2026-09 papers

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

2026-09 · 776 records

date	id	title	authors	venue	↑
2026-09-30	2609.33439	Raven: The Harness of Harnesses for Composable Agentic Intelligence	EverMind AI	arXiv	134
2026-09-30	2609.36012	In-Context Learning for Robots: Methods and Applications	Haojian Huang et al.	arXiv	105
2026-09-30	2609.34309	MaLiang-Harness: A Programmable Path to Image and Video Generation	Haoyu Zhao et al.	arXiv	97
2026-09-30	2609.34981	What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling	Renping Zhou et al.	arXiv	93
2026-09-30	2609.38155	Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies	Hui Ren et al.	arXiv	85
2026-09-30	2609.36380	LEGO-Anything: Coding Agents for 3D Scene Reconstruction	Xirui Li et al.	arXiv	71
2026-09-30	2609.37226	Follow the Entities: A Corpus Map for Agentic Search	Soyeong Jeong et al.	arXiv	68
2026-09-30	2609.37372	Think Before You Score: Thinking Reward Model for Visual Generation	Xuehai Bai et al.	arXiv	66
2026-09-30	2609.35427	LLMs are General Asynchronous Agents	George Yakushev et al.	arXiv	63
2026-09-30	2609.31847	Omni-IO Skills: Harnessing Your Agent Omni-Native	Yanlin Li et al.	arXiv	63
2026-09-30	2609.37686	EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?	Hongcheng Gao et al.	arXiv	54
2026-09-30	2609.32607	VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models	Yang Xiao et al.	arXiv	53
2026-09-30	2609.36071	LongCat-DeepResearch Technical Report	Meituan LongCat Team et al.	arXiv	52
2026-09-30	2609.37868	Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR	Doohyuk Jang et al.	arXiv	49
2026-09-30	2609.38079	OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?	Jiaxin Ge et al.	arXiv	45
2026-09-30	2609.34759	PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation	Zhen Wang et al.	arXiv	40
2026-09-30	2609.32722	Scaling Properties of Same-Family On-Policy Distillation	Yuntai Bao et al.	arXiv	39
2026-09-30	2609.37725	Context Language Models	Rulin Shao et al.	arXiv	38
2026-09-30	2609.36322	Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression	Xingyu Zhu et al.	arXiv	36
2026-09-30	2609.37559	APM-Bench: Benchmarking Cross-session Persistent Memory for Egocentric Streaming Video Assistants	Jianguo Huang et al.	arXiv	36
2026-09-30	2609.37969	SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video	Haozhe Liu et al.	arXiv	34
2026-09-30	2609.35954	ROSS: Relearning from Self-Generated Rollouts through Selective Supervision	Zhiwei Zhang et al.	arXiv	34
2026-09-30	2609.34606	WorldAttention: An Efficient Attention Architecture for Interactive Video World Models	Zeyu Zhang et al.	arXiv	34
2026-09-30	2609.38057	EVO-WAM: Evolving World Action Models through Video-Action Verification	Shiyang Zhou et al.	arXiv	33
2026-09-30	2609.38008	HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents	Tongbo Chen et al.	arXiv	32
2026-09-30	2609.37236	Asking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents	Ido Levy et al.	arXiv	30
2026-09-30	2609.38154	LongLive-Plug: Once-for-All Distillation for Video Generation	Shuai Yang et al.	arXiv	29
2026-09-30	2609.34378	Marathoner: Ultra-Long-Horizon Autonomous Intelligence	Zhang Ruiyang et al.	arXiv	27
2026-09-30	2609.36802	EasyPPO: Stabilizing the Critic Is Key	Xuanyi Zhou et al.	arXiv	26
2026-09-30	2609.37441	Anisotropic Representations Improve Planning in JEPA World Models	Mingu Kang et al.	arXiv	26
2026-09-30	2609.36601	SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation	Miteto Wei et al.	arXiv	26
2026-09-30	2609.36651	FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution	FangZhi Zhong et al.	arXiv	24
2026-09-30	2609.38360	On the Off-Policy Teacher in On-Policy Distillation	Langlin Huang et al.	arXiv	23
2026-09-30	2609.32522	Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations	Wenxu Jia et al.	arXiv	23
2026-09-30	2609.33326	ANTMAN: Adaptive Need Tracking for Multi-Agent Navigation in Large Information Spaces	Jerry Wang et al.	arXiv	23
2026-09-30	2607.11433	Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents	Ming Ma et al.	arXiv	21
2026-09-30	2609.38059	WorldLine: Action-Driven Visual Simulation for Robotic Manipulation	Shenghe Zheng et al.	arXiv	21
2026-09-30	2609.36653	Scheduling Recursive Reasoning in Looped Transformers	Boyuan Wang et al.	arXiv	19
2026-09-30	2609.38087	CrossBFM: Distilling a Shared Latent Behavior Space Across Humanoid Embodiments	Tan-Dzung Do et al.	arXiv	19
2026-09-30	2609.16409	Reasoning with Image Generation	Nishad Singhi et al.	arXiv	18
2026-09-30	2609.32488	When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections	Maojun Sun et al.	arXiv	18
2026-09-30	2609.37775	HiRAE: Hierarchical Representation Autoencoding with Residual Budgets	Xuanyu Zhu et al.	arXiv	18
2026-09-30	2609.37959	TabFM: A Zero-Shot Foundation Model for Tabular Data	Weihao Kong et al.	arXiv	17
2026-09-30	2609.37402	Routing Should Pay for Itself: Sparse Supervision for Economical LLM Routing	Guannan Lai et al.	arXiv	16
2026-09-30	2609.35530	AutoRef: Harness Optimization for Agentic Multi-Reference Image Generation	Yuta Oshima et al.	arXiv	16
2026-09-30	2609.36965	Chinese-Jev: Bringing System One Model to Chinese-Language Tasks	Zexiao Wang et al.	arXiv	16
2026-09-30	2609.37040	Selecting The Most Informative Tokens in Natural Language Autoencoders	Federico Torrielli et al.	arXiv	15
2026-09-30	2609.38157	EmoRES-TTS: Residual-Enhanced Vector Steering for Emotional Speech Generation	Kuan-Po Huang et al.	arXiv	15
2026-09-30	2609.38170	Adversarial Training for Pixel Diffusion	Xin Lin et al.	arXiv	15
2026-09-30	2609.36139	Language Models Are "Insecure" Reporters	Jenny Y. Huang et al.	arXiv	13
2026-09-30	2609.34605	PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy Distillation	Youzhi Liu et al.	arXiv	12
2026-09-30	2609.37989	TabFM-Auto: Self-Evolving Pipelines for Tabular Foundation Models	Deqing Fu et al.	arXiv	11
2026-09-30	2609.36730	Can Agents Design Libraries for Agents?	Gabriel Orlanski et al.	arXiv	10
2026-09-30	2609.37923	EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory	Ziyun Zeng et al.	arXiv	9
2026-09-30	2609.38119	VideoLoop: Looped Working Memory Against Semantic Thrashing in Long-Form Video Agents	Jinfa Huang et al.	arXiv	9
2026-09-30	2609.33627	StoryEngine: A State-Grounded Agentic Framework for Video Storytelling	Yingrui Wang et al.	arXiv	8
2026-09-30	2609.36130	Memory Is a Derivation: The Distributed-Evidence Paradox in Long-Term Agents	Hongjun Liu et al.	arXiv	7
2026-09-30	2609.36636	What Makes Recurrence Effective in Looped Language Models?	Xinlin Zhuang et al.	arXiv	7
2026-09-30	2609.38146	LIFT: Layout-In-Future Video Generation under Large Viewpoint Change via On-Policy Self-Distillation	Shengxiang Ji et al.	arXiv	7
2026-09-30	2609.33748	AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models	Rui Wang et al.	arXiv	7
2026-09-30	2609.35342	Jev thinks "I don't know'', but doesn't say it: Introducing Sys1Cal-v1 Dataset for Probability Calibration	Riccardo Porcedda	arXiv	7
2026-09-30	2609.36159	Principled Thoughts for Latent Recursive LLM Systems	Fahd Seddik et al.	arXiv	7
2026-09-30	2609.36864	Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards	Fanchao Chen et al.	arXiv	7
2026-09-30	2609.33589	TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs	Zihan Lin et al.	arXiv	7
2026-09-30	2609.33591	Pretraining Transformers with Quantized Softmax in Attention	Shangzhen Zhu et al.	arXiv	6
2026-09-30	2609.35025	AutoDataBench: Can Agents Write the Data That Feeds the Self-Improvement Loop?	Haotian Luo et al.	arXiv	6
2026-09-30	2609.35232	Beyond Selection: Token Parameterization for Extreme Visual Token Compression	Rui Zhong et al.	arXiv	6
2026-09-30	2609.37089	Real2Gym: Building Gyms from Videos, Bringing Skills to Robots	Kerui Ren et al.	arXiv	6
2026-09-30	2609.35770	FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets	Srinjay Sarkar et al.	arXiv	6
2026-09-30	2609.36199	PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents	Vighnesh Subramaniam et al.	arXiv	5
2026-09-30	2608.19669	Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning	Haoqiang Kang et al.	arXiv	5
2026-09-30	2609.38140	Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE	Yu Xu et al.	arXiv	5
2026-09-30	2609.36352	StructRL: Online Structured Reinforcement Learning for Long-Horizon Vision-Language-Action Tasks	Ziyi Yin et al.	arXiv	5
2026-09-30	2609.35932	Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection	Yan Zhan et al.	arXiv	5
2026-09-30	2609.34528	Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement	Hyun-Kurl Jang et al.	arXiv	5
2026-09-30	2609.32915	AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents	Asif Shahriar et al.	arXiv	4
2026-09-30	2609.36314	Fractional State Space Transition for Long Sequence Modeling	Ivan Kobyzev et al.	arXiv	4
2026-09-30	2609.33620	Learning Dynamics of Continual Learning: A Unified View of Data Attribution, Forgetting, and Plasticity Loss	Yi Ren et al.	arXiv	4
2026-09-30	2609.34962	ALICE: In-context, Zero-shot, Mutual Information Estimation	Giulio Franzese et al.	arXiv	4
2026-09-30	2609.37147	Improved Distributional Diffusion Models	Tommaso Martorella et al.	arXiv	4
2026-09-30	2609.36014	Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion	Chong Wang et al.	arXiv	4
2026-09-30	2609.34314	PlaylistEval: Can Video-Language Judges Be Trusted at Day Scale and Beyond?	Shayekh Bin Islam et al.	arXiv	4
2026-09-30	2609.31957	CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs	Zhenhao Zhang et al.	arXiv	4
2026-09-30	2609.32429	PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers	Yanlong Chen et al.	arXiv	4
2026-09-30	2609.34392	Org-Agent: Beyond Personal Assistants Towards Organizational Agents	Luyao Zhuang et al.	arXiv	3
2026-09-30	2609.37687	WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation	Muhammad Huzaifa et al.	arXiv	3
2026-09-30	2609.34518	SEAD: A State-Based Perspective on Attack and Defense in Tool-Using Agents	Xinjie Shen et al.	arXiv	3
2026-09-30	2609.35514	One Proposal for Every Margin: Zero-Shot Amortized Sequential Importance Sampling for Binary Matrices	Ruishuo Chen et al.	arXiv	3
2026-09-30	2609.36608	Act First, Reason Later: Accelerating On-Policy Distillation for Multi-Turn Agents via Reference-Conditioned Inverse Dynamics	Zubin Zheng et al.	arXiv	3
2026-09-30	2609.35210	Understanding On-Policy Distillation: A Mechanistic Interpretability Perspective via Sparse Crosscoders	Zichao Yu et al.	arXiv	2
2026-09-30	2609.38172	Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation	Zihan Wang et al.	arXiv	1
2026-09-30	2609.35845	Hyperspherical Semantic Trajectory Analysis: Mapping Technological Diffusion across Academic Preprints, Patent Signals, and Compute Scaling	Muhammad Sukri Bin Ramli	arXiv	1
2026-09-29	2609.33757	YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality	Ruibin Yuan et al.	arXiv	164
2026-09-29	2609.35347	Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation	Xin Li et al.	arXiv	75
