{"total":56,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47,"area":null},{"id":"2512.09299","title":"VABench: A Comprehensive Benchmark for Audio-Video Generation","created":"2025-12-10","cited_by_count":30,"area":null},{"id":"2512.21094","title":"T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation","created":"2025-12-24","cited_by_count":24,"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":"2604.23632","title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","created":"2026-04-26","cited_by_count":13,"area":"diffusion"},{"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":"2507.20579","title":"AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations","created":"2025-07-28","cited_by_count":8,"area":null},{"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":"2604.11804","title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","created":"2026-04-13","cited_by_count":8,"area":null},{"id":"2510.22994","title":"SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2503.14295","title":"PC-Talk: Precise Facial Animation Control for Audio-Driven Talking Face Generation","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2505.22581","title":"Tell me Habibi, is it Real or Fake?","created":"2025-05-28","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":"2512.24408","title":"DyStream: Streaming Dyadic Talking Heads Generation via Flow Matching-based Autoregressive Model","created":"2025-12-30","cited_by_count":5,"area":"diffusion"},{"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":"2512.01340","title":"EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2508.06511","title":"DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2512.13495","title":"Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation","created":"2025-12-15","cited_by_count":3,"area":null},{"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":"2606.26092","title":"TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy","created":"2026-06-24","cited_by_count":3,"area":null},{"id":"2601.22127","title":"EditYourself: Audio-Driven Generation and Manipulation of Talking Head Videos with Diffusion Transformers","created":"2026-01-29","cited_by_count":2,"area":"diffusion"},{"id":"2604.08405","title":"SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.28056","title":"CogPortrait: Fine-Grained Eye-Region Control in Portrait Animation via Hierarchical Agent Planning","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"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":"2606.11180","title":"Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip Synchronization","created":"2026-06-09","cited_by_count":2,"area":"diffusion"},{"id":"2505.08294","title":"FauForensics: Boosting Audio-Visual Deepfake Detection with Facial Action Units","created":"2025-05-13","cited_by_count":1,"area":null},{"id":"2510.10069","title":"SyncLipMAE: Contrastive Masked Pretraining for Audio-Visual Talking-Face Representation","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2510.10269","title":"VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework","created":"2025-10-11","cited_by_count":1,"area":null},{"id":"2511.08613","title":"Assessing Identity Leakage in Talking Face Generation: Metrics and Evaluation Framework","created":"2025-11-05","cited_by_count":1,"area":null},{"id":"2512.13677","title":"JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.09534","title":"AUHead: Realistic Emotional Talking Head Generation via Action Units Control","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.10542","title":"VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2608.26517","title":"HUG-VIS: A Multimodal Benchmark for Human-centered Understanding and Generation in Visual Intelligence","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2509.21887","title":"StableDub: Taming Diffusion Prior for Generalized and Efficient Visual Dubbing","created":"2025-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2512.02492","title":"YingVideo-MV: Music-Driven Multi-Stage Video Generation","created":"2025-12-02","cited_by_count":0,"area":"diffusion"},{"id":"2512.05126","title":"SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2512.18318","title":"Asynchronous Pipeline Parallelism for Real-Time Multilingual Lip Synchronization in Video Communication Systems","created":"2025-12-20","cited_by_count":0,"area":null},{"id":"2512.20033","title":"FlashLips: 100-FPS Mask-Free Latent Lip-Sync using Reconstruction Instead of Diffusion or GANs","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.03882","title":"UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.09084","title":"SyncEdit: Rethinking Lip Synchronization as Editing with Audio-Driven Diffusion Models","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.11283","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.10334","title":"The Alpha Blending Hypothesis: Compositing Shortcut in Deepfake Detection","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.30230","title":"IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face Generation","created":"2026-05-28","cited_by_count":0,"area":"diffusion"},{"id":"2606.20302","title":"CUPID: Reconstructing UV Texture Maps for Interpretable Person-of-Interest Deepfake Detection","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.22772","title":"LoCC: Detection and Localization of Lip-Syncing Deepfakes via Counterfactual Frame Consistency","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.27779","title":"MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2607.02799","title":"Conversational Human Audio-visual Talking Dialogue Generation","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.09288","title":"DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.18632","title":"VibeAvatar: Aligning Phonetic Kinematics and Human Aesthetics for High-Fidelity Talking Avatar Synthesis","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.29225","title":"ComplexSync: High-Fidelity and Real-Time Lip Sync in Complex Scenarios","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.38019","title":"Beyond Lip Sync: Reference-Grounded Oral Refinement for Audio-Driven Portrait Animation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.06339","title":"BabelFake: A Multilingual Audio-Visual DeepFake Benchmark","created":"2026-10-05","cited_by_count":0,"area":"synth"},{"id":"2610.08417","title":"Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.09223","title":"PVSync: A Unified Lip-Sync Expert for Timing and Articulation","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}