Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs
In shortLOWN skips image processing during diffusion decoding unless needed, cutting FLOPs while keeping performance.
Published 26 Oct 2026
1 Nov 2026
200 papers that day.
Picks that day
Proving and Improving the Platonic Representation Hypothesis with JEPAs
In shortJEPAs trained on paired views learn a shared representation up to rotation, proving the Platonic Representation Hypothesis and outperforming next‑token prediction.
Published 29 Oct 2026
Everything else
198 more papers from this day- Oct 29 Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
- Oct 28 Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps
- Oct 21 VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team
- Oct 29 HairDeck: Animation-Ready Stylized Hair Cards from a Single Image
- Oct 28 AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding
- Oct 22 A Broader Look into MLLM's Retrieval Heads
- Oct 25 Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models
- Oct 27 IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation
- Oct 18 LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book Models
- Oct 14 CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue Models
- Oct 26 Know, then Draw: A New Learning Paradigm for Visual Generation
- Oct 25 Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks
- Oct 29 Your LR Schedule May Not Be Principled: Effective Learning Rate Scheduling in Weight-Normalized Training
- Oct 29 EditAgent: Rethinking Agentic Image Editing
- Oct 27 Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?
- Oct 29 Intrinsic Distribution Matching
- Oct 15 ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics
- Oct 27 Scaling Lean Theorem Proving for Real-World Code Verification
- Oct 27 Multi-Token Prediction Done Right
- Oct 27 WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video
- Oct 13 Amortizing Sequential Experimental Design in Reasoning LLMs
- Oct 29 PhysInsert: Physically Plausible Object Insertion with Geometric Priors and Bidirectional Object-Scene Interactions
- Oct 28 AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers
- Oct 20 LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data
- Oct 29 Glance: The Generator Is Its Own Reranker
- Oct 28 FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss
- Oct 28 OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation
- Oct 15 PersonaCUABench: Benchmarking Computer-Use Agents Serving Diverse Personas
- Oct 14 RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI Agents
- Sep 29 TauIndianBankBench: Procedure-Aware, Action-Oriented Evaluation of Tool-Using Conversational Agents
- Oct 28 Training Foundation Models with a Single Algorithm
- Oct 29 MLLM-GS: Multimodal Large Language Model Prior-Guided Fast Novel View Synthesis in Extreme Environments
- Oct 27 Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models
- Oct 17 Holo4D: Holistic 4D Reconstruction as Geometric Control for Video Diffusion
- Oct 26 WebAnything: From the Wild Web to Scalable Agent Environments
- Oct 28 Unlocking Any-Order Generation in Pretrained Autoregressive Image Models
- Oct 28 EPSBench: Benchmarking LLM Agents for Earnings Forecasting
- Oct 20 CausGround: Causal Interaction Grounding for Adaptive Embodied Planning
- Oct 24 Broken on Arrival: Non-Functional Quantized LLM Artifacts in Public Model Registries and How to Catch Them
- Oct 23 After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System
- Oct 23 PreView: Enhancing GUI Grounding with Preprocessed Views and Cues
- Oct 26 SO-101 Bench: Accessible Spatial Manipulation
- Oct 29 Localizing Concepts in Visual Autoregressive Models
- Oct 29 DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis
- Oct 24 Matched Capabilities, Different Behaviors: A Controlled Study of MCP and CLI Interfaces for Language Agents
- Oct 25 Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load
- Oct 29 Calibrating Attention-Based Token Pruning for Efficient Multi-Image Synthesis in UMMs
- Oct 29 CLaW: Codec-Guided Adaptive Latent Watermarking for Traceable Diffusion Image Generation
- Oct 29 Mind The Gap (MTG-AD): Dataset and Fine-grained Evaluation for End-to-End Inline Audio Descriptions
- Oct 29 Heterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels
- Oct 29 ATLAS-Bench: An Agentic Tool-Use Benchmark for Local Area Search
