{"total":77,"rows":[{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73,"area":null},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30,"area":null},{"id":"2506.15838","title":"EchoShot: Multi-Shot Portrait Video Generation","created":"2025-06-16","cited_by_count":29,"area":"diffusion"},{"id":"2510.11647","title":"IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment","created":"2025-10-13","cited_by_count":28,"area":null},{"id":"2510.26794","title":"The Quest for Generalizable Motion Generation: Data, Model, and Evaluation","created":"2025-10-30","cited_by_count":22,"area":"diffusion"},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2511.23475","title":"AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement","created":"2025-11-28","cited_by_count":20,"area":null},{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20,"area":null},{"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":"2506.00830","title":"SkyReels-Audio: Omni Audio-Conditioned Talking Portraits in Video Diffusion Transformers","created":"2025-06-01","cited_by_count":14,"area":"diffusion"},{"id":"2507.12956","title":"FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers","created":"2025-07-17","cited_by_count":13,"area":"diffusion"},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.21818","title":"SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2510.14256","title":"Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learning","created":"2025-10-16","cited_by_count":10,"area":null},{"id":"2601.01425","title":"DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer","created":"2026-01-04","cited_by_count":9,"area":"diffusion"},{"id":"2604.23789","title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","created":"2026-04-26","cited_by_count":9,"area":null},{"id":"2506.11144","title":"AlignHuman: Improving Motion and Fidelity via Timestep-Segment Preference Optimization for Audio-Driven Human Animation","created":"2025-06-11","cited_by_count":8,"area":"diffusion"},{"id":"2510.12089","title":"Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback","created":"2025-10-14","cited_by_count":8,"area":"diffusion"},{"id":"2507.04909","title":"HumanVideo-MME: Benchmarking MLLMs for Human-Centric Video Understanding","created":"2025-07-07","cited_by_count":6,"area":"mllm"},{"id":"2507.07202","title":"A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2509.26165","title":"Human-MME: A Holistic Evaluation Benchmark for Human-Centric Multimodal Large Language Models","created":"2025-09-30","cited_by_count":6,"area":"mllm"},{"id":"2605.08729","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","created":"2026-05-09","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":"2509.25731","title":"LaTo: Landmark-tokenized Diffusion Transformer for Fine-grained Human Face Editing","created":"2025-09-30","cited_by_count":5,"area":"diffusion"},{"id":"2512.19546","title":"ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2603.01685","title":"FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2605.24652","title":"AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models","created":"2026-05-23","cited_by_count":5,"area":"alignment"},{"id":"2606.22905","title":"InteractiveAvatar: Real-Time Streaming Video Generation for Consistent and Intent-Aware Avatars","created":"2026-06-22","cited_by_count":5,"area":null},{"id":"2508.17404","title":"MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling","created":"2025-08-24","cited_by_count":4,"area":null},{"id":"2510.18262","title":"UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding","created":"2025-10-21","cited_by_count":4,"area":"mllm"},{"id":"2512.00408","title":"Low-Bitrate Video Compression through Semantic-Conditioned Diffusion","created":"2025-11-29","cited_by_count":4,"area":null},{"id":"2512.08294","title":"OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation","created":"2025-12-09","cited_by_count":4,"area":null},{"id":"2603.18600","title":"Improving Joint Audio-Video Generation with Cross-Modal Context Learning","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2605.25195","title":"Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation","created":"2026-05-24","cited_by_count":4,"area":"diffusion"},{"id":"2607.24731","title":"Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation","created":"2026-07-27","cited_by_count":4,"area":"diffusion"},{"id":"2507.05300","title":"Structured Captions Improve Prompt Adherence in Text-to-Image Models (Re-LAION-Caption 19M)","created":"2025-07-07","cited_by_count":3,"area":null},{"id":"2508.11255","title":"FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation","created":"2025-08-15","cited_by_count":3,"area":"alignment"},{"id":"2511.22553","title":"Bringing Your Portrait to 3D Presence","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2512.14938","title":"TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2604.18326","title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2605.25659","title":"StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2502.08189","title":"AnyCharV: Bootstrap Controllable Character Video Generation with Fine-to-Coarse Guidance","created":"2025-02-12","cited_by_count":2,"area":null},{"id":"2502.20811","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","created":"2025-02-28","cited_by_count":2,"area":"mllm"},{"id":"2508.03050","title":"Multi-human Interactive Talking Dataset","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2511.01450","title":"Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation","created":"2025-11-03","cited_by_count":2,"area":"alignment"},{"id":"2512.13015","title":"What Happens Next? Next Scene Prediction with a Unified Video Model","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2603.01418","title":"UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation","created":"2026-03-02","cited_by_count":2,"area":null},{"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":"2605.26241","title":"RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.03168","title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2607.16742","title":"Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model","created":"2026-07-18","cited_by_count":2,"area":"moe"},{"id":"2512.07951","title":"Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2603.17889","title":"Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2605.29488","title":"AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.20891","title":"Go-with-the-Track: Video Compositing and Motion Control with Point Tracking","created":"2026-06-18","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":"2507.20368","title":"MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation","created":"2025-07-27","cited_by_count":0,"area":null},{"id":"2508.09476","title":"Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2509.01232","title":"FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2601.19406","title":"Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2605.02948","title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2606.24336","title":"TIGER: Taming Identity, Geometry, and Generative Priors for High-Quality Face Video Restoration","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.29473","title":"MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.14595","title":"MagicPrompt: Ultra-Lightweight Prompt Tuning for Video Generation","created":"2026-07-16","cited_by_count":0,"area":"diffusion"},{"id":"2607.23023","title":"OmniMate: Open-Ended Real-Time Streaming Audio-Visual Generation for Interactive Avatars","created":"2026-07-25","cited_by_count":0,"area":"diffusion"},{"id":"2608.16717","title":"PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.31106","title":"DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.04120","title":"BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo Data","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.22069","title":"OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.38748","title":"Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.10047","title":"AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11023","title":"Expression-Diverse References for Identity-Preserving Video Generation","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}