All papers
Every paper that carries a page of its own here. The Papers page leads with what is trending and lets you filter the recent catalog; this is the plain index of the rest.
Harness-Aware Distillation for Small Language Model Agents2026Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric Rewards2026Foresight: planning future perception in streaming VLMs without retraining2026EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras20264DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes2026Retrieval-Centric Deep Learning in Growing Nonparametric Neural Networks2026CUAWright: A Minimal Unified Interface for Digital Agents2026ALoDLM: Adaptively Looped Diffusion Language Models2026CurveCodec 2: Skeleton-agnostic animation compression with a learned entropy model2026LMBuild: Evaluating LLM Agents for Generating Buildable and Functional Structures2026Agentic discovery of blood biomarker from distilled private health records2026TIDES: Implicit Time-Awareness in Selective State Space Models2026Decentralized Multi-Agent Systems with Shared Context2026SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation2026The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models2026StepCAD: Mesh-to-CAD Code Generation via LLM Policy and Geometry-Guided Search2026Learning Latent Protein Languages for Autoregressive Generation2026PaLoRA: Paced Low-Rank Adaptation for Continual Learning2026UnAct: Gradient-Free Unlearning via Targeted Activation Intervention2026Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents2026Recurrent Looped Transformer2026Stateless Language Agents: Scaling Long-Horizon Automated Research2026DLoop: Looped Speculative Decoding2026From Evidence to Action: How Tool-Using Agents Fail2026VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs2026DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks2026Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight2026Towards In-Parameter Memory Augmentation for Large Language Models2026AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model2026Sherpa: Teaching LLMs to Teach Adaptively2026EVISKILL: Grounding Skill Evolution in Replayable Evidence2026Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy2026CoDance: Learning Reactive and Compliant Human-Humanoid Interaction from Video2026Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation2026UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents2026Beyond Semantic Similarity: Performance and Costs of Agentic Retrieval for Complex Tasks2026JLD: Perceptual Distance Through A Jacobian Lens2026GraphDecisionBench: Benchmarking System One Models on Graph Tasks2026You Changed Your Mind, The Model Didn't: Demystifying Intent in Multi-Turn Dialogue2026Closing the Context Gap: Activation Alignment for Tabular In-Context Learning2026MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers2026Sharpen Without Search: On-Policy Distillation of Sequence-Level Power Distribution2026TRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement Learning2026Is this machine playing?2026Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation2026Learning Discriminative Geometry for Drifting Models2026ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience2026Technical Report on the Turba Fertilizer Machine Learning Stack in Morocco2026MEND: RL For Flow Models via Proximal Velocity Matching2026Empirical Variational Autoencoder2026RealtimeWAM: One-Step Asynchronous World Action Models2026H-JEPA: End-to-End Learning of Hierarchical World Models for Visual Planning2026Towards Looped Models Done Right, Part II: Rethinking at Fixed Points2026On KL-Regularized Policy Optimization2026U-Space: Uncovering When and Why Uncertainty Arises in Language Models2026ARCS: Towards Precise Text-to-SQL via Structured Disambiguation2026Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning2026Coding-Agent Benchmarks Should Match Their Users' Task Flows2026From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery2026Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression2026LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets2026Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position2026EdgeRock: Strong Reasoning at Constant Memory2026EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory2026DSReg: Provably Recovering Individual World Latents without Reconstruction2026NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime2026Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute2026Clinician use of language models diverges from how the models are evaluated2026The Lattice of Transition Laws2026REMORY: Learning Residual Memory for Context Compaction2026Incremental Open-Ended Deep Research with Structured Harness2026Thinking Inertia: LLMs Keep Thinking When Told Not To2026MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement2026DataVista: Diagnosing Multimodal LLMs on Data Video Understanding2026TokenRouter: Efficient Serving System for Token-Level LLM Routing2026Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition2026Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict2026SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models2026ViSkill: Reinforcing VLM Agents with Evolving Visual-Native Skills2026WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification2026CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?2026Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents2026Sensor-Language-Action Models2026NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale2026Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness2026nanoMuse: An Open-Source Personal Agent for Every Device You Own2026WorldSonus: Bringing Sound to Worlds2026Systematic Multi-Agent Vision-and-Language Navigation: Formulation, Benchmark, and Method2026Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station2026CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use2026Consistent Distribution Matching for Data-Free Diffusion Distillation2026Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning2026UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles2026UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving Policy2026MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent2026RoboQuest: Generalist Physical Agents that Search, Inspect and Test2026Q-Learning with Scalar Adjoint Matching2026RoboJEPA: Scaling