Kaihui Cheng

5 papers · 2025–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze ⭐ Rising Star (5)

Venues

CVPR (3) AAAI (1) ICLR (1)

Top co-authors

Siyu Zhu (5) Hui Li (4) Jingdong Wang (4) Yao Yao (2) Shan Mu (2) Hanlin Shang (2) Yun Zhan (2) Jiahao Cui (2) Hang Zhou (2) Jun Wang (1)

Research topics

Deep Learning (5) Models (5) Computer Vision (2) Generation (2) Interdisciplinary (1) Machine Learning (1) Architectures (1) Core Methods (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Science (1) Techniques (1)

Keywords

diffusion model (3) portrait animation (2) video generation (2) motion capture (1) protein structure prediction (1) molecular dynamics (1) latent diffusion (1) video diffusion (1) diffusion transformer (1) exposure bia (1) conformational dynamics (1) skeleton sequence (1) audio-driven synthesis (1) facial identity (1) human-centric video (1) structural prediction (1) 4d modeling (1) dynamic protein structure (1) protein trajectory (1) class-conditional image generation (1)

Papers

MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture CVPR 2026 4D Diffusion for Dynamic Protein Structure Prediction with Reference and Motion Guidance AAAI 2025 Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation ICLR 2025 Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer CVPR 2025 OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation CVPR 2025