Hugging Face — günün makaleleri
Yazan: Fatih · Son güncelleme: 2026-10-24
Son kontrol: 2026-10-24 · İzleme başlangıcı: 2026-10-01 · 404 kayıt
Ne izleniyor
api/daily_papers ucundan günün öne çıkan araştırma makalelerinin kimliği, başlığı ve tarihi alınır (ilk 10).
Ne izlenmiyor
Makale metni ya da özeti alınmaz. Listede olmak hakemli doğruluk anlamına gelmez; yalnız görünürlüğü gösterir.
Bağlantılar
API cevabında adres alanı yok — kayıt başına bağlantı verilmez; makaleye kök adresteki arama üzerinden ulaşılır. Kaynak: https://huggingface.co/papers
Bu sayfadaki veri nereden geliyor
Zincir dört halkadır ve her halkanın adresi burada açıkça yazılıdır: kaynağın kendi sayfası, motorumuzun fiilen çağırdığı uç nokta, o uç noktanın resmî belgesi ve kaynağın kullanım koşulu. Uç nokta adresi, motorun kodundaki adresle her denetimde karşılaştırılır; ikisi ayrışırsa kapı kırmızı yanar ve yayın durur.
- Kaynak sayfası: https://huggingface.co/papers
- Çağrılan uç nokta:
https://huggingface.co/api/daily_papers?limit=10 - Uç noktanın belgesi: Hugging Face Hub API belgesi
- Kullanım koşulu: Hugging Face kullanım koşulları
Gözlemler
Her satırdaki ilk gözlem damgası, kaydı bizim ilk gördüğümüz andır; kaynağın yayın tarihiyle aynı olmak zorunda değildir. Terimin tanımı Sözlük sayfasındadır.
- — Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models (ilk gözlem 2026-10-24)
- — BrickWright: Agentic Creation of Physically Feasible Brick Builds (ilk gözlem 2026-10-24)
- — F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation (ilk gözlem 2026-10-23)
- — AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark (ilk gözlem 2026-10-23)
- — TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments (ilk gözlem 2026-10-24)
- — Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems (ilk gözlem 2026-10-24)
- — Self-Distilling Future Video Representations for World Action Models (ilk gözlem 2026-10-23)
- — Toward Recursive Self-Improvement in Physical AI (ilk gözlem 2026-10-23)
- — PACE: Periodic and Channel-Aligned Encoding of Four-Bit Recurrent States (ilk gözlem 2026-10-22)
- — RealMe: Immersive Volumetric Video from Minimal Captures (ilk gözlem 2026-10-22)
- — Think Harder Where It Matters: Item-Level Adaptive Recursion for Sequential Recommendation (ilk gözlem 2026-10-22)
- — Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use (ilk gözlem 2026-10-22)
- — DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations (ilk gözlem 2026-10-22)
- — Diffusion Language Models Change Speed Across Tasks and Languages (ilk gözlem 2026-10-24)
- — HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second (ilk gözlem 2026-10-24)
- — RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian Splatting (ilk gözlem 2026-10-23)
- — Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild? (ilk gözlem 2026-10-22)
- — Answering in the User's Variety: Calibrated Accommodation Pairs for Post-Training (ilk gözlem 2026-10-22)
- — Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual Worlds (ilk gözlem 2026-10-22)
- — Specter: Fast MoE Inference via Quantization-Enabled Multi-Step Speculative Offloading (ilk gözlem 2026-10-21)
- — Multimodal Reranking Is a System One Decision (ilk gözlem 2026-10-21)
- — Harness Self-Evolution for Long-Horizon Terminal Agents (ilk gözlem 2026-10-21)
- — DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems (ilk gözlem 2026-10-21)
- — RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing (ilk gözlem 2026-10-23)
- — Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents (ilk gözlem 2026-10-23)
- — HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RL (ilk gözlem 2026-10-21)
- — More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM Agents (ilk gözlem 2026-10-21)
- — SpecMRL: Redesign Matryoshka Representation Learning within Parametric Spectrum (ilk gözlem 2026-10-20)
- — Text-to-Image Generative Modeling Without Language Pretraining (ilk gözlem 2026-10-20)
- — HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation (ilk gözlem 2026-10-20)
- — Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic Manipulation (ilk gözlem 2026-10-20)
- — TILDE: Teacher-in-the-Loop Distillation from Embodied Foundation Models (ilk gözlem 2026-10-23)
- — Painting Change Map as guidance for generating painting processes (ilk gözlem 2026-10-21)
- — CoEvo-RSI: When Harnesses Evolve, Which Models Should Follow? (ilk gözlem 2026-10-21)
- — Bridging Exploration and Persona: Information-Directed Dueling for Test-Time Agent Personalization (ilk gözlem 2026-10-24)
- — IF-MAP: Influence-Function-Inspired Agent Prioritization in Multi-Agent Systems (ilk gözlem 2026-10-24)
- — Editing Images into Reusable Layers via Compositional Edit-Prior Distillation (ilk gözlem 2026-10-23)
