collaborators

7 papers

cs.CV2026

CoT-Edit: Let CoT Guide Instruction Video Editing

Sen Liang, Fengbin Guan, Youliang Zhang +2

Text-driven instruction-based video editing in complex scenes remains challenging: purely textual prompts often fail to capture precise spatial relationships and physical constrain…

cs.CV2026

Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing

Sen Liang, Cong Wang, Zhentao Yu +8

Existing instruction-based video editing datasets commonly focus on single-task appearance editing, failing to meet the complex creative demands of real-world scenarios. To bridge…

cs.CV2026

SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing

Sen Liang, Cong Wang, Fengbin Guan +6

Visual and acoustic events in the physical world are inherently coupled, yet existing video editing methods typically adopt decoupled pipelines, lacking bidirectional modality inte…

cs.CV2026

Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

Youliang Zhang, Zhengguang Zhou, Zhentao Yu +11

Generating talking avatars is a fundamental task in video generation. Although existing methods can generate full-body talking avatars with simple human motion, extending this task…

cs.CV2025

HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters

Yi Chen, Sen Liang, Zixiang Zhou +6

Recent years have witnessed significant progress in audio-driven human animation. However, critical challenges remain in (i) generating highly dynamic videos while preserving chara…

cs.CV2025

OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation

Sen Liang, Zhentao Yu, Zhengguang Zhou +8

The emergence of Diffusion Transformers (DiT) has brought significant advancements to video generation, especially in text-to-video and image-to-video tasks. Although video generat…