Turns Matter: Advancing Streaming Video RL via Turn-Level Credit
In shortTurnWise adds turn-level credit assignment to streaming video RL, improving decision quality without extra critics.
Published 4 Nov 2026
5 Nov 2026
200 papers that day.
Picks that day
Think Less, Locally: Local Preference Learning for Reasoning Compression
In shortLoCo learns when to stop reasoning locally, cutting chain length while keeping accuracy.
Published 3 Nov 2026
Everything else
198 more papers from this day- Nov 3 DreamX: Video Diffusion Model is a Universal Latent Action Learner
- Nov 4 From Pixels to Actions - Towards Native Vision-Language-Action Policies
- Nov 3 Factorized MLLM Embeddings for Composed Image Retrieval
- Nov 3 PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data
- Oct 29 EvoTeam: Multi-Agent Collaboration via Evolving Teams
- Oct 31 FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting
- Nov 2 VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks
- Oct 30 GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling
- Nov 4 EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL
- Nov 2 Dory1.0-4B: A Looped Normalized-GPT
- Nov 4 What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents?
- Nov 2 SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
- Nov 3 FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing
-
Nov 4
FrontierPhysics: Evaluating Agents for End-to-End Physics Research
TrendingReasoning & Agents
- Nov 3 LoopVQ: Sub 1-bit KV Cache Quantization for Looped Transformers
- Nov 2 VidDub: Replacement-Aware Distillation for Two-Step Video Dubbing
- Oct 28 How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
- Nov 2 Solv3R: 3D Looped Transformer as a Multi-view Solver
- Nov 4 PyRUA-REAL: Robot Exploration and Adaptive Learning through RSI in the Real World
- Nov 2 VideoMemBench: How Well Do MLLMs Remember in Video Conversations?
- Oct 28 Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation
- Nov 3 Adversarial Speculative Reasoning Improves Long Horizon Agents
- Nov 3 RoboTryOn: Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On
-
Oct 30
Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents
Top pickReasoning & Agents
- Oct 30 StreamDuo: A Live Commentator and a Research Agent for Unseen Games
- Nov 2 BEND 2.0: Benchmarking the Capabilities Needed to Design DNA
- Nov 4 VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation
- Oct 29 MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation
- Nov 1 Every Pixel Is an Option: A System One Model for Medical Ultrasound Biometry
- Oct 31 Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
- Nov 3 Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting
- Nov 3 Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAs
- Nov 3 Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs
- Nov 3 SphereFlow: Missing Modality Imputation via Geometric Transport on Hypersphere
- Nov 2 GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data
- Oct 26 Muon Makes the First Mixture-of-Experts Layer Harder to Balance
- Nov 4 SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?
- Nov 3 On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation
- Nov 3 You don't need long context
- Nov 3 Going Deeper With Memories
- Nov 2 AnchorComplete: Recovering Complete Scene Meshes from Partial Point Clouds
- Nov 4 LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis
- Nov 4 GeoBiaset: A Counterfactual Benchmark for Demographic Bias in World-Level Geolocalization
- Nov 4 Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline
- Nov 3 YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction
- Nov 2 VeriSpoof: Beyond Real or Fake with One Audio LLM
- Oct 29 Cross-Prompt Reuse of Entity-Replacement Responses
- Nov 2 Auto-Research Agent on MSA Organization to Improve Protein-Protein Complex Structure Prediction
- Nov 4 BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories
- Nov 4 Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web
- Nov 4 Reasoning-Aware Cross-Modal Association Unlearning in Multimodal Large Reasoning Models
- Nov 4 VABAR: A Variational Automation Benchmark for Agentic Robotics
- Nov 4 Agent-Driven Generative Priors for Pathology Image Synthesis and Segmentation
- Nov 4 Overview of the NTCIR-19 SciClaimEval Task: Cross-modal Claim Verification in Scientific Papers
- Nov 4 WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark
- Nov 3 How Finely Can Vision-Language Models See Biology? Bio-VQA: A Benchmark for Taxonomic, Morphological, Spatial and Individual Reasoning
- Nov 3 NightIQA: A Comprehensive Dataset and Benchmark for MLLM-Based Nighttime Image Quality Assessment
