv	3
2026-07-01	2606.31247	FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model	Jiaqi Li et al.	arXiv	2
2026-07-01	2606.22207	Lexical Consensus: Grounded Word Learning and Shared Meaning in Artificial Agents	Patricio M. Vera	arXiv	1