- — Good Judgment, Bad Advice: Decision-Model Controllers Raise Agent Cost Without Improving Success (ilk gözlem 2026-10-21)
- — HSPR: Recovering Software-Agent Benchmark Scores via Hierarchical Posterior Inference (ilk gözlem 2026-10-20)
- — EvalResearchBench: Can AI Agents Build Their Own Feedback for Recursive Self-Improvement? (ilk gözlem 2026-10-24)
- — The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems (ilk gözlem 2026-10-24)
- — Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally (ilk gözlem 2026-10-22)
- — Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization (ilk gözlem 2026-10-21)
- — LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints (ilk gözlem 2026-10-20)
- — Mine, Sample, Render: Test-Time Diversity Alignment Of Generative Models (ilk gözlem 2026-10-17)
- — Behavioral Compositionality of Sparse Autoencoder Representations (ilk gözlem 2026-10-17)
- — LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents (ilk gözlem 2026-10-17)
- — PathFM: Fast Generative Forecasting of Multivariate Trajectories (ilk gözlem 2026-10-17)
- — CoDA: Co-Evolution of Data Engines and Action Policies (ilk gözlem 2026-10-16)
- — MJev-Spatial: System One Spatial Intelligence via Native Attention Matching (ilk gözlem 2026-10-16)
- — VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models (ilk gözlem 2026-10-16)
- — Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation (ilk gözlem 2026-10-16)
- — MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search Agents (ilk gözlem 2026-10-16)
- — MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning Engineering (ilk gözlem 2026-10-16)
- — τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions (ilk gözlem 2026-10-15)
- — MolLean: A Process-Verifiable Language for Chemical Reasoning (ilk gözlem 2026-10-23)
- — PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis (ilk gözlem 2026-10-22)
- — BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References (ilk gözlem 2026-10-20)
- — Diminishing Returns of Data in Sparse Autoencoders: Functional Behavior does not Guarantee Feature Reproducibility (ilk gözlem 2026-10-17)
- — Equal CER, Unequal Damage: Severity-Weighted Character Error Rate for OCR (ilk gözlem 2026-10-17)
- — Learning to Read Out: Unembedding Dynamics in Language Model Pretraining (ilk gözlem 2026-10-17)
- — Latent Compaction with Test-Time Training (ilk gözlem 2026-10-15)
- — Cortex: Consolidating Context into Parametric Memory (ilk gözlem 2026-10-15)
- — VITAL: From Visual Motion to Precise Action (ilk gözlem 2026-10-15)
- — SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving (ilk gözlem 2026-10-15)
- — Evidence-First Agentic Verification (ilk gözlem 2026-10-20)
- — LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification (ilk gözlem 2026-10-17)
- — Copy-Paste Language Models (ilk gözlem 2026-10-17)
- — Cowork-Gym: Synthesizing Interactive Work Environments at Scale (ilk gözlem 2026-10-16)
- — H-DDCM: Hadamard Codebooks for Fast Generative Image and Video Compression (ilk gözlem 2026-10-16)
- — SHELDON: Reasoning through Dual Search over Hypothesis and Observation Spaces (ilk gözlem 2026-10-14)
- — 4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling (ilk gözlem 2026-10-14)
- — SWE-MISBEHAVIOR: Benchmarking and Mitigating Boundary Violations in Software Coding Agents (ilk gözlem 2026-10-14)
- — WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D World (ilk gözlem 2026-10-14)
- — Agent-Reflex: Teaching Language Agents to Act Reflectively (ilk gözlem 2026-10-14)
- — PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation (ilk gözlem 2026-10-16)
- — Self-Distillation with Verbal Regularization (ilk gözlem 2026-10-14)
- — Scalable Weak-to-Strong Verifier Hardening for Agent Environments (ilk gözlem 2026-10-17)
- — SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification (ilk gözlem 2026-10-15)
- — Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping (ilk gözlem 2026-10-14)
- — EviScene: Beyond "Is It AI?" for Agentic Image Factuality Assessment (ilk gözlem 2026-10-14)
- — LightVAE: Towards Compact and Efficient Video Autoencoders (ilk gözlem 2026-10-14)
- — BigCell: Generating Gigapixel Whole-Slide Images (ilk gözlem 2026-10-15)
- — Latent World Action Model for GUI Agents (ilk gözlem 2026-10-14)
- — Learning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-Training (ilk gözlem 2026-10-13)
- — AgentSWE: Can Coding Agents Build the Agent You Actually Want? (ilk gözlem 2026-10-13)
- — Scaling Agentic Data for Long-Horizon Terminal Intelligence (ilk gözlem 2026-10-13)
- — PreSTO: Predictive Subtree Prefetching for Fast LLM Power Sampling (ilk gözlem 2026-10-12)
- — Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction (ilk gözlem 2026-10-12)
- — Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding (ilk gözlem 2026-10-12)
