{"total":122,"rows":[{"id":"2506.18866","title":"OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation","created":"2025-06-23","cited_by_count":83,"area":null},{"id":"2510.09212","title":"Stable Video Infinity: Infinite-Length Video Generation with Error Recycling","created":"2025-10-10","cited_by_count":73,"area":"diffusion"},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69,"area":null},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66,"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":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44,"area":"diffusion"},{"id":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","cited_by_count":41,"area":null},{"id":"2508.09667","title":"GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors","created":"2025-08-13","cited_by_count":38,"area":"diffusion"},{"id":"2503.23307","title":"MoCha: Towards Movie-Grade Talking Character Synthesis","created":"2025-03-30","cited_by_count":31,"area":null},{"id":"2507.03905","title":"EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation","created":"2025-07-05","cited_by_count":29,"area":null},{"id":"2505.21448","title":"OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers","created":"2025-05-27","cited_by_count":27,"area":"diffusion"},{"id":"2506.03099","title":"TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models","created":"2025-06-03","cited_by_count":26,"area":"diffusion"},{"id":"2512.22065","title":"StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars","created":"2025-12-26","cited_by_count":25,"area":"diffusion"},{"id":"2509.09595","title":"Kling-Avatar: Grounding Multimodal Instructions for Cascaded Long-Duration Avatar Animation Synthesis","created":"2025-09-11","cited_by_count":21,"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":"2503.13319","title":"MagicDistillation: Weak-to-Strong Video Distillation for Large-Scale Few-Step Synthesis","created":"2025-03-17","cited_by_count":19,"area":"diffusion"},{"id":"2508.19320","title":"MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation","created":"2025-08-26","cited_by_count":19,"area":null},{"id":"2601.00664","title":"Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation","created":"2026-01-02","cited_by_count":19,"area":null},{"id":"2510.12785","title":"MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars","created":"2025-10-14","cited_by_count":17,"area":"diffusion"},{"id":"2503.05978","title":"MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice","created":"2025-03-07","cited_by_count":16,"area":"diffusion"},{"id":"2505.23525","title":"Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization","created":"2025-05-29","cited_by_count":16,"area":null},{"id":"2506.08003","title":"Audio-Sync Video Generation with Multi-Stream Temporal Control","created":"2025-06-09","cited_by_count":15,"area":null},{"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":"2507.01390","title":"FixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme Cases","created":"2025-07-02","cited_by_count":14,"area":null},{"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":"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":"2504.14373","title":"SEGA: Drivable 3D Gaussian Head Avatar from a Single Image","created":"2025-04-19","cited_by_count":11,"area":null},{"id":"2505.24866","title":"TalkingHeadBench: A Multi-Modal Benchmark & Analysis of Talking-Head DeepFake Detection","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2512.15599","title":"FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision","created":"2025-12-17","cited_by_count":10,"area":null},{"id":"2508.20210","title":"InfinityHuman: Towards Long-Term Audio-Driven Human","created":"2025-08-27","cited_by_count":9,"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":"2506.05806","title":"LLIA -- Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion Models","created":"2025-06-06","cited_by_count":7,"area":"diffusion"},{"id":"2505.15173","title":"AvatarShield: Visual Reinforcement Learning for Human-Centric Synthetic Video Detection","created":"2025-05-21","cited_by_count":6,"area":"lr"},{"id":"2506.19833","title":"Bind-Your-Avatar: Multi-Talking-Character Video Generation with Dynamic 3D-mask-based Embedding Router","created":"2025-06-24","cited_by_count":6,"area":null},{"id":"2603.14331","title":"AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising","created":"2026-03-15","cited_by_count":6,"area":null},{"id":"2505.21724","title":"OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2508.05115","title":"RAP: Real-time Audio-driven Portrait Animation with Video Diffusion Transformer","created":"2025-08-07","cited_by_count":5,"area":"diffusion"},{"id":"2510.08555","title":"VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2512.16900","title":"FlashPortrait: 6x Faster Infinite Portrait Animation with Adaptive Latent Prediction","created":"2025-12-18","cited_by_count":5,"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":"2603.24793","title":"AVControl: Efficient Framework for Training Audio-Visual Controls","created":"2026-03-25","cited_by_count":5,"area":null},{"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":"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":"2602.07449","title":"SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads","created":"2026-02-07","cited_by_count":4,"area":null},{"id":"2604.19679","title":"MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation","created":"2026-04-21","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":"2607.03118","title":"Vidu S1: A Real-Time Interactive Video Generation Model","created":"2026-07-03","cited_by_count":4,"area":null},{"id":"2506.23552","title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","created":"2025-06-30","cited_by_count":3,"area":"diffusion"},{"id":"2508.02944","title":"X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio","created":"2025-08-04","cited_by_count":3,"area":"diffusion"},{"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":"2508.07246","title":"Consistent