- Nov 3 Kierston & KierstonBench: Simulation of Allentown, PA and Evaluation of Language Models in Crime Investigation and Surveillance Tasks
- Oct 25 When Fine-Grained Credit Assignment Helps and Hurts: Multimodal Agentic Reinforcement Learning through Video Editing
- Nov 4 EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models
- Nov 4 LibriSpeech-Real-QA: A Benchmark for Streaming Question Answering
- Nov 4 HarnessFlow: MCTS-Guided Harness Optimization for LLM Agents
- Nov 4 FedIA: Instance-Aware Cross-Modal Representations for Federated Prompt Learning
- Nov 3 Self-Supervised Learning of Universal Latent Spaces for Operator Learning
- Nov 3 Grounded but Not Immune: Confirmation Bias in Agent-as-a-judge
- Nov 3 Data-Efficient Scaling-Law Discovery for Recommendation Systems via Coupled Hyperparameter Scaling
- Nov 3 From Tokens to Trajectories: Parameter-Efficient Continuous Adaptation of Unified Multimodal Models
- Nov 3 MDSKILL: Learning to Internalize Skill Memory through Multi-View Distillation for Efficient Dynamic Agent Self-Evolution
- Nov 3 Learning Where to Look: Observation Policy Optimization for Thinking with Images
- Nov 3 Anomaly Detection on Resource-Constrained Devices with Reservoir Computing
- Nov 3 Where to Connect? Boosting MLLMs via Dynamic Gated Pathways across ALL ViT and LLM Layers
- Nov 4 Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment Transfer, Learning, and Evaluation
- Nov 4 Entropogram-guided Visual Realignment Decoding: Capturing the Rhythm of Multimodal Reasoning
- Nov 4 Twists and Turns: A Graph-Based Benchmark and Framework for Long-Term Memory in Exploration Tasks
- Nov 4 Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning
- Nov 4 SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving
- Nov 4 Retrieval Supersedes Scale: Efficient Log Level Prediction via Multiplex Socio-Technical Context
- Nov 4 Feature Puzzles: Single-Image Supervision for Multi-View 3D-Aware Segmentation
- Nov 3 Modulating Merging Strengths via Joint Loss Estimation for LoRA-based Continual Learning
- Nov 3 Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models
- Nov 3 TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport
- Nov 3 iMED: A Multi-Endoscope Dataset for Surgical 3D Perception
- Nov 3 MambaHand: Local Identity and Behavioral Sequence Learning with Mamba for Dynamic Hand Gesture Authentication
- Nov 4 ServerBench: How can your coding agents design specialized LLM serving systems?
- Nov 3 Open-HumanScale: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models
- Nov 4 Energy-Guided Transport for Projection-Free Physics-Informed Flow Matching
- Nov 4 EvoOPD: Evolving Privileged Information Strategies for Black-Box On-Policy Distillation
- Nov 4 CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation
- Nov 4 AmbiHTMLBench: A Benchmark for HTML-based Visually Rich Document parsing
- Nov 4 EvoGuard: Mitigating Degradation in Online Skill Evolution
- Nov 4 MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection
- Nov 4 DSRS: Teaching MLLMs to Perceive, Reason, and Segment in Complex Driving Scenes
- Nov 4 Which One Is Sounding? Binaural Sounding Instance Disambiguation for Audio-Visual Segmentation
- Nov 4 TouchéWorld tech report : Towards Online Unified Camera--Hand Exploration in Generative Worlds
- Nov 4 Alleviating Limited Effectiveness and Multi-Class Collapse in Deep Graph-level Clustering
- Nov 4 Timing is Everything: Inferring Temporal Membership in Continually Updated Models
- Nov 3 Text-Only Domain Adaptation for Low-Resource Medical ASR: Shallow Fusion and Density Ratio Rescoring for Hausa
- Nov 3 TSFM Meets LLM: Context as Covariates
- Nov 3 GUILD: Guided Iterative Data Collection for Imitation Learning
- Nov 3 Möbius: A Unified Motion-Language Model Bridging Understanding and Generation
- Nov 3 Meta$^2$: Precomputing Reusable Knowledge for Online Harness Evolution in Long-Horizon Agents
- Nov 3 ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents
- Nov 3 The Pen is Mightier than the Pixel: Natural Textual Unlearnable Example for Large Vision Language Models
- Nov 3 Training Specialist LLMs on Your Phone: Forward-Only Optimization via Block-Spectral Coordinates
- Nov 3 Density-Aware Reward Scaling: A Reinforcement Learning Framework for Reward-Proportional Sampling
- Nov 3 FedCSGA: Evolutionary Client Selection with Joint Statistical and System Heterogeneity in Federated Learning
- Oct 31 QFabric: Guarded Cross-Domain Task Recovery and Its Limits on a Linux-RTOS Board
- Nov 4 CompressionBench: How can your coding agents compress LLMs?