2026-09-29	2609.33295	TraceDance: An Automated System for Building Agent Behavior Benchmarks from Real-World Agent Deployment Traces	Dehai Min et al.	arXiv	70
2026-09-29	2609.35748	Improving Test-Time Scaling with Adaptive Looped Transformers	Yichen You et al.	arXiv	62
2026-09-29	2609.35457	How Far Are We from Removing the Visual Encoder? Scaling Laws for Encoder-Free Multimodal Pretraining	Lin Chen et al.	arXiv	61
2026-09-29	2609.33325	VisionHOPE: Visual Backbones as Self-Modifying Learning Systems	Siran Peng et al.	arXiv	60
2026-09-29	2609.33848	QwenGyre: An Elastic Reinforcement Learning Framework for Training xLong-Horizon Agents	Weiqi Wang et al.	arXiv	49
2026-09-29	2609.29233	Post-Training Leaves Behavioral Shadows on Unrelated Decisions	Ziyang Zhang et al.	arXiv	48
2026-09-29	2609.35767	Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning	Yijia Fan et al.	arXiv	46
2026-09-29	2609.32577	Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL	Jinhao Dong et al.	arXiv	45
2026-09-29	2609.33781	Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning	Woongyeong Yeo et al.	arXiv	44
2026-09-29	2609.31948	Duplex-MPE: Benchmarking Multi-Party Interaction in Full-Duplex Dialogue	Chengqian Ma et al.	arXiv	43
2026-09-29	2609.32712	MassAlloc Attention: Let Attention Allocate Its Own Compute	Jingze Shi et al.	arXiv	42
2026-09-29	2609.36246	Learning from Teacher Continuations at Student States	Haojin Wang et al.	arXiv	41
2026-09-29	2609.33378	Recursive Harness Distillation across Agents for Robot Manipulation	Seungyeon Kim et al.	arXiv	40
2026-09-29	2609.33665	CompoWorld: Compositional Environment Scaling for General Agents	Xiao-Wen Yang et al.	arXiv	40
2026-09-29	2609.34327	Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge	Chanuk Lee et al.	arXiv	39
2026-09-29	2609.33780	Selecting Diverse SFT Traces Improves Post-RL Generalization	Dylan Zhang et al.	arXiv	36
2026-09-29	2609.33772	Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents	Weiyi Xu et al.	arXiv	36
2026-09-29	2609.35432	Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence	Hongcheng Gao et al.	arXiv	35
2026-09-29	2609.32534	DepthBench: Measuring How Residual Connections Enable More Computational Depth	Keyu Wang et al.	arXiv	33
2026-09-29	2609.32704	CoWindow Attention: Full Causal Coverage Is a Collective Property	Jingze Shi et al.	arXiv	32
2026-09-29	2609.33803	Diffusion Reward Models	Xiangyang Wang et al.	arXiv	32
2026-09-29	2609.35673	FlowTool: Controlling Tool Parameter in Image Retouching via Flow Matching	Thanh-Long V. Le et al.	arXiv	31
2026-09-29	2609.33642	Learning to Learn from Context: Synthetic Training from Perturbed Public Documents	Haoyi Wu et al.	arXiv	31
2026-09-29	2609.32540	In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion	Yikai Wang et al.	arXiv	30
2026-09-29	2609.35560	WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon	Haiyu Zhang et al.	arXiv	30
2026-09-29	2609.35505	An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning	Shangzhe Li et al.	arXiv	28
2026-09-29	2609.32444	Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It	Tianrun Yu et al.	arXiv	28
2026-09-29	2609.34972	Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models	Jingdi lei et al.	arXiv	27
2026-09-29	2609.32862	RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents	Jingsong Liang et al.	arXiv	25
2026-09-29	2609.33616	SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning	Yang Cao et al.	arXiv	25
2026-09-29	2609.35718	Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision	Hanoona Rasheed et al.	arXiv	23
2026-09-29	2609.32814	Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers	Ilya Koziev et al.	arXiv	22
2026-09-29	2609.33095	REALM: A Coarse-to-Fine Generative Framework for Embodied Reactive Listening	Peizhen Li et al.	arXiv	20
2026-09-29	2609.33382	WideSWE: Can Coding Agents Coordinate Changes Across Repositories?	Baoyi Wang et al.	arXiv	19
2026-09-29	2609.34470	Precise Editing and Flexible Referencing for Interactable Worlds	Xinyao Liao et al.	arXiv	19
2026-09-29	2609.32472	AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research	Kailin Jiang et al.	arXiv	19
2026-09-29	2609.28236	EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks	Lizhou Liang et al.	arXiv	19
2026-09-29	2609.33419	TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining	Shih-Ying Yeh et al.	arXiv	18
2026-09-29	2609.34645	Nereus: Adaptive Parallelism for LLM Post-Training	Songlin Jiang et al.	arXiv	17
2026-09-29	2609.35504	SolveEdit: Benchmarking Visual Problem Solving in Generative Models	Wenjie Shu et al.	arXiv	17
2026-09-29	2609.35134	VideoPhysEdit: Physical Counterfactual Video Editing via Rigid-Body Physical Scene Reconstruction	Conghan Yue et al.	arXiv	16
2026-09-29	2609.33203	Structured Residual Connectivity Matters for Diffusion Transformers	Yuhe Liu et al.	arXiv	16
2026-09-29	2609.33399	SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation	Jiali Chen et al.	arXiv	16
2026-09-29	2609.35261	Imprint Reader: From Weight-Update Readout to Behavioral Intervention	Guanxu Chen et al.	arXiv	15
2026-09-29	2609.32630	ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis	Kwangwook Seo et al.	arXiv	12
2026-09-29	2609.32241	Residual Transferability in Neural Image Watermarking	Ziping Dong et al.	arXiv	11
2026-09-29	2609.33855	Program-Verified Self-Evolution for Vision-Language Models	Ahmed Heakl et al.	arXiv	10
2026-09-29	2609.35743	InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video	Kerui Ren et al.	arXiv	9
2026-09-29	2609.35734	GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space	Kerui Ren et al.	arXiv	9
2026-09-29	2609.23033	WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models	Hyeongju Ha et al.	arXiv	9
2026-09-29	2609.34754	Draft-KV: Learning Useful Latent Communication Between Language Models	Linquan Wu et al.	arXiv	8
2026-09-29	2609.35551	BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation	Peilin Feng et al.	arXiv	8
2026-09-29	2609.32353	Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction	Junxian Li et al.	arXiv	8
2026-09-29	2609.32965	Relic: From Multi-Agent Collaboration to Persistent Organizational Capability	Hongyi Du et al.	arXiv	7
2026-09-29	2609.34899	ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport	Zhuchenyang Liu et al.	arXiv	7
2026-09-29	2609.35069	RenderRank: Learning to Rerank Text with Compressed Visual Tokens	Seongtae Hong et al.	arXiv	7
2026-09-29	2609.34060	KVCMAS: Efficient KV cache Correction for Shared Context in Multi-Agent Systems	Hyesung Jeon et al.	arXiv	7
2026-09-29	2609.34054	PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction	Hyesung Jeon et al.	arXiv	7
2026-09-29	2609.34848	Can We Trust the Teacher? Decoupled Credit Direction-Magnitude for Self-Distillation	Yugu Li et al.	arXiv	6
2026-09-29	2609.34479	SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis	Hangyul Yoon et al.	arXiv	6
2026-09-29	2609.33999	Rethinking Automated Voice Similarity by Shifting from EER to Embedding Geometry	Szu-Chi Chen et al.	arXiv	6
2026-09-29	2609.33253	VGGT-Diff: Visual Geometry Meets Diffusion for Sparse-View Novel View Synthesis	Kangjie Chen et al.	arXiv	6
2026-09-29	2609.35706	Reinforcing Agentic Creativity in Scientific Ideation with Night Science	Priyanka Kargupta et al.	arXiv	5
2026-09-29	2609.33437	SMAT: Simple and Efficient Merge-Aware Training	Yanggan Gu et al.	arXiv	5
2026-09-29	2609.33074	KernelZero: Co-Evolving Proposer and Coder for Continuously Improved GPU Kernel Generation	Changxin Ke et al.	arXiv	5
2026-09-29	2609.33148	DroneWAM: Efficient World Action Model for Drone Visual Navigation	Liang Yao et al.	arXiv	5
2026-09-29	2609.35279	Measuring Collapse and Correction in Homogeneous-Panel LLM Debate	Xin Li et al.	arXiv	5
2026-09-29	2609.35760	TokenCast: Forecasting Token Consumption During LLM Agent Execution	Chaoqian Ouyang et al.	arXiv	5
2026-09-29	2609.32821	Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs	Yuanyi Wang et al.	arXiv	5
2026-09-29	2609.33586	Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration	Shangzhen Zhu et al.	arXiv	4
2026-09-29	2609.31892	NVAlign: Direct-Gradient Optimization for Non-Verbal Control in Continuous Autoregressive Flow Matching Text-to-Speech	Qiaolin Wang et al.	arXiv	4
2026-09-29	2608.18486	WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing	Wenbo Zhang et al.	arXiv	4
2026-09-29	2609.34722	Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation	Zesong Yang et al.	arXiv	4
2026-09-29	2609.33645	Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training	Yifan Yang et al.	arXiv	4
2026-09-29	2609.35578	FactorEngram: Factorized N-gram Memory with Basis-Level Gating for Language Models	Bowen Yang et al.	arXiv	4
2026-09-29	2609.31009	G^2PTQ: Improving LLM Post-Training Quantization with Generalized Gradient Compensation	Ruikang Liu et al.	arXiv	4
2026-09-29	2606.29521	Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization	Dara Varam et al.	arXiv	4
2026-09-29	2609.34771	When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety	Tianyi Guan et al.	arXiv	4
2026-09-29	2609.35616	EvolvingAvatar: Interactive 3D Head Generation That Adapts as Conversations Unfold	Junjie Chen et al.	arXiv	4
2026-09-29	2609.33391	Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents	Mingju Chen et al.	arXiv	4
2026-09-29	2609.30936	Self-Play Search Distillation for Large Language Model Reasoning	Lorenzo Molfetta et al.	arXiv	3
2026-09-29	2609.33791	Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models?	Wenze Lin et al.	arXiv	3
2026-09-29	2609.32913	Allspark: Weak to Strong Transfer via Alternating Chain of Thought	Kaizhao Liang et al.	arXiv	3
2026-09-29	2609.34065	Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models	Mir Tafseer Nayeem et al.	arXiv	3
2026-09-29	2609.35699	Distillation Defenses Easily Break After Reinforcement Learning	Shidan Javaheri et al.	arXiv	3
2026-09-29	2609.33485	DISCO: Distributed Long Context Scaling with Grounding-Reasoning Disaggregation	Guanzheng Chen et al.	arXiv	3
2026-09-29	2609.32146	Playing to Par: Reinforcement Learning for Provably Optimal Quadrilateral Block Decompositions	Arjun Narayanan et al.	arXiv	3
2026-09-29	2609.33487	What masking geometry works best for EEG foundation models?	Pierre Guetschel et al.	arXiv	3
2026-09-29	2609.35611	On-Policy Self-Distillation for Multi-Turn Image Editing	Liangbing Zhao et al.	arXiv	3
2026-09-29	2609.30247	Rolling-WAM: World Action Models with Rolling Imagination	Yinghua Zhou et al.	arXiv	3
2026-09-29	2609.32754	Adaptive Consistency Graph for Long-Horizon Agents	Jiecong Wang et al.	arXiv	3
2026-09-29	2609.34313	ControlScope: Workflow Revision and Reliability in LLM Agents	Jingjie Ning et al.	arXiv	3
2026-09-29	2609.36219	LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning	Bang Xiao et al.	arXiv	2
2026-09-29	2609.34044	SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models	Ahmadreza Jeddi et al.	arXiv	2
2026-09-29	2609.35247	AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors	Mohamed Eltahir et al.	arXiv	2