and Controllable Image Animation with Motion Linear Diffusion Transformers","created":"2025-08-10","cited_by_count":3,"area":"diffusion"},{"id":"2511.06833","title":"ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search","created":"2025-11-10","cited_by_count":3,"area":"diffusion"},{"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":"2602.01538","title":"Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2605.01638","title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","created":"2026-05-02","cited_by_count":3,"area":null},{"id":"2605.17248","title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","created":"2026-05-17","cited_by_count":3,"area":"diffusion"},{"id":"2505.16819","title":"Character-Centered Dialogue Generation from Scene-Level Prompts","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2508.02362","title":"Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2508.03457","title":"READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head Generation","created":"2025-08-05","cited_by_count":2,"area":"diffusion"},{"id":"2509.19965","title":"SynchroRaMa : Lip-Synchronized and Emotion-Aware Talking Face Generation via Multi-Modal Emotion Embedding","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2512.04677","title":"Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length","created":"2025-12-04","cited_by_count":2,"area":"diffusion"},{"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":"2603.01418","title":"UniTalking: A Unified Audio-Video Framework for Talking Portrait Generation","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.26934","title":"Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark","created":"2026-03-27","cited_by_count":2,"area":null},{"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":"2604.19702","title":"Face Anything: 4D Face Reconstruction from Any Image Sequence","created":"2026-04-21","cited_by_count":2,"area":null},{"id":"2604.23586","title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","created":"2026-04-26","cited_by_count":2,"area":"diffusion"},{"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":"2505.22141","title":"FaceEditTalker: Controllable Talking Head Generation with Facial Attribute Editing","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2508.20615","title":"EmoCAST: Emotional Talking Portrait via Emotive Text Description","created":"2025-08-28","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":"2511.22167","title":"IMTalker: Efficient Audio-driven Talking Face Generation with Implicit Motion Transfer","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2512.05991","title":"EmoDiffTalk:Emotion-aware Diffusion for Editable 3D Gaussian Talking Head","created":"2025-11-30","cited_by_count":1,"area":null},{"id":"2512.17773","title":"Pix2NPHM: Learning to Regress NPHM Reconstructions From a Single Image","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2512.20296","title":"TAVID: Text-Driven Audio-Visual Interactive Dialogue Generation","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2602.00702","title":"JoyStreamer: Unlocking Highly Expressive Avatars via Harmonized Text-Audio Conditioning","created":"2026-01-31","cited_by_count":1,"area":null},{"id":"2604.07273","title":"GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos","created":"2026-04-08","cited_by_count":1,"area":"diffusion"},{"id":"2606.10839","title":"HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.13872","title":"Avatar V: Scaling Video-Reference Avatar Video Generation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2608.13602","title":"Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2608.17707","title":"DynaForcing: Overcoming Dynamic Collapse in Self-Forcing Distillation for Streaming Avatar Generation","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2507.03256","title":"MoDA: Multi-modal Diffusion Architecture for Talking Head Generation","created":"2025-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2507.18649","title":"Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching","created":"2025-07-22","cited_by_count":0,"area":"diffusion"},{"id":"2507.20987","title":"JWB-DH-V1: Benchmark for Joint Whole-Body Talking Avatar and Speech Generation Version 1","created":"2025-07-28","cited_by_count":0,"area":"diffusion"},{"id":"2508.08891","title":"Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos","created":"2025-08-12","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":"2512.02492","title":"YingVideo-MV: Music-Driven Multi-Stage Video Generation","created":"2025-12-02","cited_by_count":0,"area":"diffusion"},{"id":"2512.09005","title":"A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2512.13247","title":"STARCaster: Spatio-Temporal AutoRegressive Video Diffusion for Identity- and View-Aware Talking Portraits","created":"2025-12-15","cited_by_count":0,"area":"diffusion"},{"id":"2512.14056","title":"FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling","created":"2025-12-16","cited_by_count":0,"area":"diffusion"},{"id":"2512.16893","title":"Instant Expressive Gaussian Head Avatars at Over 100 FPS","created":"2025-12-18","cited_by_count":0,"area":"diffusion"},{"id":"2512.18772","title":"In-Context Audio Control of Video Diffusion Transformers","created":"2025-12-21","cited_by_count":0,"area":"diffusion"},{"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":"2601.02125","title":"SingingBot: An Avatar-Driven System for Robotic Face Singing Performance","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2603.05506","title":"FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.17427","title":"ECHO: Towards Emotionally Appropriate and Contextually Aware Interactive Head Generation","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.14541","title":"Giving Faces Their Feelings Back: Explicit Emotion Control for Feedforward Single-Image 3D Head Avatars","created":"2026-04-16","cited_by_count":0,"area":null}],"next_cursor":"100"}