{"total":160,"rows":[{"id":"2604.27792","title":"Motubrain: An Advanced World Action Model for Robot Control","created":"2026-04-30","cited_by_count":57,"area":"wm"},{"id":"2606.09811","title":"AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing","created":"2026-06-08","cited_by_count":46,"area":"wm"},{"id":"2605.25874","title":"WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation","created":"2026-05-25","cited_by_count":39,"area":"wm"},{"id":"2606.25473","title":"Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models","created":"2026-06-24","cited_by_count":25,"area":"wm"},{"id":"2605.05204","title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","created":"2026-05-06","cited_by_count":22,"area":"diffusion"},{"id":"2608.04404","title":"Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models","created":"2026-08-05","cited_by_count":17,"area":"wm"},{"id":"2606.14048","title":"WAM4D: Fast 4D World Action Model via Spatial Register Tokens","created":"2026-06-12","cited_by_count":15,"area":"wm"},{"id":"2607.07675","title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","created":"2026-07-08","cited_by_count":15,"area":"moe"},{"id":"2608.27549","title":"Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning","created":"2026-08-27","cited_by_count":14,"area":"lr"},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"id":"2606.09507","title":"Prisma-World: Camera-Controllable Multi-Agent Video World Model","created":"2026-06-08","cited_by_count":11,"area":"wm"},{"id":"2605.12496","title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","created":"2026-05-12","cited_by_count":10,"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":"2606.31672","title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","created":"2026-06-30","cited_by_count":10,"area":"wm"},{"id":"2604.27505","title":"Leveraging Verifier-Based Reinforcement Learning in Image Editing","created":"2026-04-30","cited_by_count":9,"area":"alignment"},{"id":"2605.26244","title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","created":"2026-05-25","cited_by_count":9,"area":null},{"id":"2606.16533","title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","created":"2026-06-15","cited_by_count":9,"area":"wm"},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2605.27589","title":"What-If World: A Causal Benchmark for General World Models in Embodied Scenarios","created":"2026-05-26","cited_by_count":8,"area":"wm"},{"id":"2605.15190","title":"RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO","created":"2026-05-14","cited_by_count":7,"area":"diffusion"},{"id":"2605.25343","title":"Toward Native Multimodal Modeling: A Roadmap","created":"2026-05-25","cited_by_count":7,"area":"wm"},{"id":"2605.27705","title":"AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?","created":"2026-05-26","cited_by_count":7,"area":"agents"},{"id":"2605.30073","title":"Native Audio-Visual Alignment for Generation","created":"2026-05-28","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":"2605.21028","title":"DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation","created":"2026-05-20","cited_by_count":6,"area":null},{"id":"2606.06042","title":"LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2606.09639","title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","created":"2026-06-08","cited_by_count":6,"area":null},{"id":"2606.13432","title":"OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data","created":"2026-06-11","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2607.14189","title":"MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation","created":"2026-07-15","cited_by_count":6,"area":null},{"id":"2607.26754","title":"StatePlay: State-Aware Game World Models for Mechanics-Consistent Generation","created":"2026-07-29","cited_by_count":6,"area":"wm"},{"id":"2608.03974","title":"JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion","created":"2026-08-04","cited_by_count":6,"area":null},{"id":"2608.14530","title":"Marionette: Predicting World States, Rendering Geometry, Painting Appearance","created":"2026-08-14","cited_by_count":6,"area":"wm"},{"id":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2606.02564","title":"VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization","created":"2026-06-01","cited_by_count":5,"area":"lr"},{"id":"2606.14667","title":"Memento: Reconstruct to Remember for Consistent Long Video Generation","created":"2026-06-12","cited_by_count":5,"area":null},{"id":"2607.03964","title":"Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control","created":"2026-07-04","cited_by_count":5,"area":"wm"},{"id":"2607.06401","title":"A Definition and Roadmap for World Models","created":"2026-07-07","cited_by_count":5,"area":"wm"},{"id":"2607.13336","title":"Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization","created":"2026-07-14","cited_by_count":5,"area":null},{"id":"2608.05485","title":"VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing","created":"2026-08-06","cited_by_count":5,"area":"agents"},{"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":"2609.11638","title":"Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation","created":"2026-09-10","cited_by_count":5,"area":null},{"id":"2606.14699","title":"Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control","created":"2026-06-12","cited_by_count":4,"area":"mllm"},{"id":"2606.27374","title":"World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays","created":"2026-06-25","cited_by_count":4,"area":"wm"},{"id":"2607.03118","title":"Vidu S1: A Real-Time Interactive Video Generation Model","created":"2026-07-03","cited_by_count":4,"area":null},{"id":"2607.17097","title":"HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis","created":"2026-07-19","cited_by_count":4,"area":null},{"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":"2608.02603","title":"WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity","created":"2026-08-03","cited_by_count":4,"area":"wm"},{"id":"2608.13049","title":"H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models","created":"2026-08-13","cited_by_count":4,"area":"wm"},{"id":"2608.16859","title":"HarnessEval-W: Agentifying the Evaluation of Visual Worlds","created":"2026-08-17","cited_by_count":4,"area":"wm"},{"id":"2605.26105","title":"On-Policy Adversarial Flow Distillation for Autoregressive Video Generation","created":"2026-05-25","cited_by_count":3,"area":"distill"},{"id":"2606.21982","title":"CoDMD: Copula-aware Distribution Matching Distillation for Fast Video Generation","created":"2026-06-20","cited_by_count":3,"area":"diffusion"},{"id":"2606.23254","title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","created":"2026-06-22","cited_by_count":3,"area":"diffusion"},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.08763","title":"OpenCoF: Learning to Reason Through Video Generation","created":"2026-07-09","cited_by_count":3,"area":"lr"},{"id":"2607.24241","title":"FilmBench: A Film-Grade Benchmark for Cinematic Video Generation","created":"2026-07-27","cited_by_count":3,"area":null},{"id":"2608.19583","title":"VGI-Bench: Probing Visual Intelligence in Video Generation Models","created":"2026-08-20","cited_by_count":3,"area":"lr"},{"id":"2608.25518","title":"Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models","created":"2026-08-26","cited_by_count":3,"area":"wm"},{"id":"2608.27168","title":"Magpie: Real-Time World Renderer for Interactive Games","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2605.14382","title":"Delta Forcing: Trust Region Steering for Interactive Autoregressive Video Generation","created":"2026-05-14","cited_by_count":2,"area":"wm"},{"id":"2605.17488","title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.20476","title":"Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.00499","title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","created":"2026-05-30","cited_by_count":2,"area":"wm"},{"id":"2606.04098","title":"When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.04507","title":"Self-Evolving Deep Research via Joint Generation and Evaluation","created":"2026-06-03","cited_by_count":2,"area":"synth"},{"id":"2606.27826","title":"NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms","created":"2026-06-26","cited_by_count":2,"area":"mllm"},{"id":"2607.20940","title":"Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention","created":"2026-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2607.21553","title":"SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation","created":"2026-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2608.01157","title":"InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2608.09873","title":"Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains","created":"2026-08-10","cited_by_count":2,"area":"lr"},{"id":"2608.10439","title":"Stream Forcing: Constructing Unified Training Trajectory for Robust Streaming Video Generation","created":"2026-08-11","cited_by_count":2,"area":"wm"},{"id":"2608.17566","title":"CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing","created":"2026-08-18","cited_by_count":2,"area":null},{"id":"2608.21839","title":"FIRM-Video: Check Before You Score for Reliable Text-to-Video Reward Modeling","created":"2026-08-22","cited_by_count":2,"area":"alignment"},{"id":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2,"area":null},{"id":"2609.23658","title":"Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms","created":"2026-09-20","cited_by_count":2,"area":"diffusion"},{"id":"2609.36995","title":"Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2605.10218","title":"Relative Score Policy Optimization for Diffusion Language Models","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.25569","title":"ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.14202","title":"KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.16401","title":"Apple-$\\pi$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence","created":"2026-07-17","cited_by_count":1,"area":"wm"},{"id":"2607.23588","title":"JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2607.26818","title":"Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2607.28261","title":"TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.05049","title":"OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.05776","title":"Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification","created":"2026-08-06","cited_by_count":1,"area":"diffusion"},{"id":"2608.12314","title":"StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.14391","title":"Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination","created":"2026-08-14","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":"2609.20414","title":"TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2610.03543","title":"DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2605.02134","title":"Video Generation with Predictive Latents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.03652","title":"AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2605.07800","title":"SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models","created":"2026-05-08","cited_by_count":0,"area":"diffusion"},{"id":"2605.19995","title":"CogOmniControl: Reasoning-Driven Controllable Video Generation via Creative Intent Cognition","created":"2026-05-19","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":"2606.01285","title":"Knowledge-Intensive Video Generation","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.04811","title":"Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.11838","title":"Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph Grounding","created":"2026-06-10","cited_by_count":0,"area":"alignment"},{"id":"2606.21337","title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2606.23643","title":"TailorMind: Towards Preference-Aligned Multimodal Content Generation","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":"100"}