2026-09-29	2609.16145	Safe Error Correction for Language Models: Frozen-Base Adjustment with Capability Preservation	Gautam Kishore	arXiv	2
2026-09-29	2609.31669	NanoForecast v0.5: Competitive Time Series Forecasting Through Training Pipeline Optimization	Gautam Kishore	arXiv	2
2026-09-29	2609.30074	How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure	Dipankar Sarkar	arXiv	2
2026-09-28	2609.26333	Disaggregated Quantization: Specializing LLM Prefill and Decode	Andrei Panferov et al.	arXiv	90
2026-09-28	2609.31620	FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders	Hongyang Du et al.	arXiv	61
2026-09-28	2609.18703	RayOrch: Programming and Executing Lineage-Controlled Multi-Grain Dataflows for Foundation-Model Data Preparation	Xiaochen Ma et al.	arXiv	53
2026-09-28	2609.31093	Block Sparse Attention with Log-Linear Complexity	Bohao Tang et al.	arXiv	32
2026-09-28	2609.27277	TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent	Jie Yang et al.	arXiv	31
2026-09-28	2609.28845	LastOPD: Taming Collapse in Latent On-Policy Distillation	Jie Yang et al.	arXiv	29
2026-09-28	2609.31394	InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data	Xingyu Miao et al.	arXiv	29
2026-09-28	2609.24385	Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors	Elizaveta Kovtun et al.	arXiv	22
2026-09-28	2609.25716	FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance	Jaihyun Lew et al.	arXiv	19
2026-09-28	2609.29167	IndicBankBench: Evaluating Safety and Reliability of Language Model Assistants in Indian Retail Banking	Suvradip Paul et al.	arXiv	18
2026-09-28	2609.24749	D-JEPA: A Decision-Aligned Latent World Model	Shuaijun Liu et al.	arXiv	16
2026-09-28	2609.30216	Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem	Guoming Ling et al.	arXiv	15
2026-09-28	2609.30222	TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations	Ayush Jain et al.	arXiv	14
2026-09-28	2609.28327	LightMIS: Ultra-Lightweight Medical Image Segmentation Without a Stage-Wise Decoder	Andrei Arhire et al.	arXiv	12
2026-09-28	2609.31199	Enhancing Photogrammetric Digital Surface Models with Pretrained Diffusion Models and Multimodal Conditioning	Antoine Lorentz et al.	arXiv	12
2026-09-28	2609.31590	AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs	Raphael Shu et al.	arXiv	12
2026-09-28	2609.28660	Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy	Tara Sadjadpour et al.	arXiv	12
2026-09-28	2609.29050	SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL	Yan Zhan et al.	arXiv	11
2026-09-28	2609.31473	Game Arena: Strategic LLM Evaluation in Competitive Environments	Bovard Doerschuk-Tiberi et al.	arXiv	11
2026-09-28	2609.30837	MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation	Tianze Xu et al.	arXiv	9
2026-09-28	2608.09444	Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching	Kristian Schwethelm et al.	arXiv	9
2026-09-28	2601.06362	Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs	Yutong Song et al.	arXiv	9
2026-09-28	2609.22237	Not All Ranks Are Equal: Budget-Aware LoRA Merging Across Tasks	Avinash Amballa et al.	arXiv	8
2026-09-28	2609.30192	SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance	Xinyue Zeng et al.	arXiv	8
2026-09-28	2609.30670	TRACE: Temporal Audit and Condition-aware Evaluation of Streaming Video Understanding	Yibo Ma et al.	arXiv	8
2026-09-28	2609.04355	VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models	Chenyu Su et al.	arXiv	7
2026-09-28	2609.23551	Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure	Shuyang Xiang	arXiv	7
2026-09-28	2604.02103	BoundInk: Boundary-Aware Online Handwriting Generation	Jinsu Shin et al.	arXiv	6
2026-09-28	2601.06352	CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation	Yutong Song et al.	arXiv	6
2026-09-28	2609.31291	Softmax Reparameterization for Output-Head Quantization	Asim Kadav et al.	arXiv	5
2026-09-28	2609.29474	CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding	Federico Pennino et al.	arXiv	5
2026-09-28	2609.30867	Evidence-Grounded Auditing of Identification Assumptions in Climate-Policy Causal Evaluations	Yonghong Zhang et al.	arXiv	5
2026-09-28	2609.31002	ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker	Siqiao Xue et al.	arXiv	3
2026-09-25	2609.28654	Training Object Permanence in World Models	Haotian Zhang et al.	arXiv	112
2026-09-25	2609.29845	Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs	Pavel Tikhonov et al.	arXiv	100
2026-09-25	2609.30221	WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation	Yubo Zhu et al.	arXiv	45
2026-09-25	2609.28416	Agent-Editing World Model: Rethinking World Modeling for LLM Agents	Shuang Sun et al.	arXiv	41
2026-09-25	2609.29421	Rufus-Air: An Open LLM Post-Training Recipe	Chia-Yuan Chang et al.	arXiv	39
2026-09-25	2609.23407	OmniEcho: Spatial Audio Understanding for Embodied Agents	Ruixun Liu et al.	arXiv	31
2026-09-25	2609.30199	ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds	Ming Zhang et al.	arXiv	30
2026-09-25	2609.29892	Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents	Tingyu Qu et al.	arXiv	29
2026-09-25	2609.29429	Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures	Ruoqi Guo et al.	arXiv	25
2026-09-25	2609.29837	PUBG Ally: A Conversational Embodied Agent as an AI Teammate	Beomsoo Kim et al.	arXiv	22
2026-09-25	2609.30233	Coding Agents for Generalized Task and Motion Planning Problems	Matteo Merler et al.	arXiv	21
2026-09-25	2609.29444	IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis	Xingyu Wu et al.	arXiv	20
2026-09-25	2609.29362	Parts-of-Speech as Emergent Categories in SAE Latent Space	Alessandro Bondielli et al.	arXiv	17
2026-09-25	2609.28811	DeltaWAM: Delta World Action Models for Bimanual Manipulation	Han Yan et al.	arXiv	17
2026-09-25	2609.28603	Learning to Discover Interesting Mathematics	Niket Patel et al.	arXiv	16
2026-09-25	2609.29964	World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal	Yehang Zhang et al.	arXiv	14
2026-09-25	2609.29647	AgentKernel: The Trust-Native Agentic Operating System	Zhenhua Zou et al.	arXiv	13
2026-09-25	2609.29028	RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation	Shaohua Dong et al.	arXiv	12
2026-09-25	2609.23087	Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone	Chenyu Zhu et al.	arXiv	11
2026-09-25	2609.29816	AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation	Zhiyu Xu et al.	arXiv	9
2026-09-25	2609.28923	ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation	Zichong Meng et al.	arXiv	5
2026-09-25	2609.30077	Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimates	Samuel Fernández-Menduiña et al.	arXiv	5
2026-09-24	2609.28466	The Past Frames the Future: Memory for Autoregressive Video Generation	Harold Haodong Chen et al.	arXiv	57
2026-09-24	2609.24308	HappyWorld-Bench	Zhiqi Bai et al.	arXiv	55
2026-09-24	2609.27334	Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents	Yefan Zhou et al.	arXiv	54
2026-09-24	2609.23038	Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World	Kaixiang Yao et al.	arXiv	41
2026-09-24	2609.26780	SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue	Haobo Zheng et al.	arXiv	36
2026-09-24	2609.22947	RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling	Zhenchen Tang et al.	arXiv	36
2026-09-24	2609.26355	PACT: From Credit Assignment to Critic Alignment	Jiayan Fu et al.	arXiv	28
2026-09-24	2609.27891	Schrödinger's Code Repository: Have LLMs Learned SWE-bench or Memorized It?	Silin Chen et al.	arXiv	28
2026-09-24	2609.26637	Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models	Xiaoyu Luo et al.	arXiv	24
2026-09-24	2609.27284	Hunyuan-A13B Technical Report	Tencent Hunyuan Team et al.	arXiv	21
2026-09-24	2609.27321	Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms	Xinjie Shen et al.	arXiv	21
2026-09-24	2609.27901	All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation	Ohad Rahamim et al.	arXiv	18
2026-09-24	2609.25963	GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression	Baher Mohammad et al.	arXiv	16
2026-09-24	2609.28256	MemBodied: Recurrent Associative Memory for Vision-Language-Action Models	Tej Deep Pala et al.	arXiv	15
2026-09-24	2609.27490	WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents	Jingjie Ning et al.	arXiv	15
2026-09-24	2609.27656	InternW0: A Foundational Physical World Model for Efficient Real-World Interactions	Jisong Cai et al.	arXiv	14
2026-09-24	2609.23784	PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing	Donghao Zhou et al.	arXiv	13
2026-09-24	2609.25853	MemoryAthena: Adaptive Routing over Latent and Generated Memories	Mingyuan Li et al.	arXiv	12
2026-09-24	2609.28473	On the Diffusibility of High-Dimensional Latents	Chao Feng et al.	arXiv	12
2026-09-24	2609.28470	StudentBench: AI and human tutoring yield equivalent GRE learning gains	Curtis Northcutt et al.	arXiv	12
2026-09-24	2609.26634	Knowledge Pull Requests for Continual Document Authoring	Alexander Martin et al.	arXiv	11
2026-09-24	2609.24815	Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI	Wenkang Qin et al.	arXiv	9
2026-09-24	2609.22682	Self-Organizing Agent Teams Learn to Reason Together	Aneesh Pappu et al.	arXiv	7
2026-09-24	2609.27657	FLEET: From Logits Entropy to Enhanced Trajectories in Text Generation	Oleksii Streltsov et al.	arXiv	5
2026-09-24	2609.26489	Calibration as a First-Class Criterion in LLM Evaluation	Mario Sanz-Guerrero et al.	arXiv	4
2026-09-24	2609.27980	Six Layers Less: Encoder Pruning for Whisper with Label-Free Recovery	Rasmus Aagaard et al.	arXiv	4
2026-09-24	2609.27308	EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics	Haoxiang You et al.	arXiv	4
2026-09-24	2609.27158	The Linear Representation Hypothesis Needs a Group Action	Louie Hong Yao et al.	arXiv	3
2026-09-24	2609.25187	X-Planner: Event-Structured Task Planning for Embodied Intelligence	Howard Lu et al.	arXiv	2
2026-09-23	2609.25270	RULER: Instance-aware Rubric Rewards for SVG Generation	Hangyu Ran et al.	arXiv	98
2026-09-23	2609.24981	GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation	Jiahao Lu et al.	arXiv	74
2026-09-23	2609.25165	Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings	Embedding Team	arXiv	68
2026-09-23	2609.25804	The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks	Wenbo Pan et al.	arXiv	53
2026-09-23	2609.24058	All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts	Xingsong Ye et al.	arXiv	53
2026-09-23	2609.26774	StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training	Bao Tang et al.	arXiv	51
2026-09-23	2609.15987	Bellman Policy Optimization	Zhuoqing Song et al.	arXiv	44
2026-09-23	2609.26550	JEV-as-a-Judge: Accept When Confident, Escalate When Unsure	Yubo Li et al.	arXiv	41
2026-09-23	2609.24657	Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models	Xiaoqiang Wang et al.	arXiv	35
2026-09-23	2609.26796	Flash-dLLM: IO-Aware KV Caching and Parallel Decoding for Fast, Memory-Efficient Diffusion LLMs	Quan Nguyen-Tri et al.	arXiv	31
2026-09-23	2609.25186	From Pattern Recognizers to Personalized Companions: A Survey of Large Language Models in Mental Health	He Hu et al.	arXiv	30