- Oct 29 Tracking Task Progress Through Errors and Recovery:A Benchmark and Recurrent Distributional Model
- Oct 28 Trustworthy Distributed Machine Learning in Cloud-Edge-IoT Systems: A Heterogeneity-Aware Survey of Security, Privacy, and Robustness
- Oct 29 M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models
- Oct 29 Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin
- Oct 29 Raincheck: Deferred Multimodal Prefill for Efficient Multi-Turn MLLM Inference
- Oct 29 LatentWeave: Test-Time Latent Optimization for Multimodal Reasoning
- Oct 28 Beyond Passing Tests: A Systematic Review and Controlled Re-evaluation of Techniques for Improving the Quality of LLM-Generated Code
- Oct 28 Deogen: Automatic Benchmark Generation for Reasoning over Policies
- Oct 29 A Unified Benchmark for Aerial-Enhanced Autonomous Driving: The KITScenes Aerial Dataset
- Oct 29 Human--AI Interactions as First-Class Data: A Formal Interaction Model and Runtime for Explainable AI Collaboration
- Oct 29 Turing LLM Post-Training: Calibrated Distillation and Efficient Dynamic-MoE Execution
- Oct 28 Open-World Object Motion Anticipation via Meta-Learned Semantic Adaptation
- Oct 29 MetaRefine: Score Refinement with Multi-Level Features for Image Assessment
- Oct 29 AVPS-360: A Spatial Audio-Visual Benchmark for Instance Segmentation and Tracking of Sound-Producing Persons
- Oct 29 Uncertainty-aware Feedback Loop Diagnosis: integrating reinforcement learning and conformal prediction for reliable wafer defect classification
- Oct 29 A Unified Hessian-Guided Framework for Post-Training Quantization
- Oct 29 Hierarchical Step Decomposition for Training-free Online Video Step Grounding
- Oct 29 PhysAg3D: Bridging 3D Generative and Agentic Models for High-Fidelity and Physically-Interactive Assets
- Oct 29 LiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models
- Oct 29 ROAD: Modern Adversarial Training for Simple One-Step Distillation at Scale
- Oct 29 Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-Dual
- Oct 29 Regional Anchor Routing for Multi-Object Motion Transfer
- Oct 29 Safe Multi-Objective Reinforcement Learning: Zero Constraint Violation and Primal-Averaging Convergence
- Oct 29 Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models
- Oct 29 Can Image Agents Complete Visual Commissions? A Benchmark and Modular Framework
- Oct 29 MRC-MMAgent: Reinforcement Learning for Multi-Role Collaboration in Multimodal Tool-Using Agents
- Oct 29 Efficient Covariance-Aware Vicinal Latent Diffusion for Continuous Conditional Image Generation
- Oct 29 IMRouter: Imbalance-aware Temporal Pattern Routing for LLM-based Time Series Forecasting
- Oct 29 COGS: A Diagnostic Benchmark for Attribute-Aware Object-Level 3D Gaussian Splatting Perception
- Oct 29 From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion
- Oct 29 SymAnt: Grounding Long-Horizon Action Anticipation with Adaptable Symbolic Priors
- Oct 29 TextSeal2: Distortion-Free LLM Watermarking with Copula Mixing and Memoryless Races
- Oct 29 VeriCUA: Verification as Agentic Exploration for Computer-Using Agents
- Oct 29 A Tutorial on Shape Servoing of Deformable Objects-Part I: Fundamentals
- Oct 29 PhysCount: Do MLLMs Count Visual Appearances or Physical Entities?
- Oct 29 LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation
- Oct 29 Agentic University: Collaborative Agents for Personalized Learning
- Oct 29 TouchBridge: Tactile-Conditioned Human-to-Robot Transfer for Dexterous Manipulation
- Oct 29 TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
- Oct 29 Learned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic
- Oct 29 Locating and Closing Information Gaps in Multi-Agent Systems
- Oct 29 Greenscapes: Optimized Vegetation Configurations in Cities
- Oct 29 UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation
- Oct 29 TokenRepel: Generating Diverse Image Sets Without Compromising Quality
- Oct 29 DWISE: Denoising Workload-Informed Scheduling Engine
- Oct 29 Aligning Medical Vision Language Models at the Capability Boundary with Entropy Adaptive Rubric Grounding
- Oct 29 Revisiting Over-refusal in Safety-aligned Large Language Models: A Representation and Optimization Perspective
- Oct 29 A New AFIB Detection Method with Deep Neural Networks
- Oct 28 Where Do Vision Language Models Fail at 3D Reasoning?