Robotic Latent World Models2026Long-WAM: Scaling the Context of World-Action Models2026Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?2026Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data2026Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals2026MIMESIS: Learning User Simulators as Training Environments for Interactive Agents2026A Closer Look at Agentic BBO: Benchmarking LLM Agents for Black-Box Optimization2026VibeEdit: Image Editing with Canvas Instructions2026From Prompting to Composing: A Spatial Canvas Interface for Poster Generation2026Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction2026Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language Models2026SpaceFlow: Locally Controllable 3D Generation2026BrickBench: Evaluating Agentic Brick Design2026RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments2026SplitJEPA: Learning Invariant and Variant Latent Worlds without Reconstruction2026SWE-Duel: Towards a Self-Scaling Arena for Coding Agents2026Contextual Correction of Parallel Drafts for Speculative Decoding2026Self-Preservation in Language Models2026EmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents2026PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling2026S-Space: Exploring Spatial Workspace in Multimodal Language Models2026APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces2026AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis2026Multi-Stream Attention Residuals2026RSI-Anything: Unlocking Recursive Self-Improvement with World Models2026Constrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality Constraints2026LeWAM: End-to-End World and Action Modeling with JEPAs2026Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training2026Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction2026AgentSWE: Can Coding Agents Build the Agent You Actually Want?2026SpatialASM: Internalizing Active Mentalization for Spatial Reasoning2026Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching2026DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models2026APEX: Asynchronous Prefix Denoising for Extreme Compression2026Rethinking Relative Policy Differences Transfer of On-Policy Distillation2026OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools2026Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation2026AutoEnvScaling: Automating the Data Flywheel with Terminal Agents2026Harness^2: Recursive Agent Harnessing for an Open World2026The Thinking Leakage in Reinforcement Learning for LLMs2026Vela: User Behavior as Supervision Sparks LLM Intelligence2026RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution2026Agent Sociodrama: Social-Dynamics-Guided Persona Recasting for LLM Agent Teams2026Dream2Discern: Learning from Hard Latent Variants for Runtime Failure Prediction in Multi-Agent Systems2026Self-Distillation with Verbal Regularization2026EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents2026TPPO: Tracking-Value PPO For Language Model Reasoning2026Calibrated Typed Decisions for Entity, Relation, and Event Extraction2026StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions2026Agent-Reflex: Teaching Language Agents to Act Reflectively2026Virtual Head Attention2026Fish Audio Drama 3 Technical Report2026JevGPT: Thinking Fast and Slow in Autonomous Research2026Rethinking Projector Training in Multimodal LLMs2026Self-Evolving Agent Harness2026OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding2026Hybrid Reasoning Agents2026DoubtLess: Training-Free Contrastive Decoding for Efficient Reasoning2026ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty2026RoboHarness: A Simple Harness Outperforms VLA and World Action Models2026Last Secure Code Benchmark: Is the Code You Vibe Secure?2026ProgAgent: Learning Tool Orchestration through Programmatic Training2026Training a Compact, Strong, and Realistic Text-to-Speech Model2026EvoWeb: A Benchmark for Coding Agents on Evolving Web Applications2026InfoVis: Unified Slide Image Generation and Editing2026AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding2026FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation2026FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching20264LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling2026BigCell: Generating Gigapixel Whole-Slide Images2026Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding2026GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning2026DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision2026Into the Unknown: Benchmarking AI agents on open scientific research problems2026Copy-Paste Language Models2026VLX-Go: Robust Embodied Tracking through Multi-Stage Learning and On-Policy Refinement2026Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory2026$τ$-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions2026RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing2026More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning2026The COUNT: Counting N-grams Unlocks Scaling on Host Memory and Training-Free Adaptation2026Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR2026ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models2026PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis2026LEV: Thinking Fast and Deep with Looped Decision Models2026PremiseCheck: Efficient Fact-Checking of Human and AI Peer Reviews2026Behavioral Compositionality of Sparse Autoencoder Representations2026Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents2026Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation2026Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language Modeling2026Lexical Reference Frames: Interpreting LM Residual Streams in Native Semantics2026Mosaic: Multi-Session Agentic Reinforcement Learning2026AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-Tuning2026Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory Writing2026Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries2026Learning Self-Orchestration in Decentralized Agent Swarms2026MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering2026FDE-Gym: The Last Mile of AI Delivery2026OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World Modeling2026APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation2026Choosing LLMs for Strategic Agent Interactions2026Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes2026