2026-09-23	2609.26781	Agensh: Scaling Organizational Intelligence to 1,024 Agents	Zhihao Zhan et al.	arXiv	27
2026-09-23	2609.25199	Lean Pool: An AI-Maintained Archive of Formalized Mathematics	Vasily Ilin	arXiv	24
2026-09-23	2609.26457	Recursive self-improvement of AI research agents	Dhruv Srikanth et al.	arXiv	22
2026-09-23	2609.24967	Emergent Collusion in Long-Horizon LLM Agent Interaction	Xinrui Shi et al.	arXiv	16
2026-09-23	2609.06011	Tri-PvP: Exposing Modality Bias in Omni-Modal Large Language Models through Perceptual-Propositional Evidence Conflicts	Yen-Ting Piao et al.	arXiv	14
2026-09-23	2609.25053	LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay	Simon P. Villani	arXiv	14
2026-09-23	2609.22319	Embedding Physics Priors in Robot Learning: A Survey	Mattia Piccinini et al.	arXiv	11
2026-09-23	2609.25636	RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents	Chang Guo et al.	arXiv	11
2026-09-23	2609.25267	ImIR: Image-Instruction Tuning for All-in-One Image Restoration	Süleyman Aslan et al.	arXiv	9
2026-09-23	2609.26346	Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament	Markus Lundsfryd Jensen et al.	arXiv	8
2026-09-23	2609.26793	HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis	Shufan Sun et al.	arXiv	7
2026-09-23	2609.22323	ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning	Neeraj Yadav	arXiv	7
2026-09-23	2609.25247	Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes	Hanyang Kong et al.	arXiv	7
2026-09-22	2609.24972	RRSI: Regularized Recursive Self-Improvement of Agent Harnesses	Peng Xia et al.	arXiv	173
2026-09-22	2609.24984	WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory	Wangbo Yu et al.	arXiv	160
2026-09-22	2609.13814	Realtime-Venus: A full-duplex interaction system with asynchronous delegation	Ruixiang Zhao et al.	arXiv	151
2026-09-22	2609.23088	OmniEdu: Open Foundation Models for Learning and Teaching	Hao Liang et al.	arXiv	69
2026-09-22	2609.22966	Transferring the Intelligence of VLMs to Robotic Control	Meng-Hao Guo et al.	arXiv	67
2026-09-22	2609.24997	VideoGen-Agent: Reinforcing Video Generation Agents	Binxu Li et al.	arXiv	66
2026-09-22	2609.24220	Document Retrieval-Aware Chunking (D-RAC): Universal Retrieval-Aware Ingestion of Enterprise Documents via PDF Normalization and Multimodal Markdown Conversion	Uday Allu et al.	arXiv	55
2026-09-22	2609.24983	onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction	Lei Yang et al.	arXiv	52
2026-09-22	2609.25001	GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay	Yiran Wang et al.	arXiv	52
2026-09-22	2609.23377	One to More, More to One: Category-Aware Iterative Expert Training for Software Engineering Agents	Jie Zhao et al.	arXiv	47
2026-09-22	2609.24974	Harness-Zero: Harness Distillation via Agent-as-Harness	Haoran Ye et al.	arXiv	34
2026-09-22	2609.23863	Grounded Action Model: 3D Grounding as a Foundation for Robotics	Gehao Zhang et al.	arXiv	30
2026-09-22	2609.23986	Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents	Dongming Jiang et al.	arXiv	30
2026-09-22	2609.23658	Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms	Yueyan Li et al.	arXiv	27
2026-09-22	2609.24118	CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies	Junlan Xiao et al.	arXiv	24
2026-09-22	2609.22255	Deep Persona: A Psychologically Grounded Architecture and Evaluation Framework for Role-Playing Agents and Simulations	Rotem Dror et al.	arXiv	21
2026-09-22	2609.10706	HuRo: Robotizing Human Videos for Scalable VLA Pretraining	Jinho Jeong et al.	arXiv	18
2026-09-22	2609.13231	ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models	Manan Tayal et al.	arXiv	16
2026-09-22	2609.24432	1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation	Huanxin Sheng et al.	arXiv	16
2026-09-22	2609.22870	Towards Full Pipeline FP8 Reinforcement Learning for LLMs	Fanchao Chen et al.	arXiv	14
2026-09-22	2609.15991	The Functionalizer: Lossless Functional Decomposition for Subword Tokenization	Connor Makowski et al.	arXiv	14
2026-09-22	2609.24797	Complex KDA: Understanding and Enhancing the Expressivity of Kimi Delta Attention	Julien Siems et al.	arXiv	13
2026-09-22	2609.24682	Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies	Trung Dao et al.	arXiv	13
2026-09-22	2609.23989	ACLArena: Agent Continue Learning in Multi-stage Post-training	Haixin Wang et al.	arXiv	12
2026-09-22	2609.06052	SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness	Yizhuo Zhang et al.	arXiv	11
2026-09-22	2609.21996	A Lie Detector Test for Language Models: Reading Knowledge a Model Won't Reveal	Hiskias Dingeto	arXiv	7
2026-09-22	2609.24788	Streaming Video Editing with Easy Adaptation	Yujia Hu et al.	arXiv	7
2026-09-22	2609.11063	The information geometry of large language models is shared, learned, and controllable	Dario Picozzi	arXiv	6
2026-09-22	2609.22220	Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles	Mingzhe Du et al.	arXiv	6
2026-09-22	2609.24115	EDGEGEN: Improving Tool-Calling Agents Beyond Happy Paths with Synthetic Edge Case Generation	Harshavardhan Abichandani et al.	arXiv	5
2026-09-22	2609.20758	Prediction-Powered Smoothing and Validation for Disaggregated AI Evaluation	Sho Kawano et al.	arXiv	4
2026-09-22	2609.23169	UltraTex: Unleashing 2K Multi-View Diffusion for 3D Texturing	Yibo Zhang et al.	arXiv	3
2026-09-22	2609.23796	Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene	Yang-Tian Sun et al.	arXiv	3
2026-09-22	2609.20869	TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision	Sergey Kurinov et al.	arXiv	2
2026-09-21	2609.22068	CodeMidas: Scaling Agentic Coding RL Environments from Code Itself	Bowen Ye et al.	arXiv	129
2026-09-21	2609.15779	EvoOntology: A Self-Evolving Ontology Layer for Data Agents	Meiduo Chong et al.	arXiv	104
2026-09-21	2609.05571	Grounded Skill Synthesis from Code at Scale for Agentic Intelligence	Yongqi Tong et al.	arXiv	92
2026-09-21	2609.22000	RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents	Shuai Bai et al.	arXiv	76
2026-09-21	2609.21465	OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue	Haolin He et al.	arXiv	69
2026-09-21	2609.20816	Paint-Anything: Unified Any-Color Control for Image Generation and Editing	Ji Xie et al.	arXiv	50
2026-09-21	2609.21346	IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts	Ran Cheng et al.	arXiv	42
2026-09-21	2609.22086	Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design	Hongyang Du et al.	arXiv	34
2026-09-21	2609.22069	OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation	Wenxue Li et al.	arXiv	33
2026-09-21	2609.22083	MintAct: A Unified Visual Agent for Digital Environments	Mingfei Gao et al.	arXiv	27
2026-09-21	2609.20886	BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence	Chuxuan Hu et al.	arXiv	26
2026-09-21	2609.18620	DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation	Can Li et al.	arXiv	22
2026-09-21	2609.21749	GraphSkillEvo: Evolutionary Optimization of Graph-Structured Agent Skills	Rui Sun et al.	arXiv	18
2026-09-21	2609.16251	CADWorld: Computer-Use Benchmark for Long-Horizon Computer-Aided Design	Zihan Dong et al.	arXiv	15
2026-09-21	2609.15126	MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup	Muchen Li et al.	arXiv	12
2026-09-21	2609.21788	From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention	Sichang Su et al.	arXiv	11
2026-09-21	2609.22039	Gricea: An Open Science Platform for Conversational AI Research	Nikhil Sharma et al.	arXiv	11
2026-09-21	2609.09206	MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads	Meng'en Qin et al.	arXiv	11
2026-09-21	2609.18748	TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection	Huiyuan Liu et al.	arXiv	10
2026-09-21	2609.21619	Calibrating Teacher--Student Discrepancy for On-Policy Distillation	Qiangqiang He et al.	arXiv	10
2026-09-21	2609.20633	Refinement Is Inherently Editable: Training-Free Prompt-to-Prompt Image Editing with Generative Refinement Network	Yulong Chen et al.	arXiv	9
2026-09-21	2609.19169	SiliconBench: Speed, Memory, and Fidelity for LLM Serving on Unified-Memory Desktops	Ranran Haoran Zhang et al.	arXiv	8
2026-09-21	2609.20942	When AI Reviews Train AI Reviewers: Scientific-Judgment Collapse and Mitigation	Sy-Tuyen Ho et al.	arXiv	8
2026-09-21	2609.20669	Learning Foresight without Explicit Trajectories for 3D Diffusion Policies	Zhongbo Zhang et al.	arXiv	8
2026-09-21	2609.19315	GAVEL: Graph World Models for Verified and Efficient Long-Horizon LLM Task Planning	Ruiyang Wang et al.	arXiv	6
2026-09-21	2609.18766	FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection	Chengxian Hu et al.	arXiv	6
2026-09-21	2609.12623	SteerDuplex: Steerable Duplex Speech Dialogue Models	Utkarsh Tyagi et al.	arXiv	5
2026-09-21	2609.21094	Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models	Utkarsh Agarwal et al.	arXiv	5
2026-09-21	2609.19122	Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation	Meng'en Qin et al.	arXiv	5
2026-09-21	2609.22076	APort Vault: Benchmarking AI Agent Payment Authorization with the Open Agent Passport	Uchi Uchibeke	arXiv	3
2026-09-21	2609.21038	Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy	Sebastián A. Cruz Romero	arXiv	3
2026-09-18	2609.19969	DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression	DeepSeek-AI et al.	arXiv	213
2026-09-18	2609.20519	SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness	Haozhe Liu et al.	arXiv	112
2026-09-18	2609.20804	An Empirical Study of Harness Design for Coding Agents	Run-Ze Fan et al.	arXiv	68
2026-09-18	2609.20511	When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation	Yuxiao Yang et al.	arXiv	59
2026-09-18	2609.20800	JEPA-Anything: Learning Predictive Models across Different Worlds	Taoyong Cui et al.	arXiv	55
2026-09-18	2609.18323	Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model	Haoyu Zhao et al.	arXiv	52
2026-09-18	2609.17496	Verifiable Social Reasoning for LLM Assistants	Amir Taubenfeld et al.	arXiv	43
2026-09-18	2609.19656	Self-Evolving Search Index	Sangam Lee et al.	arXiv	38
2026-09-18	2609.20784	RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning	Yan Yu et al.	arXiv	31
2026-09-18	2609.19671	When2Think: Learning When and How Much to Reason	Jaejun Shim et al.	arXiv	31
2026-09-18	2609.20744	Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation	Haocheng Xi et al.	arXiv	29
2026-09-18	2609.20423	WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing	Hao Yu et al.	arXiv	24
2026-09-18	2609.16900	RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation	ZhuoXin Liu et al.	arXiv	23
2026-09-18	2609.17653	Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents	Bofan Chen et al.	arXiv	21
2026-09-18	2609.19554	VABench: Measuring Embodied Spatial Intelligence through Visual Demonstrations, Active Perception, and Metric Control	Zhongbo Zhang et al.	arXiv	20
2026-09-18	2609.20715	Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL	Juzheng Zhang et al.	arXiv	19
2026-09-18	2609.12397	UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation	Danning Zhang et al.	arXiv	18
2026-09-18	2609.20817	FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations	Kevin Qu et al.	arXiv	16