- Nov 4 TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing
- Nov 4 MKD2World: A Typed Spatial MarkDown World Model For Web Agents
- Nov 4 DreamRealm: Exploring and Materializing Hallucination Worlds for Trustworthy Vision-Language Models
- Nov 3 D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding
- Nov 4 Traffic-VL: Reinforced Vision-Language Models for Generalizable End-to-End Traffic Signal Control
- Nov 4 Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification
- Nov 4 A Systematic Benchmark for Evaluating Multimodal Personalized Reasoning of Vision-Language Models
- Nov 4 ModalSearcher: Weaving Visual Evidence into Autonomous Cross-Modal Deep Search
- Nov 4 STARE: Scene Text-Aware multimodal Retrieval for Everyday objects
- Nov 4 SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation
- Nov 4 RI-Prune: Relation and Information Aware Visual Token Pruning for Multi-Image Vision-Language Models
- Nov 4 MotoVerse: A Benchmark for Predictive Perception of Motorized Two-Wheelers in Dense Unstructured Traffic
- Nov 3 On the Design of Hyper-Connections: Simplification, Stability, and Scalability
- Nov 4 Chronos: Sequential Identity-Preserving Video Generation by Temporal Anchoring
- Nov 4 Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet
- Nov 4 ReTailor: A Residual Feature Tailoring Framework for Real-Time Cross-Sensor Pansharpening Adaptation
- Nov 3 FlyHash for LLM Agent Memory: An Empirical Validation and a New Application
- Nov 3 Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses
- Nov 3 TRUST-Stereo: Teacher-Assisted Robust Uncertainty-Guided Search and Transfer for Fast Stereo Matching
- Nov 3 VIPBench: A Human-Aligned Benchmark for Voice Identity Perception in the Age of Voice Cloning
- Nov 3 ViBench 2.0: A Benchmark for Long-Horizon Software Building
- Nov 3 C-GRPO: Conformal Group Relative Policy Optimization
- Nov 3 Towards Efficient Whole Page Ranking with One-Pass Inference
- Nov 3 Agnostic Learning by Imitating
- Nov 3 Multi-Objective Generative Optimization via Expected Hypervolume Fine-Tuning
- Nov 3 Beyond Foundation Models: PFN Priors Improve Tabular Hyperparameter Optimization
- Nov 3 Robustness Verification against Patch Attacks via Group-Lasso Semidefinite Relaxation
- Nov 2 VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents
- Nov 3 PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations
- Nov 3 TEXMET: A Deep Learning Benchmark for Archaeological Textile Reconstruction
- Nov 3 DenseTwins: Dense Modality Decoupling for Multimodal Self-Supervision
- Nov 3 Self-Privileged Fine-Tuning
- Nov 3 Directional Statistics in Signal Processing: A Geometry Driven Overview of Models, Learning, and Applications
- Nov 2 Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval
- Nov 4 Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
- Nov 4 FedFiOT: Fisher-Weighted Optimal Transport for Model Merging in One-Shot and Few-Round Federated Learning
- Nov 4 Interactive World Simulation with Cosmos for Physical AI
- Nov 4 BudgetSplat: Budget-Controllable Generalizable Gaussian Splatting
- Nov 4 IDSISA: Influence-Distilled Sharded Training for Efficient Machine Unlearning
- Nov 4 FPTR: Feasibility-Preserving Transactional Refinement for Deadline-Constrained Joint Beam and Resource Allocation
- Nov 4 SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory
- Nov 4 TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics
- Nov 4 TOP: Transmission-Oriented Remote Sensing Pansharpening
- Nov 4 LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution
- Nov 4 Prism: Bidirectional Self-Teaching for Unified Multimodal Models
- Nov 4 A.S.E 2.0: Understanding How Repository Context Impacts the Security of LLM-Generated Code
- Nov 4 Cross-Modal Semantic Successive Refinement for Generative Image Communication over Underwater Acoustic Channels
