{"total":57,"rows":[{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"id":"2511.13853","title":"Can World Simulators Reason? Gen-ViRe: A Generative Visual Reasoning Benchmark","created":"2025-11-17","cited_by_count":19,"area":"lr"},{"id":"2606.00793","title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","created":"2026-05-30","cited_by_count":18,"area":"wm"},{"id":"2509.24427","title":"UI2V-Bench: An Understanding-based Image-to-video Generation Benchmark","created":"2025-09-29","cited_by_count":11,"area":"diffusion"},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2605.20183","title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","created":"2026-05-19","cited_by_count":10,"area":null},{"id":"2606.10804","title":"SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning","created":"2026-06-09","cited_by_count":8,"area":null},{"id":"2510.26412","title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2512.02942","title":"Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench","created":"2025-12-02","cited_by_count":7,"area":null},{"id":"2606.08091","title":"VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation","created":"2026-06-06","cited_by_count":7,"area":"agents"},{"id":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6,"area":"agents"},{"id":"2605.15199","title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","created":"2026-05-14","cited_by_count":6,"area":null},{"id":"2605.26525","title":"ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2505.24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2601.21716","title":"DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning","created":"2026-01-29","cited_by_count":5,"area":null},{"id":"2603.08403","title":"SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents","created":"2026-03-09","cited_by_count":5,"area":null},{"id":"2512.05969","title":"Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices","created":"2025-11-02","cited_by_count":4,"area":null},{"id":"2605.07079","title":"Learning Visual Feature-Based World Models via Residual Latent Action","created":"2026-05-08","cited_by_count":4,"area":"wm"},{"id":"2605.28035","title":"MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2605.30090","title":"DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2608.16859","title":"HarnessEval-W: Agentifying the Evaluation of Visual Worlds","created":"2026-08-17","cited_by_count":4,"area":"wm"},{"id":"2512.25066","title":"From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping","created":"2025-12-31","cited_by_count":3,"area":null},{"id":"2602.01623","title":"Omni-Judge: Can Omni-LLMs Serve as Human-Aligned Judges for Text-Conditioned Audio-Video Generation?","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2604.20157","title":"HumanScore: Benchmarking Human Motions in Generated Videos","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2606.07435","title":"The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2510.08398","title":"VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?","created":"2025-10-09","cited_by_count":2,"area":"wm"},{"id":"2603.04727","title":"Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild","created":"2026-03-05","cited_by_count":2,"area":"mllm"},{"id":"2604.19193","title":"How Far Are Video Models from True Multimodal Reasoning?","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2608.22751","title":"Risk-Aware Reranking for Agentic Tool Retrieval","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2606.24256","title":"Trimming the Long-Tail of Visual World Modeling Evaluation","created":"2026-06-23","cited_by_count":1,"area":"wm"},{"id":"2606.28757","title":"A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models","created":"2026-06-27","cited_by_count":1,"area":"wm"},{"id":"2606.30026","title":"MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.01499","title":"Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.28022","title":"Flux-OPD: On-Policy Distillation with Evolving Contexts","created":"2026-07-30","cited_by_count":1,"area":"distill"},{"id":"2608.06732","title":"From Cheap Fakes to Pure Synthesis: Addressing the New Era of T2V Fake News Videos","created":"2026-08-07","cited_by_count":1,"area":null},{"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":"2610.01499","title":"VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2509.25998","title":"VRWKV-Editor: Reducing quadratic complexity in transformer-based video editing","created":"2025-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2601.19236","title":"VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2606.05665","title":"V2V-Bench: A Comprehensive Benchmark for Video-to-Video Generation Evaluation","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.21146","title":"ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization","created":"2026-06-19","cited_by_count":0,"area":"diffusion"},{"id":"2606.30248","title":"Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2608.09111","title":"RAVEN-Eval: Rubric-Guided Automatic Evaluation for AI Video Generation Models Based on LMM Preference Judgement","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.13990","title":"Content Depth Matters in Short-Video Recommendation: Rethinking the Attention Economy","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2608.21425","title":"Aligning Human Sense: Calibrated Distributional Reward Learning for Video Generation","created":"2026-08-16","cited_by_count":0,"area":"alignment"},{"id":"2608.28694","title":"SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video Generation","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.00646","title":"DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03153","title":"VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement","created":"2026-09-02","cited_by_count":0,"area":"wm"},{"id":"2609.16878","title":"VOR-Bench: A Human Perception-Driven Benchmark for Video Object Removal","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2609.30595","title":"Action Forcing: Training World Models on Unsupervised Video by Recovering Underlying Egomotion Bases","created":"2026-09-24","cited_by_count":0,"area":"wm"},{"id":"2609.32460","title":"REMEDY: How Far Is Video Generation from Medical Education World Models?","created":"2026-09-26","cited_by_count":0,"area":"wm"},{"id":"2609.36598","title":"Beyond Legibility: Benchmarking Visual Text Rendering and In-Place Editing in Unified Video Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39147","title":"MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01052","title":"Towards Subject Consistency over Dynamic Subject Sets in Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.15452","title":"EmoTrace-Bench: Diagnosing Emotional Expression in Text-to-Video Generation through Controlled Cues and Intensity","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19823","title":"PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20571","title":"Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}