- — The value of information and the emergence of communication in evolved e-puck robots (ilk gözlem 2026-10-12)
- — Continually Post-training Small Models via Synthetic Self-distillation (ilk gözlem 2026-10-12)
- — AI-Driven, Timing-Aware Power Optimization (ilk gözlem 2026-10-16)
- — Super-Resolution in The Right Latent Space: A Frozen Vision-Foundation Substrate (ilk gözlem 2026-10-15)
- — SWEeper-Bench: Can Agents Discover Bugs in Interactive Software? (ilk gözlem 2026-10-15)
- — Thinking Inertia: LLMs Keep Thinking When Told Not To (ilk gözlem 2026-10-13)
- — Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition (ilk gözlem 2026-10-12)
- — SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments (ilk gözlem 2026-10-12)
- — Reflex: Visually Grounded Reactive Humanoid Control (ilk gözlem 2026-10-12)
- — DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models (ilk gözlem 2026-10-12)
- — The Lattice of Transition Laws (ilk gözlem 2026-10-10)
- — Opera: A Verbal Critic Framework for Long-horizon Coding Agents (ilk gözlem 2026-10-10)
- — Skill Constellations: Tracing the Supply Chain of Agent Skills on GitHub (ilk gözlem 2026-10-10)
- — Predicting Cable Dynamics with Physical Attention Bias (ilk gözlem 2026-10-10)
- — MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination (ilk gözlem 2026-10-09)
- — MiMo-V2.6: Scaling Reinforcement Learning Towards Self-Improvement (ilk gözlem 2026-10-09)
- — Foundations of Large Language Models (ilk gözlem 2026-10-09)
- — OuroWorld: Bringing Any 3D World Alive as Diverse, Endlessly Looping 3D Cinemagraphs (ilk gözlem 2026-10-09)
- — BrickBench: Evaluating Agentic Brick Design (ilk gözlem 2026-10-09)
- — OmniCapBench: A Deep-Structured Evaluation Framework for Fine-Grained Audio-Visual Captioning (ilk gözlem 2026-10-09)
- — Accurate but Not Humble: Evaluating Epistemic Humility in LLM Agents under Knowledge Conflict (ilk gözlem 2026-10-09)
- — Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models (ilk gözlem 2026-10-20)
- — NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime (ilk gözlem 2026-10-15)
- — ARCS: Towards Precise Text-to-SQL via Structured Disambiguation (ilk gözlem 2026-10-13)
- — Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation (ilk gözlem 2026-10-10)
- — On-Policy Distillation Teaches New Skills but Not New Knowledge (ilk gözlem 2026-10-09)
- — From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery (ilk gözlem 2026-10-08)
- — QuadTok: Quadtree Visual Tokenizer for Autoregressive Image Generation (ilk gözlem 2026-10-08)
- — SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles (ilk gözlem 2026-10-08)
- — Tetris3D: 3D Scene Generation With Objects That Fit Together (ilk gözlem 2026-10-08)
- — SWE-Game: Can Coding Agents Build the Games We Want? (ilk gözlem 2026-10-08)
- — SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code (ilk gözlem 2026-10-13)
- — A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learning (ilk gözlem 2026-10-10)
- — Incidental information contaminates patient notes and disrupts clinical reasoning in large language models (ilk gözlem 2026-10-10)
- — Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI (ilk gözlem 2026-10-10)
- — SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation (ilk gözlem 2026-10-09)
- — PhysEvo: Astra Can Act, Let It (ilk gözlem 2026-10-08)
- — Co-Evolving Robot Orchestrators and Policies through Deployment (ilk gözlem 2026-10-08)
- — DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks (ilk gözlem 2026-10-07)
- — CtrlCache: Accelerating Interactive Video World Models with Control-Aware Caching (ilk gözlem 2026-10-07)
- — MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents (ilk gözlem 2026-10-20)
- — Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation (ilk gözlem 2026-10-08)
- — Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks (ilk gözlem 2026-10-07)
- — Execution-Aligned Progressive Noise for Consistent Asynchronous Replanning in Generative Robot Policies (ilk gözlem 2026-10-07)
- — WildMatch: Weakly Supervised Image Matcher Adaptation for Wildlife Re-Identification (ilk gözlem 2026-10-07)
- — Arm-wise Compositional Generalization in Dual-Arm Vision-Language-Action Models (ilk gözlem 2026-10-06)
- — OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal Hallucination (ilk gözlem 2026-10-06)
- — Noise Out, Bias In: Targeted Bias Injection in Diffusion Language Models via Closed-Loop Activation Steering (ilk gözlem 2026-10-06)
- — Certification of Real Images through Calibrated Content Authentication (ilk gözlem 2026-10-06)
- — Code2Games: Enabling Coding Agents for Gaming World Generation (ilk gözlem 2026-10-06)
- — Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy (ilk gözlem 2026-10-06)
- — DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation (ilk gözlem 2026-10-07)
- — Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation (ilk gözlem 2026-10-07)
- — Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence (ilk gözlem 2026-10-07)
- — T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images (ilk gözlem 2026-10-13)
- — Gains and Collapse in On-Policy Distillation:A Reinforcement Learning Perspective (ilk gözlem 2026-10-08)
- — Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery (ilk gözlem 2026-10-06)
- — Dynamic Harness Search: Building Multi-Agent Systems Per-Query via Prediction (ilk gözlem 2026-10-06)
- — Native Action-Prior Learning from Videos for World Action Models (ilk gözlem 2026-10-05)
- — Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models (ilk gözlem 2026-10-05)
- — HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents (ilk gözlem 2026-10-05)
- — When Do Biological Reasoning Models Use Their Biological Inputs? (ilk gözlem 2026-10-12)
- — Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation (ilk gözlem 2026-10-08)
- — The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models (ilk gözlem 2026-10-06)
- — From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders (ilk gözlem 2026-10-05)
- — Local Support Learning (ilk gözlem 2026-10-05)
- — SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation (ilk gözlem 2026-10-05)
- — Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation (ilk gözlem 2026-10-03)
- — Keyword Harnesses Fail Open: A Cheap Diagnostic Ladder for Tool-Use Claims in Small Language Models (ilk gözlem 2026-10-03)
- — InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation (ilk gözlem 2026-10-02)
- — SILSA: Sliding-Window Slice Latents for Topology-Preserving High-Resolution 3D Generation (ilk gözlem 2026-10-02)
- — GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed (ilk gözlem 2026-10-13)
- — GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives (ilk gözlem 2026-10-13)
- — Source Identification Is Not Fitness Testing: Measuring the Limits of Synthetic-Data Attribution (ilk gözlem 2026-10-07)
- — QuantCode Model: Specializing Language Models for Executable Algorithmic Trading Code (ilk gözlem 2026-10-06)
- — Does Learning Protein Folding Generalize to Broader Reasoning? (ilk gözlem 2026-10-05)
- — LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models (ilk gözlem 2026-10-05)
- — Video Generation Models: A Survey of Post-Training and Alignment (ilk gözlem 2026-10-03)
- — Honeycomb: Constant-Size Scene Memory Representation for Video World Models (ilk gözlem 2026-10-03)
- — Memorizon: Training World Models Beyond Their Context Window (ilk gözlem 2026-10-02)
- — Benchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation (ilk gözlem 2026-10-02)
- — Smaller Models, Better Rejects: Preference Distillation Scaling (ilk gözlem 2026-10-02)
- — Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces (ilk gözlem 2026-10-02)
- — Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL (ilk gözlem 2026-10-02)
- — SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models (ilk gözlem 2026-10-01)
- — Soft Spatial Reasoning (ilk gözlem 2026-10-01)
- — Mitigating the Length-Scaling Tax with Online Distillation (ilk gözlem 2026-10-01)
- — How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text (ilk gözlem 2026-10-01)
- — LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception (ilk gözlem 2026-10-01)
- — Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text (ilk gözlem 2026-10-01)
- — Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics (ilk gözlem 2026-10-10)
- — HelixWorld: A Real-time Interactive Audio-Visual World Model (ilk gözlem 2026-10-05)
- — MotorMind: Scaffolding General Vision Language Models for Zero-Shot Robot Manipulation (ilk gözlem 2026-10-05)
- — MemFold: Learning Compact Soft Memory for Long-Context Personalization via On-Policy Optimization (ilk gözlem 2026-10-03)
- — Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It (ilk gözlem 2026-10-03)
- — Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling (ilk gözlem 2026-10-02)
- — Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs (ilk gözlem 2026-10-02)
- — TERRA: Terrain-Aware Reconstruction, Retargeting and Control for Musculoskeletal Locomotion (ilk gözlem 2026-10-01)
- — Context Language Models (ilk gözlem 2026-09-30)
- — Chinese-Jev: Bringing System One Model to Chinese-Language Tasks (ilk gözlem 2026-09-30)
- — EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory (ilk gözlem 2026-09-30)
- — EngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments? (ilk gözlem 2026-09-30)
- — ReSPO: Reshaped Sequence Policy Optimization for Gradient Starvation in Off-Policy Learning (ilk gözlem 2026-10-09)
- — Persona Dosing: Calibrated Activation Steering for Graded Trait Control (ilk gözlem 2026-10-03)