- Oct 29 Well-Specified and Well-Tested? Assessing SWE-bench-Style Datasets with a Self-Evolving Agent
- Oct 29 Decoding Geometry, Not Tokens: Efficient VLMs for Robot Affordance and Trajectory Prediction
- Oct 28 WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining
- Oct 29 SocialArena: Evaluating Social Intelligence in Large Language Models
- Oct 29 Seeing and Imagining as One: Unified Video Generation and 4D Perception for Embodied World Modeling
- Oct 28 How Architecture, Typology, and Adaptation Strategies Shape ASR for Low-Resource African Languages: A Controlled Empirical Study
- Oct 28 Communication-Efficient Clustered Federated Learning in Non-IID Wireless Networks
- Oct 28 What do MLLMs know about 'Waldo'? Evaluating Visual Reasoning under Multi-Instance Multi-Object Challenges
- Oct 28 Evaluating Visual Realism of AI-Generated Videos with Eye Tracking
- Oct 28 Explore Where It Matters: Targeted Exploration for Efficient Rover Adaptation
- Oct 29 SwapBot: Tool-Centric Robot Manipulation via Interchangeable End-Effectors and Tactile Sensing
- Oct 29 Advancing Clinical Genomic Analysis with a Skill-Centred Agent
- Oct 29 Efficient Scalable Oversight via Rewinding
- Oct 29 IndicIPR-QA: A Benchmark for Extractive Question Answering on Indian IPR Laws
- Oct 28 How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
- Oct 29 Algebraic World Model: From Exploration to Proofs
- Oct 29 Training language models in simulation for psychiatric intake
- Oct 29 Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records
- Oct 29 Rimuru: Unified Memory Management for Modern LLM Serving via Elastic Expert Offloading
- Oct 29 LoRe-MIM: Lost-or-Replaced Masked Image Modeling for Self-Supervised Representation Learning in Whole-Body PET/CT
- Oct 29 Confidence-Aware Speed-over-Ground Estimation from Doppler Spectra via Reconstruction-Based Representation Learning
- Oct 29 Conformal Annotation with Randomized Expert Review: Application to Online Cell-Type Labeling
- Oct 29 ScienceJudge: Pattern Perturbation Augmentation for Sentence-Level Scientific Claim Verification
- Oct 29 Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs
- Oct 29 Upcycling Language Models for Multiple Specialized Domains
- Oct 29 Uncertainty-aware Coarse-to-Fine Main Pancreatic Duct Segmentation for Width Measurement in 3D MRCP
- Oct 29 BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots
- Oct 29 EvoTeam: Multi-Agent Collaboration via Evolving Teams
- Oct 29 PAPERBENCHX: Can AI Reproduce Science Across Disciplines?
- Oct 29 Cross-Encoder Anchor Refinement for Zero-Shot Anomaly Detection
- Oct 29 WorldProbe: When Video World Models Fall Apart under Long-Horizon Spatial Exploration
- Oct 29 MoLRSI: A Recursive Self-Improving AI agent for Molecular Discovery
- Oct 29 Bayes-Consistent Losses for Adaptive Inference in Classification
- Oct 29 DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence
- Oct 29 From Reasoning to Action: Consequence-Grounded Alignment for Vision-Language-Action Models
- Oct 29 Category-Anchored Large Language Models for Next POI Recommendation
- Oct 29 Compile Away Uncertainty: Self-Evolving Agent Skills via Programmatic Compilation
- Oct 29 Sparse Fine-Tuning for Parameter-Efficient Adversarial Training
- Oct 29 Utility-WAM: Correcting Future-Induced Action Changes
- Oct 29 RetroChessBench: A Benchmark for Reconstructing and Proving Chess Histories
- Oct 29 Language-Grounded Force/Torque Pretraining for Extrinsic Contact Perception
- Oct 29 Analyzing Condensation on Patterned Surfaces via Deep Learning
- Oct 29 DICE: Decentralized Incentive-driven Federated Learning for Efficient & Scalable Customization of Pretrained Models in Web3
- Oct 29 HERA: Assessing an Autonomous Agent for Quantum Device Measurement
- Oct 28 Reinforcement Learning for the Game of Balatro: A Fast Simulator and Two-Policy Training Approach
- Oct 28 Modular Bayesian Foundation Models: Bayesian time series encoders for OOD detection, routing and forecasting
- Oct 28 LightGenBench: A Benchmark for 3D Emission Generation
- Oct 28 TableTune: Measured, Self-Correcting Draft-Length Tables for Dynamic Speculative Decoding
- Oct 28 TreasuryQA Bench: Can AI Agents Work an Archive of Scanned Financial Records?