2026-09-18	2609.19745	Region-Level Policy Optimization for Fine-grained MLLM Perception	Yuheng Shi et al.	arXiv	16
2026-09-18	2609.18605	PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?	Mika Okamoto et al.	arXiv	15
2026-09-18	2609.05661	Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts	Anil Pai	arXiv	14
2026-09-18	2609.19499	Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling	Mobina Kashaniyan et al.	arXiv	13
2026-09-18	2609.20612	What Does Privileged Information Add to On-Policy Self-Distillation?	XiuYu Zhang et al.	arXiv	11
2026-09-18	2609.19879	VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering	Bhavana Akkiraju et al.	arXiv	8
2026-09-17	2609.17488	LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence	Xingxuan Zhang et al.	arXiv	284
2026-09-17	2609.19134	ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments	Hejia Geng et al.	arXiv	82
2026-09-17	2609.18708	Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening	Yizhuo Li et al.	arXiv	63
2026-09-17	2609.17708	Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents	Caiqi Zhang et al.	arXiv	58
2026-09-17	2609.18805	ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks	Jeonghye Kim et al.	arXiv	46
2026-09-17	2609.18094	Agora: Git as Shared Memory for Collective AutoResearch	Yifan Zhang et al.	arXiv	35
2026-09-17	2609.15810	VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention	Xingyang Li et al.	arXiv	30
2026-09-17	2609.18063	The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction	Yu Lin et al.	arXiv	29
2026-09-17	2609.19138	In-Context Robot Learning with VLM Agents	Dongzhou Cheng et al.	arXiv	28
2026-09-17	2609.18487	ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models	Shijie Lian et al.	arXiv	28
2026-09-17	2609.17909	Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control	Mingyang Chen et al.	arXiv	26
2026-09-17	2609.17632	EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents	Sehee Kim et al.	arXiv	25
2026-09-17	2609.14306	Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training	Shrey Pandit et al.	arXiv	18
2026-09-17	2609.19143	PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection	Sara Pieri et al.	arXiv	17
2026-09-17	2609.18779	CERA-MoA: Co-Evolving Routing Mechanisms with Continually Learning LLM Agents	Jiaxuan Jiang et al.	arXiv	15
2026-09-17	2609.14320	SpectralShift: Effective Context Window Extension of Gated DeltaNet via Spectral Reparameterization	Zian Liu et al.	arXiv	13
2026-09-17	2609.19144	A Zeroth-Order Paradigm for LLM Preference Alignment	Peter Chen et al.	arXiv	12
2026-09-17	2609.18011	Gaze as Evidence for Common Grounding: A Cross-Corpus Analysis of MapTask and MUNDEX	Nan Li et al.	arXiv	10
2026-09-17	2609.15938	HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses	Jieyuan Liu et al.	arXiv	9
2026-09-17	2609.17172	Fingers as Legs: Learning Self-Supported Locomotion and Manipulation with an Anthropomorphic Hand	Amirhossein Kazemipour et al.	arXiv	6
2026-09-17	2609.17189	EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset	Ryosei Hara et al.	arXiv	6
2026-09-17	2609.17652	Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches	Vivek Kalyanarangan	arXiv	5
2026-09-17	2609.15524	Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026	Tristan Kirscher et al.	arXiv	2
2026-09-16	2609.16679	AI for Games in the Foundation Model Era	Meng Luo et al.	arXiv	124
2026-09-16	2609.14005	StepAudio 3 Realtime Technical Report	Bin Lin et al.	arXiv	120
2026-09-16	2609.16034	StepAudio 3 Music Technical Report	Chengli Feng et al.	arXiv	103
2026-09-16	2609.06986	Continual Learning Mechanisms Compose for Long-Horizon Memorization	Zheyuan Zhang et al.	arXiv	94
2026-09-16	2609.14857	ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement	Siwei Wu et al.	arXiv	73
2026-09-16	2609.17523	ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents	Shuhan Xue et al.	arXiv	29
2026-09-16	2609.15195	HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness	Yang Chen et al.	arXiv	19
2026-09-16	2609.11873	The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement	Yi Duan et al.	arXiv	19
2026-09-16	2609.16591	FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation	Guangyu Sun et al.	arXiv	16
2026-09-16	2609.13406	Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement	Hongyao Tang et al.	arXiv	13
2026-09-16	2609.17524	Modality-Autoregressive World-Action Models	Adam Hung et al.	arXiv	11
2026-09-16	2609.17521	PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control	Chuhao Chen et al.	arXiv	10
2026-09-16	2609.13680	Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models	Fei Yuan et al.	arXiv	10
2026-09-16	2609.16816	ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals	Bowen Qin et al.	arXiv	9
2026-09-16	2609.15972	Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States	Zixuan Wang et al.	arXiv	9
2026-09-16	2609.15975	Disentangling Representation Evolution in Transformers through Directional Decomposition	Shwai He et al.	arXiv	9
2026-09-16	2609.12552	RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs	Maëlic Neau	arXiv	8
2026-09-16	2609.13770	Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation	Yilei Tu et al.	arXiv	8
2026-09-16	2609.16372	Register Tokens for Bounded-State Reasoning in Diffusion Language Models	Albert Ge et al.	arXiv	7
2026-09-16	2609.14803	Another Blueprint In The Wall: How to Ask Frontier AI Like a Kid?	Afshin Khadangi	arXiv	7
2026-09-16	2609.15982	The Router Within: Eliciting Native Skill Routing from a Frozen LLM	Ruishuo Chen et al.	arXiv	7
2026-09-16	2609.16204	Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration	Aashiq Muhamed et al.	arXiv	4
2026-09-16	2609.16057	OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning	Xu Xu et al.	arXiv	3
2026-09-16	2609.14011	Convergent Emergence of In-Context Learning Across Modalities	Nathan Breslow et al.	arXiv	3
2026-09-16	2609.17320	Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems	Deepak Akkil et al.	arXiv	3
2026-09-15	2609.15818	Atria Dawn: The Dawn of Agentic Superintelligence	Honglin Guo et al.	arXiv	253
2026-09-15	2609.11638	Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation	Jintao Zhang et al.	arXiv	237
2026-09-15	2609.14858	Dream-RSI: Recursive Self-Improvement through Evolving Worlds	Tong Zheng et al.	arXiv	148
2026-09-15	2609.13356	ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search	Jiyan He et al.	arXiv	103
2026-09-15	2609.15364	RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments	Sibo Zhu et al.	arXiv	88
2026-09-15	2609.13285	Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction	Vishesh Tripathi et al.	arXiv	68
2026-09-15	2609.14973	PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models	DeepCybo Team et al.	arXiv	64
2026-09-15	2609.15863	LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual Workflows	Xiaofeng Mao et al.	arXiv	34
2026-09-15	2609.15973	Discovery Foundation Models: Toward Open-Ended Discovery Intelligence	Ling Yang et al.	arXiv	33
2026-09-15	2609.15478	BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender	Yolo Y. Tang et al.	arXiv	31
2026-09-15	2609.14462	AlayaVista: Streaming World Modeling from Panoramic States to Perspective Video	Jiaming Tan et al.	arXiv	27
2026-09-15	2609.15128	Omni-Streaming Thinking	Enjun Du et al.	arXiv	22
2026-09-15	2609.15504	How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus	Ilya Koziev et al.	arXiv	21
2026-09-15	2609.15659	Kaininja: Extending Native 3D Generators to the Part Level	Ruihan Yu et al.	arXiv	19
2026-09-15	2609.15134	HazardAuditor: From Executable Threats to Safer Computer-Use Agents	Yunhao Feng et al.	arXiv	18
2026-09-15	2609.12541	Agent as Policy for Robotic Manipulation	Mengzhao Jia et al.	arXiv	17
2026-09-15	2609.13287	LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI Agents	Zhangxuan Gu et al.	arXiv	16
2026-09-15	2609.13443	Learning to Solve Hard Problems in RL for LLMs by Never Giving Up	Michael Noukhovitch et al.	arXiv	15
2026-09-15	2609.15051	Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training	Yuanhao Yue et al.	arXiv	13
2026-09-15	2609.12419	MInTRL: Off-policy Intervention can boost On-policy RL	Mingyu Chen et al.	arXiv	12
2026-09-15	2609.15309	When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis	Kaiyuan Liu et al.	arXiv	10
2026-09-15	2609.13053	Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model	Hoeun Lee et al.	arXiv	9
2026-09-15	2609.13498	Building a Production Greek-English Speech Recognizer	Christos Petrocheilos et al.	arXiv	9
2026-09-15	2609.15078	Enabling Creative Exploration for Vibe Design Agents	Yifan Zhang et al.	arXiv	9
2026-09-15	2609.15029	Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks	Aashiq Muhamed et al.	arXiv	8
2026-09-15	2609.13318	Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning	Changbo Yan et al.	arXiv	7
2026-09-15	2609.15635	ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs	Sebastián Andrés Cajas Ordóñez et al.	arXiv	6
2026-09-15	2609.13058	Expert-Space Exploration in MoE Reinforcement Learning	Hongyi He et al.	arXiv	6
2026-09-15	2609.13463	Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures	Harsh Raj et al.	arXiv	5
2026-09-15	2609.14708	Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition	Yecheng Wu et al.	arXiv	4
2026-09-15	2609.14302	E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning	Xiaoya Wang et al.	arXiv	3
2026-09-15	2609.13948	Thought without systematicity? Evaluating reasoning models on rule induction tasks	Simon Schug et al.	arXiv	3
2026-09-15	2609.01430	Learning Sparse Decision Trees via Transformer Variational Auto-Encoders	Giacomo Fidone et al.	arXiv	2
2026-09-14	2609.11115	Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation	Koutian Wu et al.	arXiv	153
2026-09-14	2609.12945	StepAudio 3 Gen Technical Report	Bin Lin et al.	arXiv	100
2026-09-14	2609.13141	SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking	Zhiwei Li et al.	arXiv	68
2026-09-14	2609.06107	DataFlex-RL: An Evaluation Platform for RLVR Data Policies	Hao Liang et al.	arXiv	66
2026-09-14	2609.12641	Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models	Jianman Lin et al.	arXiv	64
2026-09-14	2609.10895	ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embodied Multimodal LLMs	Yizhan Li et al.	arXiv	51
2026-09-14	2609.11682	COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization	Pingchen Lu et al.	arXiv	43
2026-09-14	2609.11977	Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work	Wenhui Chen et al.	arXiv	33
2026-09-14	2609.08418	Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models	Zongjie Li et al.	arXiv	33
2026-09-14	2608.30597	PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization	Boryeong Cho et al.	arXiv	27
2026-09-14	2609.12036	Pelican-Sim 1.0: A General World Model Simulator for Embodied Intelligence	Shilong Zou et al.	arXiv	23
2026-09-14	2609.08230	ActionSplice: In-Flight Action Editing for Interactive World Models	Pardis Taghavi et al.	arXiv	12
2026-09-14	2609.05824	Beyond Top-k Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents	Wang Wei et al.	arXiv	8
