{"total":15,"rows":[{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236,"area":"diffusion"},{"id":"2602.24289","title":"Mode Seeking meets Mean Seeking for Fast Long Video Generation","created":"2026-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2510.08318","title":"LinVideo: A Post-Training Framework towards O(n) Attention in Efficient Video Generation","created":"2025-10-09","cited_by_count":11,"area":"diffusion"},{"id":"2512.21734","title":"Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation","created":"2025-12-25","cited_by_count":11,"area":"diffusion"},{"id":"2512.23379","title":"SoulX-FlashTalk: Real-Time Infinite Streaming of Audio-Driven Avatars via Self-Correcting Bidirectional Distillation","created":"2025-12-29","cited_by_count":10,"area":"diffusion"},{"id":"2511.21780","title":"3MDiT: Unified Tri-Modal Diffusion Transformer for Text-Driven Synchronized Audio-Video Generation","created":"2025-11-26","cited_by_count":5,"area":"diffusion"},{"id":"2512.03034","title":"MAViD: A Multimodal Framework for Audio-Visual Dialogue Understanding and Generation","created":"2025-12-02","cited_by_count":4,"area":"diffusion"},{"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":"2604.19636","title":"CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation","created":"2026-04-21","cited_by_count":3,"area":"diffusion"},{"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":"2604.28126","title":"AdvDMD: Adversarial Reward Meets DMD For High-Quality Few-Step Generation","created":"2026-04-29","cited_by_count":1,"area":"diffusion"},{"id":"2605.11424","title":"VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors","created":"2026-05-12","cited_by_count":1,"area":"diffusion"},{"id":"2607.09581","title":"Wan-Dancer: A Hierarchical Framework for Minute-scale Coherent Music-to-Dance Generation","created":"2026-07-10","cited_by_count":1,"area":"diffusion"},{"id":"2606.30849","title":"SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2608.02474","title":"EchoCache: Energy-Guided Cross-Modal Caching for Efficient Audio-Driven Video Generation","created":"2026-08-03","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}