- Oct 28 Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems
- Oct 28 Contextual Embeddings Beyond the Gold Chunk
- Oct 28 Discovering Jailbreaks via Curriculum of Models
- Oct 28 Skillful and realistic precipitation forecasting with reinforced diffusion
- Oct 28 Beyond fabrication: Misattributed numbers in papers written by AI research agents
- Oct 29 Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering
- Oct 29 Rethinking Neural Thickets Without Weight Perturbations
- Oct 29 ShallowDefend: Harnessing Shallow Safety Alignment for Multi-Turn Defender
- Oct 28 Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation
- Oct 29 Soil Moisture Estimation in Precision Agriculture: A Knowledge Distillation Approach
- Oct 28 Scaling Mathematical Proof Supervision from Structured Textbooks
- Oct 28 HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model
- Oct 29 Don't Lose the Thread: Empowering Long-Horizon LLM Agents with Cognitive Resource Self-Allocation
- Oct 29 Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets
- Oct 29 EpiAgent: Epistemic Self-Play for LLM Agents
- Oct 29 Benchmarking color judgment in multimodal LLMs with CIE-computable ground truth
- Oct 29 Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement
- Oct 29 AdMuse: Skill-Guided Creative Advertising Image Generation
- Nov 2 VideoMemBench: How Well Do MLLMs Remember in Video Conversations?
- Oct 29 How Much Should a VLA Trust Its Reasoning? Step-Level Guidance as a Measured Action-Value Function
- Oct 29 Learning Calibrated Confidence for Multi-Agent Collaboration
- Oct 29 Spectral Invariant Fusion and Refinement for Domain Generalized Semantic Segmentation
- Oct 29 Surface Conditioning for Zero-Shot Multivariate Correction in a Marine Biogeochemistry Emulator
- Oct 29 Practical Assessment of Agentic Systems in Acoustics
- Oct 28 Incentivizing Self-Learning in Large Language Models via Reinforcement Learning
- Oct 29 FutureWorld: A Plug-and-Play Causal Next-State Predictor for Interactive Video World Exploration
- Oct 29 DEG: Diffusion-Enhanced GFlowNet for Solving Vehicle Routing Problems
-
Oct 28
Does Scaling Toward AGI Depend on What System-1 Lets System-2 Execute?
Top pickReasoning & Agents
- Oct 29 Achieving Minimax-Optimal First-Order and Best-of-Both-Worlds Regret Simultaneously in Multi-Armed Bandits
- Oct 29 End-to-End Guarantees for Masked Diffusion Models under Conditional Mixing
- Oct 29 PathCowork: Learning from real-world pathology practice to build AI copilots
- Oct 29 Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
- Oct 29 ACD-GS: Asymmetric Curvature-aware Densification for 3D Gaussian Splatting
- Oct 29 CAD-WAM: Anticipating Geometry for Text-to-CAD Generation
- Oct 29 DeCoRL: Decomposed Consistency Reinforcement Learning for Multi-Image Composition
- Oct 29 Where to Learn and How Far to Roll Out: Efficient Adaptive Training for GUI Agents
- Oct 29 Grounding Multimodal Reasoning with Evidence-Ablated Negatives
- Oct 29 PRISM: Personalized Item Representations in User History
- Oct 29 VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation
- Oct 29 STRATA: Reinforcement-driven Active Sampling with Tri-paradigm Adaptation for Efficient 3D Spatial Transcriptomics
- Oct 29 Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection
- Oct 29 Tactus: Tactile & Pose Sensing Glove for Natural Dexterity Data Collection
- Oct 28 When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown
- Oct 28 Distilling the Shape of Uncertainty: What On-Policy Distillation Learns and How to Predict It
- Oct 28 Where You Inject Matters: The Trust Region Effect in LLM Agents
- Oct 28 Learning to Reason from Reference Samples Alone: Reinforced Adversarial Learning for Modern LLM Post-Training
- Oct 28 Beyond Region Memory: Local Point Tracking for Vocal Cord Localization in Video Laryngoscopy
- Oct 28 AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
- Oct 29 CrossWeave: Cross-Modal Scene and Instance Retrieval from Sparse 2D-3D Alignment