{"total":174,"rows":[{"id":"2607.02770","title":"Gemma 4 Technical Report","created":"2026-07-02","cited_by_count":259,"area":"mllm"},{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2605.17912","title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","created":"2026-05-18","cited_by_count":10,"area":"wm"},{"id":"2605.31572","title":"nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous Driving","created":"2026-05-29","cited_by_count":9,"area":"driving"},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2605.27074","title":"IPIBench: Evaluating Interactive Proactive Intelligence of MLLMs under Continuous Streams","created":"2026-05-26","cited_by_count":7,"area":"mllm"},{"id":"2606.10738","title":"Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding","created":"2026-06-09","cited_by_count":7,"area":"mllm"},{"id":"2606.19336","title":"Learning User Simulators with Turing Rewards","created":"2026-06-17","cited_by_count":7,"area":null},{"id":"2606.25041","title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","created":"2026-06-23","cited_by_count":7,"area":null},{"id":"2607.01793","title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","created":"2026-07-02","cited_by_count":7,"area":"agents"},{"id":"2606.26080","title":"Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents","created":"2026-06-24","cited_by_count":6,"area":"lr"},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5,"area":"lr"},{"id":"2605.05413","title":"From History to State: Constant-Context Skill Learning for LLM Agents","created":"2026-05-06","cited_by_count":5,"area":"agents"},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5,"area":"mllm"},{"id":"2606.07229","title":"MMAE: A Massive Multitask Audio Editing Benchmark","created":"2026-06-05","cited_by_count":5,"area":null},{"id":"2606.19073","title":"Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework","created":"2026-06-17","cited_by_count":5,"area":"agents"},{"id":"2608.01078","title":"Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization","created":"2026-08-02","cited_by_count":5,"area":"lr"},{"id":"2608.12486","title":"DIVE: Unlocking Self-Improvement in Frozen Language Models Through Diversity-Driven Skill Evolution","created":"2026-08-12","cited_by_count":5,"area":"synth"},{"id":"2608.18607","title":"VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation","created":"2026-08-19","cited_by_count":5,"area":"alignment"},{"id":"2605.11363","title":"PresentAgent-2: Towards Generalist Multimodal Presentation Agents","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2605.21041","title":"Conditioning Gaussian Processes on Almost Anything","created":"2026-05-20","cited_by_count":4,"area":null},{"id":"2606.01166","title":"BraveGuard: From Open-World Threats to Safer Computer-Use Agents","created":"2026-05-31","cited_by_count":4,"area":"agents"},{"id":"2606.27828","title":"Video-MME-Logical: A Controlled Diagnostic Benchmark for Video Temporal-Logical Reasoning","created":"2026-06-26","cited_by_count":4,"area":"lr"},{"id":"2608.01397","title":"SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space","created":"2026-08-02","cited_by_count":4,"area":"wm"},{"id":"2605.12056","title":"OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2605.20035","title":"Stage-adaptive Token Selection for Efficient Omni-modal LLMs","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2605.27358","title":"MobileMoE: Scaling On-Device Mixture of Experts","created":"2026-05-26","cited_by_count":3,"area":"moe"},{"id":"2605.28192","title":"Agentic Active Omni-Modal Perception for Multi-Hop Audio-Visual Reasoning","created":"2026-05-27","cited_by_count":3,"area":"lr"},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2606.01533","title":"Multi-Agent Computer Use","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2607.00920","title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.20166","title":"Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning","created":"2026-07-22","cited_by_count":3,"area":"lr"},{"id":"2607.28611","title":"Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers","created":"2026-07-30","cited_by_count":3,"area":"diffusion"},{"id":"2608.03812","title":"OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models","created":"2026-08-04","cited_by_count":3,"area":"inference"},{"id":"2609.08977","title":"Multimodal Duplex Interaction Agent","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2609.20784","title":"RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2605.06053","title":"Towards Generation-Efficient Uncertainty Estimation in Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2605.08820","title":"FraudBench: A Multimodal Benchmark for Detecting AI-Generated Fraudulent Refund Evidence","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2605.09640","title":"Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2606.00622","title":"MM-Snowball: Evaluating and Mitigating Hallucination Snowballing in Multimodal Multi-Turn Dialogue","created":"2026-05-30","cited_by_count":2,"area":"mllm"},{"id":"2606.07027","title":"StainFlow: Entity-Stain Tracking and Evidence Linking for Process Rewards in GUI Agents","created":"2026-06-05","cited_by_count":2,"area":"agents"},{"id":"2606.13707","title":"Orchestra-o1: Omnimodal Agent Orchestration","created":"2026-06-10","cited_by_count":2,"area":"agents"},{"id":"2607.03050","title":"OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models","created":"2026-07-03","cited_by_count":2,"area":"inference"},{"id":"2607.08768","title":"UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks","created":"2026-07-09","cited_by_count":2,"area":"mllm"},{"id":"2608.22631","title":"Learning Generalizable Behaviors for Terminal Agents","created":"2026-08-23","cited_by_count":2,"area":"agents"},{"id":"2608.24168","title":"FireRedAudio: A General-Purpose Audio Language Model with Decoupled Continuous Representations for Understanding and Generation","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2608.26005","title":"VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2608.27448","title":"TTPO: Test-Time Policy Optimization","created":"2026-08-27","cited_by_count":2,"area":"lr"},{"id":"2609.25611","title":"Qwen3.8-Omni: Towards Native Omni-Modal Agents","created":"2026-09-22","cited_by_count":2,"area":"agents"},{"id":"2605.07593","title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.08762","title":"Omni-DeepSearch: A Benchmark for Audio-Driven Omni-Modal Deep Search","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.11679","title":"Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion","created":"2026-05-12","cited_by_count":1,"area":"alignment"},{"id":"2605.15764","title":"GRASP: Learning to Ground Social Reasoning in Multi-Person Non-Verbal Interactions","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.16713","title":"GeoWorld-VLM: Geometry from World Models for Vision-Language Models","created":"2026-05-15","cited_by_count":1,"area":"wm"},{"id":"2605.22168","title":"Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2605.28775","title":"Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents","created":"2026-05-27","cited_by_count":1,"area":"agents"},{"id":"2606.01016","title":"PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects","created":"2026-05-31","cited_by_count":1,"area":null},{"id":"2606.04120","title":"SaliMory: Orchestrating Cognitive Memory for Conversational Agents","created":"2026-06-02","cited_by_count":1,"area":"agents"},{"id":"2606.06635","title":"How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.09362","title":"Zero-Shot Semantic Re-Identification for Autonomous Driving: A VLM Baseline Study","created":"2026-06-08","cited_by_count":1,"area":"driving"},{"id":"2606.10147","title":"From Senses to Decisions: The Information Flow of Auditory and Visual Perception in Multimodal LLMs","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2606.11260","title":"RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded Benchmark","created":"2026-06-09","cited_by_count":1,"area":"lr"},{"id":"2606.24255","title":"Social Structure Matters in 3D Human-Human Interaction Generation","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2607.01590","title":"Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.22708","title":"StepX-Edge: An On-Device UI Vision-Language Model via Architecture-Training-Deployment Co-Design","created":"2026-07-20","cited_by_count":1,"area":"mllm"},{"id":"2607.27919","title":"Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory","created":"2026-07-30","cited_by_count":1,"area":"lr"},{"id":"2607.27958","title":"$\\Sigma$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems","created":"2026-07-30","cited_by_count":1,"area":"agents"},{"id":"2608.04355","title":"The Calibration Floor: Format Repair Can Masquerade as Self-Correction at Small-to-Mid Scale","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.10949","title":"StreamFlow: Dynamic Memory Flows for Streaming Video Understanding","created":"2026-08-11","cited_by_count":1,"area":"mllm"},{"id":"2608.23268","title":"Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner","created":"2026-08-24","cited_by_count":1,"area":"lr"},{"id":"2608.29278","title":"Modality Fault Lines: Structural Corruptions Reveal Fragile Omni-Modal Reasoning","created":"2026-08-29","cited_by_count":1,"area":"lr"},{"id":"2609.08275","title":"Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.20791","title":"StageGuard: Learning Stage Transitions for Long-Horizon Robot Tasks via Agentic Distillation","created":"2026-09-17","cited_by_count":1,"area":"agents"},{"id":"2609.21392","title":"Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction","created":"2026-09-18","cited_by_count":1,"area":null},{"id":"2609.23417","title":"Omni2Web: Benchmarking Audiovisual Website Development","created":"2026-09-20","cited_by_count":1,"area":null},{"id":"2609.24058","title":"All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts","created":"2026-09-21","cited_by_count":1,"area":"moe"},{"id":"2605.08974","title":"Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models","created":"2026-05-09","cited_by_count":0,"area":"mllm"},{"id":"2605.18799","title":"ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.22570","title":"VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2605.27038","title":"TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving","created":"2026-05-26","cited_by_count":0,"area":"mllm"},{"id":"2606.09590","title":"Clinically Grounded Privacy Evaluation of Medical LMs","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.12025","title":"Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2606.13768","title":"CineOrchestra: Unified Entity-Centric Conditioning for Cinematic Video Generation","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2606.19965","title":"ROSE: Benchmarking the Perception-to-Action Gap in Multimodal Models","created":"2026-06-18","cited_by_count":0,"area":"mllm"},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.23271","title":"Scaling LLM Knowledge Boundaries via Distribution-Optimized Synthesis","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.26968","title":"RedVox: Safety and Fairness Gaps in Speech Models Across Languages","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.05198","title":"Noisy-Channel Minimum Bayes Risk Decoding","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.05310","title":"Evaluating and Understanding Model Editing for Medical Vision Language Models","created":"2026-07-06","cited_by_count":0,"area":"mllm"},{"id":"2607.08317","title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.10350","title":"ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory","created":"2026-07-11","cited_by_count":0,"area":"agents"},{"id":"2607.12800","title":"UniVR: Thinking in Visual Space for Unified Visual Reasoning","created":"2026-07-14","cited_by_count":0,"area":"lr"},{"id":"2607.16242","title":"TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment","created":"2026-06-26","cited_by_count":0,"area":"alignment"},{"id":"2607.22561","title":"Codifying the Judge: Scalable Evaluation via Program Distillation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.22766","title":"Beyond Shapley: An Influence-Based Data Auditing Pipeline for LLM Alignment and Evaluation","created":"2026-07-24","cited_by_count":0,"area":"alignment"},{"id":"2607.27109","title":"MMAC: A Massive Multi-dimensional Benchmark for Audio Captioning","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2607.29637","title":"CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding","created":"2026-07-31","cited_by_count":0,"area":"mllm"},{"id":"2608.03028","title":"Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning","created":"2026-08-04","cited_by_count":0,"area":"lr"}],"next_cursor":"100"}