- Nov 4 Annotator-Free Object Detection via Foundation Model Collaboration
- Nov 4 Grounding in the Dark: Text-Only Training for Zero-Shot Video Temporal Localization
- Nov 4 Learning When to Think Aloud in Latent Reasoning
- Nov 4 XuanJian-DINOSAR: A SAR Foundation Model Based on Global and Local Semantic Consistency
- Nov 4 DeepfakeGenome: Toward Next-Generation Deepfake Attribution
- Nov 4 DecoupAttn: Decoupled Sparse Attention for Training-Free Acceleration of Video Diffusion
- Nov 4 Autonomous agents for electricity-system planning
- Nov 4 RECAP: Context-Aware Prediction Recycling with Request-Local and Persistent Memories for Multimodal Speculative Decoding
- Nov 4 CellCanon: An Agentic Cellular World Model for Prediction, Explanation, and Observation-Driven Updating
- Nov 4 Autonomy and Coordination in Intelligent Manufacturing: A Recursive Autonomous Agent Framework
- Nov 4 Learning When Human Decisions Matter: Executor-Relative Consultation Value for LLM Agents
- Nov 4 GREP: Grounding Generated Room Evaluation in Principles
- Nov 4 Item Representations Matter: Bridging Hard Semantic IDs and Soft Prototype Mixtures for Generative Retrieval
- Nov 3 Learning Hierarchical Patch Splitting Policies for Faster Vision Transformers
- Nov 3 Prospective Memory for Proactive LLM Agents
- Nov 3 Spatio-Temporal Multi-Order Interaction for Video Recognition
- Nov 3 Classical training of conditional instantaneous quantum polynomial-time Born machines
- Nov 3 Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark
- Nov 3 GSCV++: Lightweight 3D Gaussian Splatting Sequence Compression via Standard Video Codecs
- Nov 3 ARLoop: Fully-Open Pre-trained Looped Transformers with Attention Residuals
- Nov 3 Diagnosis by Composition: Detecting and Localizing Unseen Diseases by Composing Learned Radiological Findings
- Nov 3 Macrocanonical Generator Networks: Data-Efficient Neural Surrogates for Amortized Physics Simulation
- Nov 3 VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models
- Nov 3 Federated Transfer Learning for Medical Image Classification under Mixed Skew
- Nov 3 RGB Photo Enhancement with Deep Learning on Smartphone GPUs: Mobile AI 2026 Challenge Report
- Nov 3 Matched but Not Better: An Equivalence-Tested Benchmark of Quantum Machine Learning on Six Clinical Datasets and the QML-Health-READY Reporting Framework
- Nov 3 Learned Smartphone ISP on Mobile GPUs: Mobile AI 2026 Challenge Report
- Nov 3 An Agentic Framework for Quality-Aware and Scenario-Adaptive Image Compression
- Nov 3 One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough
- Nov 3 Feeling of Knowing in Large Language Models
- Nov 3 ReSI-Math: Exploring Recoverable Capability Frontiers for Efficient Reasoning Improvement
- Nov 3 TactiNavi: Serving and Revising an LLM Game Coach with Explicit Strategy Conditions
- Nov 3 Pixel-space video generation with U-JiT
- Nov 3 Beyond Local Refinement: Wide-Area Precise Cross-View Localization
- Nov 3 Uncertainty-Aware Prototype Learning for Open-Set Test-Time Adaptation
- Nov 3 MIMIC-Note-Extract: A Large-Scale Structured Dataset Extracted from MIMIC-IV-Note Discharge Summaries
- Nov 4 Perceptive Humanoid Motion from Simulation
- Nov 4 Visual Token Routing: Learning to keep tokens that matter
- Nov 4 Before You Continue: Evaluating Time-Sensitive Safety Awareness in Conversational Assistants
- Nov 4 LooM: Loop-Invariant Memory for Causal Encoder-Decoder Language Models
- Nov 4 Semantic Residual Vector Quantization for Sign Language Generation
- Nov 4 Route First, See Later: Enabling Vision Agents to Reason Scientifically by Separating Routing Policy from Action Spaces
- Nov 4 Continual Classification Beyond the Kernel Regime: Harnessing the Sparsity Bias of L2 Regularization in Diagonal Linear Networks