2026-09-14	2609.06251	MobileVLA-R1 2.0: RL-Enhanced Reasoning for Mobile Robot Control	Ting Huang et al.	arXiv	6
2026-09-14	2609.05820	Online Learning with LLM Experts from Limited Feedback	Wang Wei et al.	arXiv	6
2026-09-14	2609.10824	Studying Without a Syllabus: Task-Agnostic Environment Preprocessing	Vinay Samuel et al.	arXiv	5
2026-09-14	2609.10297	TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents	Yuhao Wang et al.	arXiv	4
2026-09-14	2609.03595	How Far Can Synthetic Data Take Thai OCR?	Kunat Pipatanakul	arXiv	4
2026-09-14	2609.07099	Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision	Logesh Kumar Umapathi	arXiv	3
2026-09-14	2609.07154	Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B Model	Logesh Kumar Umapathi	arXiv	3
2026-09-14	2609.13146	SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image	Yu-Rou Tuan et al.	arXiv	3
2026-09-14	2609.12101	Competence-Gated Pooling of Language Models and Priors for Event Forecasting	Aditi Tiwari et al.	arXiv	2
2026-09-14	2609.10728	Towards a Deterministic Math Solver for Clinical Language Models	Felipe Ocampo Osorio et al.	arXiv	2
2026-09-14	2609.03502	Building and Evaluating Fixed-Voice Thai TTS from Synthetic Speech	Kunat Pipatanakul et al.	arXiv	2
2026-09-14	2609.08365	ReMoMask-2: Latent Retrieval-Augmented Masked Motion Generation	Yiran Wang et al.	arXiv	1
2026-09-14	2609.12078	Feature Recovery for Object Understanding After Irreversible Fire Damage	Aditi Tiwari et al.	arXiv	1
2026-09-11	2609.10715	NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction	NCP Team et al.	arXiv	176
2026-09-11	2609.11929	SenseNova-U1.5: Towards Native Unified Visual Intelligence	Haiwen Diao et al.	arXiv	145
2026-09-11	2609.07064	SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem	Soohyun Ryu et al.	arXiv	62
2026-09-11	2609.11317	Mi-Ripple: Restoring Images Degraded by Iterative AI Editing	Jiayin Chen et al.	arXiv	29
2026-09-11	2609.11412	X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation	Haojun Zhang et al.	arXiv	24
2026-09-11	2609.11561	Memory as Plans: World-Action Modeling with Memory-Grounded Planning	Sizhe Zhao et al.	arXiv	21
2026-09-11	2609.10712	An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics	Ivan Moshkov et al.	arXiv	21
2026-09-11	2609.05903	EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents	Nanxi Li et al.	arXiv	20
2026-09-11	2609.11699	Negative Self-Distillation: Learning to Reason by Avoiding Flaws	Rongcan Pei et al.	arXiv	13
2026-09-11	2609.11548	World in World: Explore the World with World Models	Chenxi Song et al.	arXiv	13
2026-09-11	2609.10445	Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning	Mehrnaz Mofakhami et al.	arXiv	12
2026-09-11	2609.11085	Beyond Solver Verdicts: Generative Reward Models for Autoformalization	Vikash Singh et al.	arXiv	12
2026-09-11	2609.11486	FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation	Vladislav Bargatin et al.	arXiv	12
2026-09-11	2609.11499	Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs	Zhiqi Li et al.	arXiv	12
2026-09-11	2609.09143	Studying Image Tokenizers as Visual Languages in Unified Multimodal Models	Siting Li et al.	arXiv	10
2026-09-11	2609.01515	TempCloze: Can Video-LLMs Identify the Missing Middle?	Wenqi Pei et al.	arXiv	10
2026-09-11	2609.11155	DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat	Junlin Liu et al.	arXiv	7
2026-09-11	2609.10016	MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes	Remco Hendriks	arXiv	7
2026-09-11	2609.09076	ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation	Yiling Ma et al.	arXiv	6
2026-09-11	2609.11808	Generative Late-Interaction Embeddings For Visual Document Retrieval	Mohamed Eltahir et al.	arXiv	6
2026-09-11	2608.27875	HyQuant: Hybrid-Precision Quantization for LLM Attention	Jiatong Ding et al.	arXiv	6
2026-09-11	2608.15380	Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2	Kaushalraj Puwar et al.	arXiv	5
2026-09-11	2609.10539	IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications	Yiling Ma et al.	arXiv	4
2026-09-11	2609.06931	CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation	Jia-Jen Lee et al.	arXiv	4
2026-09-11	2609.11156	UniH^3: Unifying Hierarchical Homogeneity and Heterogeneity for All-in-One Medical Image Restoration	Zhiwen Yang et al.	arXiv	3
2026-09-11	2609.10745	Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking	Parinthapat Pengpun et al.	arXiv	2
2026-09-10	2609.10522	Show-Harness: Just a VLM Agent Can Play Robots	Yanzhe Chen et al.	arXiv	102
2026-09-10	2608.12564	Scaling Automatic Research Agents via World Models	Xiyuan Yang et al.	arXiv	82
2026-09-10	2609.10540	Programmable World Model	Zheng-Hui Huang et al.	arXiv	75
2026-09-10	2609.11042	T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks	Junyao Yang et al.	arXiv	65
2026-09-10	2609.08572	AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems	Jaewon Chu et al.	arXiv	33
2026-09-10	2609.05405	WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data	Ji Soo Lee et al.	arXiv	24
2026-09-10	2609.06702	PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents	Kun Li et al.	arXiv	23
2026-09-10	2609.09113	SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?	Yuqiao Tan et al.	arXiv	20
2026-09-10	2609.00369	Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation	Vida Adeli et al.	arXiv	20
2026-09-10	2609.07103	Revisiting Complete Reasoning Traces for Post-Training	Jaehui Hwang et al.	arXiv	20
2026-09-10	2609.10226	Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?	Leilei Ding et al.	arXiv	16
2026-09-10	2609.09155	SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators	Yuncong Yang et al.	arXiv	14
2026-09-10	2609.09219	Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents	Jingjie Ning et al.	arXiv	13
2026-09-10	2609.09187	AgenticGen: Reward-Guided Agentic Video Generation for Advertising	Xingyuan Bu et al.	arXiv	13
2026-09-10	2609.10355	Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs	Killian Steunou et al.	arXiv	12
2026-09-10	2609.08126	SchemeArena: Factorized Stress Testing of Scheming in LLM Agents	Jie Ruan et al.	arXiv	11
2026-09-10	2609.06703	DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents	Yubin Wang et al.	arXiv	11
2026-09-10	2609.08149	SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents	Pujun Zheng et al.	arXiv	10
2026-09-10	2609.09134	Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails	Zhou Yu et al.	arXiv	10
2026-09-10	2609.09264	StochBench: A Domain-Specific Benchmark for Stochastic Processes in Lean	Idan Davidovich et al.	arXiv	8
2026-09-10	2609.05779	Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models	Andrej Andrejev	arXiv	8
2026-09-10	2609.05463	A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware	Ayushman Bhattacharya et al.	arXiv	7
2026-09-10	2609.08650	Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR	Youngjun Yu et al.	arXiv	7
2026-09-10	2609.06490	OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution	Shubhashis Roy Dipta et al.	arXiv	6
2026-09-10	2609.06806	Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning	Nagham Omar et al.	arXiv	5
2026-09-10	2609.02771	From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution	Yuzhang Luo et al.	arXiv	4
2026-09-10	2609.08965	PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving	Yuan Gao et al.	arXiv	4
2026-09-10	2609.07369	DF26: We Cannot Tell Fake From Real Anymore	Severyn Shykula et al.	arXiv	4
2026-09-10	2609.10296	The Semantic Bottleneck: Leveraging Semantic Representations for Non-Invasive Speech Decoding	Gilad D. Landau et al.	arXiv	3
2026-09-10	2609.09657	RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems	Haichuan Hu et al.	arXiv	3
2026-09-10	2509.01809	The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements	Youssef Chaabouni et al.	arXiv	2
2026-09-10	2609.10060	Reference-Based Bias Detection in LLMs via Relative Representations of Hidden States	Marek Jeliński et al.	arXiv	2
2026-09-09	2609.08936	AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing	Ziyang Ma et al.	arXiv	138
2026-09-09	2609.08183	NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness	NeoHorse Team et al.	arXiv	74
2026-09-09	2609.07398	OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining	Yuran Wang et al.	arXiv	73
2026-09-09	2609.08977	Omni Interaction Agent Technical Report	Orantqing et al.	arXiv	73
2026-09-09	2609.08798	Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation	Youngrok Park et al.	arXiv	68
2026-09-09	2609.08084	Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation	Igor Pavlovic et al.	arXiv	59
2026-09-09	2609.08368	Miles v0.1: Production-Level Post-Training	RadixArk et al.	arXiv	47
2026-09-09	2609.06055	DriveZero: End-to-End Driving Beyond Human Demonstrations	Hao He et al.	arXiv	41
2026-09-09	2609.05588	GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation	AgiBot Research Team et al.	arXiv	40
2026-09-09	2609.09123	Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout	Zhuoran Zhao et al.	arXiv	31
2026-09-09	2609.04280	EVOHARNESSBENCH: Can Your Agents Keep Pace with an Evolving Harness?	Zixuan Ke et al.	arXiv	29
2026-09-09	2609.09153	Procedural Graphs: Self-Evolving Execution Structures for LLM Agents	Yuxing Lu et al.	arXiv	26
2026-09-09	2609.04971	BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference	Janghyeon Kim et al.	arXiv	24
2026-09-09	2609.06758	Agentic Visual Generation: From Generative Models to Agentic Control	Yinming Huang et al.	arXiv	21
2026-09-09	2609.05592	What Did I Just Say? Self-Listening for Full-Duplex Speech Models	Xuanning Zhou et al.	arXiv	20
2026-09-09	2609.06746	Reason Through the Latent! Making Latent Visual Reasoning Necessary	Suhyeong Park et al.	arXiv	20
2026-09-09	2609.05594	SceneMosaic: Efficient and Diverse Simulation-Ready Scene Generation via Hybrid Agentic Layout Evolution	Xingjian Ran et al.	arXiv	20
2026-09-09	2609.08108	SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation	Soroush Mehraban et al.	arXiv	17
2026-09-09	2609.07498	CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial Movements	Hongxiang Zhao et al.	arXiv	17
2026-09-09	2609.07108	Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training	Zili Wang et al.	arXiv	17
2026-09-09	2609.07816	Kalman Delta Networks: Uncertainty-aware Associative Memory	Ngoc Bui et al.	arXiv	16
2026-09-09	2609.00787	StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?	Yinghao Chen et al.	arXiv	14
2026-09-09	2609.06245	VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification	Yixin Wan et al.	arXiv	14
2026-09-09	2609.06289	Steering Geometry: Validating Human Value Geometry in LLM Steering Space	Mohammad Mahdi Abootorabi et al.	arXiv	14
2026-09-09	2609.05324	RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?	Zhenxuan Fan et al.	arXiv	13
2026-09-09	2609.07670	Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection	Xuechao Zou et al.	arXiv	10
2026-09-09	2609.08404	Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks	Hongbang Yuan et al.	arXiv	10
2026-09-09	2609.07821	A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM	Xiaoang Xu et al.	arXiv	9
