{"total":44,"rows":[{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2511.03334","title":"UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions","created":"2025-11-05","cited_by_count":38,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"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":"2512.13313","title":"KlingAvatar 2.0 Technical Report","created":"2025-12-15","cited_by_count":13,"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":"2510.01186","title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","created":"2025-10-01","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":"2605.26486","title":"LongCat-Video-Avatar 1.5 Technical Report","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2512.19546","title":"ActAvatar: Temporally-Aware Precise Action Control for Talking Avatars","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2511.19065","title":"Understanding, Accelerating, and Improving MeanFlow Training","created":"2025-11-24","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":"2607.03118","title":"Vidu S1: A Real-Time Interactive Video Generation Model","created":"2026-07-03","cited_by_count":4,"area":null},{"id":"2512.11423","title":"JoyStreamer-Flash: Real-time and Infinite Audio-Driven Avatar Generation with Autoregressive Diffusion","created":"2025-12-12","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":"2512.14938","title":"TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation","created":"2025-12-16","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":"2605.25659","title":"StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2606.30019","title":"OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2512.21736","title":"SyncAnyone: Implicit Disentanglement via Progressive Self-Correction for Lip-Syncing in the wild","created":"2025-12-25","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","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":"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":"2602.00702","title":"JoyStreamer: Unlocking Highly Expressive Avatars via Harmonized Text-Audio Conditioning","created":"2026-01-31","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":"2602.13185","title":"FlexAM: Flexible Appearance-Motion Decomposition for Versatile Video Generation Control","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2603.23132","title":"InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2607.01222","title":"Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2607.24013","title":"AptAvatar: Fast and Vivid Long-Form Audio-Driven Video Generation for Production-Ready Avatars","created":"2026-07-27","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":"2602.03570","title":"Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.13669","title":"EchoTorrent: Towards Swift, Sustained, and Streaming Multi-Modal Video Generation","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2604.09057","title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.27918","title":"Generate Your Talking Avatar from Video Reference","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2607.24359","title":"TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.00079","title":"LeapTalk: Breaking the Latency-Quality Trade-off in Talking Head Generation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.10720","title":"Ex-Omni-2D: Expressive Omni-Modal Dialogue Models with Native Visual Presence","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.15818","title":"FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streams","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.16220","title":"SingDance: Compositional Zero-Shot Singing-and-Dancing Video Generation with Role-Aware Audio Conditioning","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":"2609.13830","title":"DiVA: Enabling Interactive Digital Life Simulation via Video Models","created":"2026-09-12","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":"2609.26117","title":"Vorch-Human: Unified Multi-Task Human-Centric Generation via Long-Horizon Continuation","created":"2026-08-06","cited_by_count":0,"area":null}],"next_cursor":null}