- — Does Native 3D Texture Generation Necessarily Require 3D Assets for Training? (ilk gözlem 2026-10-02)
- — SeLMRoute: Probabilistic Semantic Evidence for Large Language Model Routing (ilk gözlem 2026-10-01)
- — Rethinking Latent Visual Reasoning: Grounding Latent Reasoning in Visual Evidence (ilk gözlem 2026-10-01)
- — NavHarness: Towards Lifelong Embodied Navigation (ilk gözlem 2026-10-01)
- — Same Bytes, Different Authority: Reserved-Token Representations in Chat-Template Prompt Injection (ilk gözlem 2026-09-30)
- — When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety (ilk gözlem 2026-09-29)
- — InfiniHand: Streaming World-Space Hand Motion Estimation from Egocentric Video (ilk gözlem 2026-09-29)
- — GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space (ilk gözlem 2026-09-29)
- — Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning (ilk gözlem 2026-09-29)
- — On-Policy Self-Distillation for Multi-Turn Image Editing (ilk gözlem 2026-09-29)
- — Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents (ilk gözlem 2026-10-13)
- — Pretraining Transformers with Quantized Softmax in Attention (ilk gözlem 2026-09-30)
- — When Privacy Moves ML-Mediated Decisions On Device: Information and Incentive Misalignment in Auctions (ilk gözlem 2026-09-29)
- — WideSWE: Can Coding Agents Coordinate Changes Across Repositories? (ilk gözlem 2026-09-29)
- — TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining (ilk gözlem 2026-09-29)
- — Replacing Large Language Models with Jev Decision Models for Low-Latency Edge Service Orchestration (ilk gözlem 2026-10-03)
- — X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization (ilk gözlem 2026-10-03)
- — OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories (ilk gözlem 2026-10-03)
- — VoxMem: Benchmarking Multimodal Memory in Large Audio Language Models (ilk gözlem 2026-09-30)
- — Residual Transferability in Neural Image Watermarking (ilk gözlem 2026-09-29)
- — Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution (ilk gözlem 2026-10-10)
- — Omni-IO Skills: Harnessing Your Agent Omni-Native (ilk gözlem 2026-09-30)
- — Hyperspherical Semantic Trajectory Analysis: Mapping Technological Diffusion across Academic Preprints, Patent Signals, and Compute Scaling (ilk gözlem 2026-09-30)
- — ZooWork-ShopRanker: An Open, Preference-Aligned E-Commerce Reranker (ilk gözlem 2026-09-28)
- — Block Sparse Attention with Log-Linear Complexity (ilk gözlem 2026-09-28)
- — AgentWorld: Benchmarking Long-Horizon Collaboration of Multi-agent LLMs (ilk gözlem 2026-09-28)
- — InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data (ilk gözlem 2026-09-28)
- — Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning (ilk gözlem 2026-10-07)
- — Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents (ilk gözlem 2026-09-30)
- — How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure (ilk gözlem 2026-09-29)
- — Jev in the Wild: A Data-Driven Analysis of the Jev Model's Functionality, Applications and Ecosystem (ilk gözlem 2026-09-28)
- — TrackEverything: Long Horizon Dense Tracking via De-Duplicating 3D Scene Representations (ilk gözlem 2026-09-28)
- — SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL (ilk gözlem 2026-09-28)
- — RGBD20K: A Large-Scale Benchmark for RGB-D Semantic Segmentation (ilk gözlem 2026-09-26)
- — AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation (ilk gözlem 2026-09-26)
- — Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs (ilk gözlem 2026-09-26)
- — Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures (ilk gözlem 2026-09-26)
- — Parts-of-Speech as Emergent Categories in SAE Latent Space (ilk gözlem 2026-09-26)
- — Coding Agents for Generalized Task and Motion Planning Problems (ilk gözlem 2026-09-26)
- — Rufus-Air: An Open LLM Post-Training Recipe (ilk gözlem 2026-09-25)
- — IterSynth: Rethinking Deep Search Agents via Role-Decoupled Iterative Synthesis (ilk gözlem 2026-09-25)
- — ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation (ilk gözlem 2026-09-25)
- — PUBG Ally: A Conversational Embodied Agent as an AI Teammate (ilk gözlem 2026-09-25)
- — World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal (ilk gözlem 2026-09-25)
- — WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation (ilk gözlem 2026-09-25)
- — ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds (ilk gözlem 2026-09-25)
- — Learning to Discover Interesting Mathematics (ilk gözlem 2026-09-26)
- — DeltaWAM: Delta World Action Models for Bimanual Manipulation (ilk gözlem 2026-09-26)
- — On the Diffusibility of High-Dimensional Latents (ilk gözlem 2026-09-24)
- — All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation (ilk gözlem 2026-09-24)
- — Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents (ilk gözlem 2026-09-24)
- — EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics (ilk gözlem 2026-09-24)
- — StudentBench: AI and human tutoring yield equivalent GRE learning gains (ilk gözlem 2026-09-24)
- — MemBodied: Recurrent Associative Memory for Vision-Language-Action Models (ilk gözlem 2026-09-24)
- — FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance (ilk gözlem 2026-09-28)
- — SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue (ilk gözlem 2026-09-24)
- — The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks (ilk gözlem 2026-09-23)
- — StableVQ: Practical Guidelines for Stable Vector-Quantized Tokenizer Training (ilk gözlem 2026-09-23)
- — HappyWorld-Bench (ilk gözlem 2026-09-24)
- — Emergent Collusion in Long-Horizon LLM Agent Interaction (ilk gözlem 2026-09-23)
- — Lean Pool: An AI-Maintained Archive of Formalized Mathematics (ilk gözlem 2026-09-23)
- — All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts (ilk gözlem 2026-09-23)
- — Geometric and Semantic Coupling for Interaction Understanding in 3D Scenes (ilk gözlem 2026-09-23)
- — Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models (ilk gözlem 2026-09-23)
- — GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation (ilk gözlem 2026-09-23)
- — 1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation (ilk gözlem 2026-09-22)
- — onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction (ilk gözlem 2026-09-22)
- — Harness-Zero: Harness Distillation via Agent-as-Harness (ilk gözlem 2026-09-22)
- — GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay (ilk gözlem 2026-09-22)
- — Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents (ilk gözlem 2026-09-22)
- — VideoGen-Agent: Reinforcing Video Generation Agents (ilk gözlem 2026-09-22)
- — Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies (ilk gözlem 2026-09-22)
- — CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation (ilk gözlem 2026-09-28)
- — Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs (ilk gözlem 2026-09-28)
- — OmniEcho: Spatial Audio Understanding for Embodied Agents (ilk gözlem 2026-09-25)
- — PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing (ilk gözlem 2026-09-24)
- — Grounded Action Model: 3D Grounding as a Foundation for Robotics (ilk gözlem 2026-09-22)
- — Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone (ilk gözlem 2026-09-25)
- — Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World (ilk gözlem 2026-09-24)
- — OmniEdu: Open Foundation Models for Learning and Teaching (ilk gözlem 2026-09-22)
- — Calibrating Teacher--Student Discrepancy for On-Policy Distillation (ilk gözlem 2026-09-21)
- — CodeMidas: Scaling Agentic Coding RL Environments from Code Itself (ilk gözlem 2026-09-21)
- — TeleAntiFraud 2.0: A Refreshable, Profile-Grounded, and Audio-Based Benchmark for Telecom Fraud Detection (ilk gözlem 2026-09-21)
- — Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation (ilk gözlem 2026-09-21)
- — Paint-Anything: Unified Any-Color Control for Image Generation and Editing (ilk gözlem 2026-09-21)
- — DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation (ilk gözlem 2026-09-21)
- — Self-Evolving Search Index (ilk gözlem 2026-09-19)
- — VākQA: A Benchmark and Evaluation Study for Telugu Spoken Factoid Question Answering (ilk gözlem 2026-09-19)
- — Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL (ilk gözlem 2026-09-19)
- — FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations (ilk gözlem 2026-09-19)
- — When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation (ilk gözlem 2026-09-19)
- — ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning (ilk gözlem 2026-09-23)
- — FRAUDSkill: Structured Frozen-Weight Skill Optimization for Audio Anti-Fraud Detection (ilk gözlem 2026-09-21)
- — Sample Count Is Not Enough: Candidate-Generation Strategy Shapes the Energy and Performance of LLM Test-Time Scaling (ilk gözlem 2026-09-19)
- — Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model (ilk gözlem 2026-09-19)
- — PACT: Can Enterprise AI Assistants Be Trusted Under Pressure? (ilk gözlem 2026-09-19)
- — Verifiable Social Reasoning for LLM Assistants (ilk gözlem 2026-09-19)
- — Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems (ilk gözlem 2026-09-16)
- — Modality-Autoregressive World-Action Models (ilk gözlem 2026-09-16)
- — PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control (ilk gözlem 2026-09-16)
- — AI for Games in the Foundation Model Era (ilk gözlem 2026-09-16)
- — Bellman Policy Optimization (ilk gözlem 2026-09-23)
- — MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup (ilk gözlem 2026-09-21)
- — EvoOntology: A Self-Evolving Ontology Layer for Data Agents (ilk gözlem 2026-09-21)
- — Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration (ilk gözlem 2026-09-16)
- — Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States (ilk gözlem 2026-09-16)
- — Disentangling Representation Evolution in Transformers through Directional Decomposition (ilk gözlem 2026-09-16)
- — RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments (ilk gözlem 2026-09-15)
- — HazardAuditor: From Executable Threats to Safer Computer-Use Agents (ilk gözlem 2026-09-15)
- — Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks (ilk gözlem 2026-09-15)
- — Enabling Creative Exploration for Vibe Design Agents (ilk gözlem 2026-09-15)
- — When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis (ilk gözlem 2026-09-15)
- — Atria Dawn: The Dawn of Agentic Superintelligence (ilk gözlem 2026-09-15)
- — Kaininja: Extending Native 3D Generators to the Part Level (ilk gözlem 2026-09-15)
- — Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models (ilk gözlem 2026-09-16)
- — Training Specialist Models without Reasoning Trajectories for Domain Expert Distillation (ilk gözlem 2026-09-16)
- — Realtime-Venus: A full-duplex interaction system with asynchronous delegation (ilk gözlem 2026-09-15)
- — Agent as Policy for Robotic Manipulation (ilk gözlem 2026-09-15)
- — ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search (ilk gözlem 2026-09-15)
- — Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models (ilk gözlem 2026-09-14)
- — SNAP3D: Physically Grounded 3D Parts for Assembly from a Single Image (ilk gözlem 2026-09-14)
- — SAS: Simple Attention Sparsification via End-to-End Optimization of Context Ranking (ilk gözlem 2026-09-14)
- — The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement (ilk gözlem 2026-09-16)
- — Benchmark Radar: A Living Database and Search Engine for AI Benchmarks and Evaluation (ilk gözlem 2026-09-14)
- — COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization (ilk gözlem 2026-09-14)
- — Beyond Solver Verdicts: Generative Reward Models for Autoformalization (ilk gözlem 2026-09-12)
- — Memory as Plans: World-Action Modeling with Memory-Grounded Planning (ilk gözlem 2026-09-12)
- — Negative Self-Distillation: Learning to Reason by Avoiding Flaws (ilk gözlem 2026-09-12)
- — FreeFlow: A Bias-free Hierarchical Transformer for Optical Flow Estimation (ilk gözlem 2026-09-12)
- — X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation (ilk gözlem 2026-09-11)
- — Generative Late-Interaction Embeddings For Visual Document Retrieval (ilk gözlem 2026-09-11)
- — Recursive Code World Models: Building Complex Worlds through Recursive Scene Programs (ilk gözlem 2026-09-11)
- — World in World: Explore the World with World Models (ilk gözlem 2026-09-11)
- — SenseNova-U1.5: Towards Native Unified Visual Intelligence (ilk gözlem 2026-09-11)
- — Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking (ilk gözlem 2026-09-12)
- — Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning (ilk gözlem 2026-09-12)
- — IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications (ilk gözlem 2026-09-12)
- — An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics (ilk gözlem 2026-09-11)
- — NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction (ilk gözlem 2026-09-11)
- — RESCUE-BENCH: Towards Relation-Aware Multi-Party Emotional Support Conversation Systems (ilk gözlem 2026-09-10)
- — Studying Image Tokenizers as Visual Languages in Unified Multimodal Models (ilk gözlem 2026-09-12)
- — ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation (ilk gözlem 2026-09-12)
- — SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research? (ilk gözlem 2026-09-10)
- — Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails (ilk gözlem 2026-09-10)
- — Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation (ilk gözlem 2026-09-09)
- — SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem (ilk gözlem 2026-09-11)
- — DF26: We Cannot Tell Fake From Real Anymore (ilk gözlem 2026-09-10)
- — Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents (ilk gözlem 2026-09-10)
- — RelightFormer: Feed-forward Generative Transformer for Multiview Object Relighting (ilk gözlem 2026-09-09)
- — Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection (ilk gözlem 2026-09-09)
- — Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's Expertise (ilk gözlem 2026-09-09)
- — Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy (ilk gözlem 2026-09-09)
- — SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions (ilk gözlem 2026-09-09)
- — ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding (ilk gözlem 2026-09-09)
- — Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2 (ilk gözlem 2026-09-12)
- — DianShi-RxnDB: A Large-Scale, Fine-Grained Organic Reaction Data Platform Built via a Fully Automated Pipeline for Researchers and AI Agents (ilk gözlem 2026-09-10)
- — MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads (ilk gözlem 2026-09-21)
- — EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents (ilk gözlem 2026-09-11)
- — Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models (ilk gözlem 2026-09-10)
- — Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model (ilk gözlem 2026-09-09)
- — Srijika: OpenType-Layout-Reusing Font Restyling for Nine Indic Scripts (ilk gözlem 2026-09-19)
- — WearableQA: A Benchmark for Health Reasoning over Real-World Wearable Data (ilk gözlem 2026-09-10)
- — RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? (ilk gözlem 2026-09-09)
- — Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization (ilk gözlem 2026-09-07)
- — RISE: Recursive Improvement via Self-Extrapolating Policy Distillation (ilk gözlem 2026-09-07)
- — Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference (ilk gözlem 2026-09-07)
- — WorldSculpt: Generating Compositional Worlds from Grounded Videos (ilk gözlem 2026-09-07)
- — Unlocking Lossless Speedups in LLMs via Discrete Diffusion (ilk gözlem 2026-09-08)
- — FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience (ilk gözlem 2026-09-08)
- — What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through Conversation (ilk gözlem 2026-09-08)
- — Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning (ilk gözlem 2026-09-08)
- — HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals (ilk gözlem 2026-09-08)
- — AdaptVPR: Route-Aware Hard Positive Generation for Robust Visual Place Recognition (ilk gözlem 2026-09-07)
- — When Models Edit Too Much: On the Fidelity of Minimal Code Edits (ilk gözlem 2026-09-07)
- — MaxKernel: Agentic Kernel Generation for TPUs (ilk gözlem 2026-09-07)
- — When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference (ilk gözlem 2026-09-07)
- — DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training (ilk gözlem 2026-09-05)
- — Last Translation Benchmark (ilk gözlem 2026-09-05)
- — Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs (ilk gözlem 2026-09-05)
- — Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction (ilk gözlem 2026-09-04)
- — Compile by Training: Turning Natural-Language Specifications into Local Neural Functions (ilk gözlem 2026-09-04)
- — PACE: Towards Surfacing Hidden Conflicts in User Requests (ilk gözlem 2026-09-04)
- — Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States (ilk gözlem 2026-09-04)
- — Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding (ilk gözlem 2026-09-04)
- — FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow (ilk gözlem 2026-09-04)
- — WorldReward: Reward Modeling for Camera-Conditioned World Models (ilk gözlem 2026-09-04)
- — Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles (ilk gözlem 2026-09-22)
- — Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation (ilk gözlem 2026-09-08)
- — ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding (ilk gözlem 2026-09-07)
- — RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning (ilk gözlem 2026-09-05)
- — A Common Measure of Communication for Speech Brain-Computer Interfaces (ilk gözlem 2026-09-05)
- — VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement (ilk gözlem 2026-09-05)
- — Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration (ilk gözlem 2026-09-04)
- — Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance (ilk gözlem 2026-09-04)
- — The Missing Temporal Link: Temporal Context Routing for Script-Driven Audio-Video Generation (ilk gözlem 2026-09-04)
- — EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents (ilk gözlem 2026-09-08)
- — PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization (ilk gözlem 2026-09-14)
- — Puppeteer: Object-Grounded Posture-Aware Co-Speech Gesture Generation (ilk gözlem 2026-09-10)
- — AgenticGen: Reward-Guided Agentic Video Generation for Advertising (ilk gözlem 2026-09-10)
- — Dr. Claw: An AI Scientist Workspace for Vibe Research (ilk gözlem 2026-09-08)
- — Using Grounded Theory for Agent Behavior Analysis at Scale (ilk gözlem 2026-09-05)
- — AgentKernel: The Trust-Native Agentic Operating System (ilk gözlem 2026-09-25)
- — Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable Questions (ilk gözlem 2026-09-09)
- — Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space (ilk gözlem 2026-09-05)
- — QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation (ilk gözlem 2026-09-05)
- — HyQuant: Hybrid-Precision Quantization for LLM Attention (ilk gözlem 2026-09-11)
- — Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue (ilk gözlem 2026-09-07)
- — Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training (ilk gözlem 2026-09-04)
- — One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation (ilk gözlem 2026-09-08)
- — Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing (ilk gözlem 2026-09-08)