2026-09-09	2609.08345	CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs	Nhat-Tan Bui et al.	arXiv	9
2026-09-09	2609.07470	Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy	Ayoub Kirouane et al.	arXiv	8
2026-09-09	2609.09158	TANGO: Humanoid Navigation in Cluttered Environments with a Whole-Body Vision-Language-Action Model	Anqi Li et al.	arXiv	7
2026-09-09	2609.06665	TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation	Mingwei Li et al.	arXiv	6
2026-09-09	2609.06652	VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes	Yan Ma et al.	arXiv	6
2026-09-09	2609.02881	Graph Machine: Towards Better Pretraining via Edges	Lintai Hou	arXiv	5
2026-09-09	2510.08999	SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions	Ziyi Wang et al.	arXiv	5
2026-09-09	2609.07941	ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding	Chia-Hui Chen et al.	arXiv	4
2026-09-09	2609.06966	MOLE: Detecting Insider Threats in AI Agents	Aashiq Muhamed et al.	arXiv	4
2026-09-09	2609.05738	RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives	Chong Zeng et al.	arXiv	3
2026-09-09	2609.09140	NOAH: Learning the Full Patient Journey. A Longitudinal Multimodal Time-Aware Model for Representation and Forecasting	Tobias Susetzky et al.	arXiv	3
2026-09-09	2609.06140	Counter-Swarm Doctrine: Containing Coordinated Agent Intrusions	Gregory N Frank	arXiv	3
2026-09-09	2609.07139	Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise	Mika Okamoto et al.	arXiv	3
2026-09-09	2609.06008	Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model	Roberto Tacconelli	arXiv	3
2026-09-09	2609.06373	Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation	Jiawei Mao et al.	arXiv	3
2026-09-09	2609.05663	What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record from Two Fleets	T. J. Barton et al.	arXiv	3
2026-09-09	2609.03209	MasterControl Seventeen Every Time	MasterControl AI Lab	arXiv	2
2026-09-09	2609.07414	RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting	Hejun Wang et al.	arXiv	2
2026-09-09	2608.29109	Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions	Yucheng Du et al.	arXiv	2
2026-09-09	2609.04942	Learning 3D Editing without Paired Supervision via Generative Prior Distillation	Hao Wen et al.	arXiv
2026-09-08	2609.04010	Unlocking Lossless Speedups in LLMs via Discrete Diffusion	Subham Sekhar Sahoo et al.	arXiv	105
2026-09-08	2609.03241	FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience	Zixun Huang et al.	arXiv	43
2026-09-08	2609.03003	Causal Foundation Models	Christopher Stith et al.	arXiv	25
2026-09-08	2609.03756	ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation	Javier del Pino et al.	arXiv	18
2026-09-08	2609.02998	Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation	Zhiwei Zhang et al.	arXiv	16
2026-09-08	2609.05533	SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models	Cheng Yin et al.	arXiv	13
2026-09-08	2608.25936	One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation	Justin Robert et al.	arXiv	13
2026-09-08	2609.01281	EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents	Wei Wang et al.	arXiv	13
2026-09-08	2609.04482	Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal	Alejo López-Ávila et al.	arXiv	10
2026-09-08	2609.03005	Unifying Conformal Language Tasks with In-Context Ensembles	Xiao Shi Huang et al.	arXiv	9
2026-09-08	2609.04382	Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys	Georgios Politis et al.	arXiv	4
2026-09-08	2609.03254	What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation	Daisuke Kikuta	arXiv	3
2026-09-07	2609.02750	Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems	Yihang Chen et al.	arXiv	142
2026-09-07	2609.04304	Iris: Climbing to the Search Frontier	Ziyuan Liu et al.	arXiv	50
2026-09-07	2609.04250	Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue	Chengqian Ma et al.	arXiv	43
2026-09-07	2609.03586	The Attention Triangle in Audio-Video Models	Sagi Polaczek et al.	arXiv	41
2026-09-07	2609.00365	Dr. Claw: An AI Scientist Workspace for Vibe Research	Dingjie Song et al.	arXiv	37
2026-09-07	2609.00581	Enoki: Efficient Multi-Level Hallucination Detection	Elisei Rykov et al.	arXiv	27
2026-09-07	2609.05416	WorldSculpt: Generating Compositional Worlds from Grounded Videos	Muyao Niu et al.	arXiv	24
2026-09-07	2609.05415	UniMate: One Unified Model to Animate Diverse Skeletons	Linzhan Mou et al.	arXiv	23
2026-09-07	2609.05275	Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference	Mostafa Elhoushi et al.	arXiv	23
2026-09-07	2609.05258	Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization	Sihan Ge et al.	arXiv	19
2026-09-07	2609.05295	RISE: Recursive Improvement via Self-Extrapolating Policy Distillation	Yang Li et al.	arXiv	18
2026-09-07	2609.04523	MaxKernel: Agentic Kernel Generation for TPUs	Shangkun Wang et al.	arXiv	17
2026-09-07	2609.04753	Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs	Seogyeong Jeong et al.	arXiv	14
2026-09-07	2609.04611	τ^τ-Bench: An Environment for End-To-End, Realistic Agent Construction	Quan Shi et al.	arXiv	10
2026-09-07	2609.03729	Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning	Yijun Yang et al.	arXiv	9
2026-09-07	2609.00444	Group Adaptive Clipping Policy Optimization	Sheng Jia et al.	arXiv	9
2026-09-07	2609.04061	When Models Edit Too Much: On the Fidelity of Minimal Code Edits	Tongyao Zhu et al.	arXiv	8
2026-09-07	2609.04720	Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models	Minji Kim et al.	arXiv	7
2026-09-07	2608.05879	To See a World in a Living Context: Unified Indoor-Outdoor Urban World Generation	Xiaobin Huang et al.	arXiv	7
2026-09-07	2609.04190	One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video Editing	Adheesh Sunil Juvekar et al.	arXiv	6
2026-09-07	2609.04714	Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models	Minji Kim et al.	arXiv	5
2026-09-07	2609.04490	When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference	Ismail Erbas et al.	arXiv	5
2026-09-07	2609.04444	HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals	Jasmine Brazilek et al.	arXiv	4
2026-09-07	2608.24263	Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing	Yaoyi Qi et al.	arXiv	3
2026-09-07	2609.03231	The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100	Francesco Mantegna et al.	arXiv	3
2026-09-07	2609.02780	ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding	Jitai Hao et al.	arXiv	3
2026-09-07	2609.04369	AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition	Shunpeng Chen et al.	arXiv	3
2026-09-07	2609.04242	Training-Free Speech-Centric Omni Understanding with Frozen VLMs	Ankan Deria et al.	arXiv	2
2026-09-04	2609.04172	Rethinking On-Policy Distillation of Large Language Models II: One Training Example	Zixuan Fu et al.	arXiv	82
2026-09-04	2609.04148	Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments	Jie Wu et al.	arXiv	80
2026-09-04	2609.03430	Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning	Heng Wang et al.	arXiv	73
2026-09-04	2609.03796	LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes	Chuyan Chen et al.	arXiv	58
2026-09-04	2609.04199	Compile by Training: Turning Natural-Language Specifications into Local Neural Functions	Yuntian Deng et al.	arXiv	55
2026-09-04	2609.04196	Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States	Kang Liao et al.	arXiv	50
2026-09-04	2609.04201	Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction	Chin-Yang Lin et al.	arXiv	39
2026-09-04	2609.04173	Last Translation Benchmark	Vilém Zouhar et al.	arXiv	33
2026-09-04	2609.01507	LatentPress: Context Compression Beyond Text and Vision	Zhengze Zhou et al.	arXiv	25
2026-09-04	2608.26730	Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training	Tingyun Li et al.	arXiv	24
2026-09-04	2609.04098	Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM	Sergii Kozyrev et al.	arXiv	24
2026-09-04	2609.04094	DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training	Shubham Gandhi et al.	arXiv	21
2026-09-04	2609.04131	Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding	Hongyu Qu et al.	arXiv	20
2026-09-04	2608.27831	RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests	Gyuhyeong Kim et al.	arXiv	19
2026-09-04	2609.02367	The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation	Yichen Liu et al.	arXiv	17
2026-09-04	2609.03952	WorldReward: Reward Modeling for Camera-Conditioned World Models	Yibin Wang et al.	arXiv	16
2026-09-04	2609.04083	CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation	Tingyu Song et al.	arXiv	13
2026-09-04	2609.03199	RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning	Howard Qian et al.	arXiv	11
2026-09-04	2609.03293	PACE: Towards Surfacing Hidden Conflicts in User Requests	Yoojin Kim et al.	arXiv	11
2026-09-04	2609.04128	Environment Evolution for Terminal Agents	Zhiyuan Fan et al.	arXiv	10
2026-09-04	2609.03153	VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement	Wenzhuo Xu et al.	arXiv	8
2026-09-04	2608.30391	Using Grounded Theory for Agent Behavior Analysis at Scale	Zhuoran Lu et al.	arXiv	7
2026-09-04	2609.03563	FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow	Byeongjun Park et al.	arXiv	7
2026-09-04	2609.04200	Principia: Relational Physics Tests for Video Models	Varun Varma Thozhiyoor et al.	arXiv	6
2026-09-04	2608.29188	Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space	Qiancheng Zhou et al.	arXiv	5
2026-09-04	2609.02887	A Common Measure of Communication for Speech Brain-Computer Interfaces	Dulhan Jayalath et al.	arXiv	4
2026-09-04	2609.01072	Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration	Daehwan Kim et al.	arXiv	4
2026-09-04	2609.03820	Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs	Prakhar Khatri	arXiv	2
2026-09-04	2609.02373	Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance	Sai Niranjan Ramachandran et al.	arXiv	2
2026-09-04	2608.29253	QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation	Yaroslav Prytula et al.	arXiv	1
2026-09-03	2609.02749	Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills	Jianlyu Chen et al.	arXiv	137
2026-09-03	2609.02886	SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models	Junchao Huang et al.	arXiv	115
2026-09-03	2609.01437	HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?	Yuhao Wu et al.	arXiv	88
2026-09-03	2609.02737	Language Models Can Control Their Own Attention	Namgyu Ho et al.	arXiv	77
2026-09-03	2609.02783	EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction	Yuling Shi et al.	arXiv	54
2026-09-03	2608.31111	Aspire: Can Models Self-Evolve from Vague Goals?	Yuhao Wu et al.	arXiv	49
2026-09-03	2609.00638	It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning	Runpeng Dai et al.	arXiv	43
2026-09-03	2609.00196	WHALE: A Simple Recipe for Joint Harness-Weight Optimization	Haechan Kim et al.	arXiv	40
2026-09-03	2609.01657	NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference	Aurélien Lac et al.	arXiv	38
2026-09-03	2608.31100	S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?	Jiajun Shi et al.	arXiv	37
2026-09-03	2609.01147	On the Design Fundamentals of Pixel Text Representation Learning	Chaohao Yuan et al.	arXiv	30
2026-09-03	2609.01740	ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes	Mingda Lin et al.	arXiv	29
2026-09-03	2609.00591	A Glance Is All You Need: Single-Pass Fine-Grained Image Captioning with SimLoss	Suryaansh Jain et al.	arXiv	17
2026-09-03	2609.02812	VibeVoice-ASR-Streaming Technical Report	Yujie Tu et al.	arXiv	16
2026-09-03	2609.02817	Cliff: Learning Process Rewards from the First Mistake	Peixuan Han et al.	arXiv	16
2026-09-03	2608.29846	Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation	Run Yang et al.	arXiv	13
2026-09-03	2609.02849	Post-Training Language Models for Gold-Medal Performance in Coding Competitions	Aleksander Ficek et al.	arXiv	12
2026-09-03	2608.21450	Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering	Hangrui Xu et al.	arXiv	10
2026-09-03	2608.30949	MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval	Seokwon Song et al.	arXiv	10
2026-09-03	2608.18972	Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers	Matteo Cargnelutti et al.	arXiv	9
2026-09-03	2609.02272	PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation	Yunhao Liu et al.	arXiv	7
2026-09-03	2609.00474	Exploring Collaboration between a language and a non-language agent	Harini S I et al.	arXiv	6
2026-09-03	2608.29607	SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions	Zirong Chen et al.	arXiv	6
2026-09-03	2609.01865	ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval	Aaryan Kapoor et al.	arXiv	6
2026-09-03	2608.30322	Ignorance or Incompetence? Constructing Knowledge-Gated, Verifiable Tasks for LLM Agents	Hanlin Tian et al.	arXiv	5
2026-09-03	2609.01925	CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing	Huu Huy Nguyen et al.	arXiv	5
2026-09-03	2609.00834	Replacing Training with Memory: Listwise Selection for Text-to-SQL	Yeonseok Jeong et al.	arXiv	4
2026-09-03	2608.30751	Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models	Ashwin Nedungadi et al.	arXiv	4
2026-09-03	2609.01936	Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens	Matteo He et al.	arXiv	3
2026-09-03	2608.30005	Small Language Models as Judges for Rubric-Based Reinforcement Learning	Fengyu Xie et al.	arXiv	3
2026-09-03	2609.02496	Debias-SparseGPT: Bias-Aware Pruning for Large Language Models	Irina Proskurina et al.	arXiv	3
2026-09-03	2609.00377	FoldingAgent: Inferring Parametric Origami Procedures from Demonstration Videos	Maya Moriya et al.	arXiv	3
2026-09-03	2609.01823	Kirin: Animal Motion Generation from In-the-Wild Video	Brian Nlong Zhao et al.	arXiv	3
2026-09-03	2608.29692	Portfolio Risk Bounds without Cross-Asset Return Covariances: Distributional Fields from Language-Model Representations	Marcus Gawronsky et al.	arXiv	2
2026-09-03	2608.29669	Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations	Marcus Gawronsky et al.	arXiv	2
2026-09-03	2504.15476	An Empirical Study on Zero-Data Bootstrapping for Conversational Recommender Systems	Rohan Surana et al.	arXiv	1
2026-09-02	2609.01591	StudentSim: Training LLM-based Student Simulators	Ke Yang et al.	arXiv	274
2026-09-02	2609.00111	Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving	Xin Zhou et al.	arXiv	131
2026-09-02	2609.00028	UI-Venus-2 Technical Report	Venus Team et al.	arXiv	65
2026-09-02	2609.01343	SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers	Shaowen Wang et al.	arXiv	54
2026-09-02	2609.01560	H3-World: Turning Language Understanding into World Control	Danze Chen et al.	arXiv	53
2026-09-02	2609.00188	ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training	Xionghao Wu et al.	arXiv	51
2026-09-02	2609.01572	From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix	Olga Tsymboi et al.	arXiv	36
2026-09-02	2608.30468	Hi-Q: Hierarchical Evidence-guided Query Refinement for Multi-Hop Question Answering	Jueun Kim et al.	arXiv	33
2026-09-02	2609.01404	Evaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching	Jaewoo Park et al.	arXiv	32
2026-09-02	2609.00768	DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory	Xincheng Wei et al.	arXiv	23
2026-09-02	2609.01607	Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System	Penghao Wu et al.	arXiv	23
2026-09-02	2609.00092	Safin-1: Safety from Within through Memory-Native State Evolution	Ming Zhang et al.	arXiv	20
2026-09-02	2609.01481	Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement	Haoyang Yan et al.	arXiv	20
2026-09-02	2608.30730	E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation	Wei Fan et al.	arXiv	17
2026-09-02	2609.00646	DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation	Haoyuan Shi et al.	arXiv	15
2026-09-02	2608.30478	Agents in the Large: Perception-Centered Architecture for Persistent Agents	Shihan Dou et al.	arXiv	12
2026-09-02	2609.00551	EM^2Mem: Event-Centric Multimodal Memory for Large Language Models	Yijun Chen et al.	arXiv	11
2026-09-02	2609.01532	Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall	Jacqueline He et al.	arXiv	8
2026-09-02	2608.26623	AgentJudgeBench: A Multi-Difficulty Benchmark for Evaluating LLM Judges on Agentic Tool-Calling	Abhigya Verma et al.	arXiv	6
2026-09-02	2609.00137	Recursive Criticality of AI Self-Improvement	Mikhail Burtsev	arXiv	6
2026-09-02	2609.00621	Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs	Wentao Zhang et al.	arXiv	6
2026-09-02	2608.28612	InternReviewer & InternAdvocate: Objective Reward and Evaluation for Agentic Reinforcement Learning in Peer Review and Rebuttal	Xuerui Su et al.	arXiv	6
2026-09-02	2609.00374	Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You	Salim Khazem et al.	arXiv	5
2026-09-02	2609.01836	Agent Memory Is a Surface for Endogenous Authorization Laundering	Tommaso Cerruti et al.	arXiv	4
2026-09-02	2608.31082	Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data	Milad Rezaei Hajidehi et al.	arXiv	4
2026-09-02	2608.30457	Learning Where Outcomes Change:Credit-Addressable Reasoning for Multimodal Geometry	Jiani Guo et al.	arXiv	4
2026-09-02	2608.27509	The Mechanics of Democratic Dominance: A System Dynamics Paradigm for Dynamic Consent Engineering	Muhammad Sukri Bin Ramli	arXiv	3
2026-09-02	2609.00968	ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation	Jeonghyeok Do et al.	arXiv	2
2026-09-02	2609.01453	Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds	Clinton Enwerem et al.	arXiv	1
2026-09-01	2608.31046	Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement	Yi Ding et al.	arXiv	86
2026-09-01	2608.29335	GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling	Guangting Zheng et al.	arXiv	72
2026-09-01	2608.30821	Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling	Minghan Qin et al.	arXiv	64
2026-09-01	2608.30320	On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability	Zihan Qiu et al.	arXiv	61
2026-09-01	2608.31036	Normalized Low-Rank Adaptation	Jiale Kang et al.	arXiv	57
2026-09-01	2608.31106	DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution	Jiashu Zhu et al.	arXiv	34
2026-09-01	2608.30968	CogEvol: Towards Efficient and Reliable Learning Environment Generation	Shangqing Tu et al.	arXiv	33
2026-09-01	2608.30935	LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation	Shaoan Wang et al.	arXiv	32
2026-09-01	2608.31075	Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence	Zhiqin Yang et al.	arXiv	31
2026-09-01	2608.31119	PaperGym: Rubric-Centered Evolution for Research-Plan Generation	Yuhan Wang et al.	arXiv	31
2026-09-01	2608.28833	Evaluating the Hidden Costs of Personalization in Large Language Models	Yumeng Wang et al.	arXiv	30
2026-09-01	2608.29310	Super Library Agent: Joint Generation and Maintenance of Multiple Applications Beyond the Single Codebase	Daegyu Sung et al.	arXiv	28
2026-09-01	2608.28600	SHAPE of Chain-of-Thought in Math Reasoning	Jonghyun Song et al.	arXiv	27
2026-09-01	2608.31076	Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research Agents	Xuehai Wang et al.	arXiv	21
2026-09-01	2608.29910	Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory	Runjia Qian et al.	arXiv	19
2026-09-01	2608.29464	Chain-of-Thought Faithfulness of Reasoning Models Varies with Where and How Preference Cues Are Delivered	Aryo Pradipta Gema et al.	arXiv	13
2026-09-01	2608.24293	Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation	Yeonkyeong Lee et al.	arXiv	13
2026-09-01	2608.30428	Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social Interactions	Jaewoo Ahn et al.	arXiv	12
2026-09-01	2608.30241	PaperBanana-Interact: Scientific Diagram Refinement with Multi-Turn Human Feedback	Xueqing Wu et al.	arXiv	12
2026-09-01	2608.30396	Scaffolding Foundation Models into Physical-World Agents Pushes the Frontier of Long-Horizon Navigation	Zixing Lei et al.	arXiv	11
2026-09-01	2608.30135	Verification-Aware Training for Speculative Decoding	Geonmo Gu et al.	arXiv	10
2026-09-01	2608.30530	WebWorld: The Browser as a World Model for Self-Improving Web Code	Jiajun Wu et al.	arXiv	9
2026-09-01	2608.31022	MNIST-PRO: MNIST is Back as a Partially Observable World for AI Agents	Vernon Toh et al.	arXiv	9
2026-09-01	2608.29098	SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models	Zongrui Wang et al.	arXiv	8
2026-09-01	2608.29387	EvoGenUI-Bench: Evaluating LLMs as Multi-Turn Generative UI Assistants	Yue Peng et al.	arXiv	7
2026-09-01	2608.30147	CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents	Amir Saeidi et al.	arXiv	7
2026-09-01	2608.28695	Weaving Visual Narratives: Agentic Image Bundle Composition Beyond Atomic Visual Matching	Rong Shan et al.	arXiv	6
2026-09-01	2609.00519	The Safeguard Worked. Is the LLM System Safer?	Pingyu Wu et al.	arXiv	5
2026-09-01	2608.28958	CoVA-SFT: A Large-Scale Dataset for Chain of Visual Abstractions	Tsung-Han Wu et al.	arXiv	5
2026-09-01	2608.29847	ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models	Shaghayegh Kolli et al.	arXiv	5
2026-09-01	2608.29252	Dynamic Important Example Mining for Reinforcement Finetuning	Haoru Tan et al.	arXiv	5
2026-09-01	2608.26671	RECAP-Forcing: Retaining Content Appearances for Long Video Generation	Haiyang Xu et al.	arXiv	4
2026-09-01	2608.29137	Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models	Shuangkang Fang et al.	arXiv	4
2026-09-01	2608.29613	Cross-lingual Functional Vectors for Emotion Detection in Large Language Models	Jieying Xue et al.	arXiv	4
2026-09-01	2608.29681	MMMMM: A Unified Taxonomy for Investigating the Mechanisms of Multilingual MultiModal Misinformation	Nadav Borenstein et al.	arXiv	3
2026-09-01	2608.29974	SpanCalib-VLM: Calibrated Hallucination Span Detection in Vision-Language Models	Amanuel Gizachew Abebe et al.	arXiv	3
2026-09-01	2608.30795	Uncertainty-Aware End-to-End AI Weather Forecasting: Disentangling Observation and Model Contributions	Rodrigo Almeida et al.	arXiv	3
2026-09-01	2608.30209	DICS: Exploring Data Intrinsic Consistency for Visual Instruction Selection	Yuyang Hong et al.	arXiv	3
2026-09-01	2608.31113	BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives	Pradyumn Goyal et al.	arXiv	3