Quanwei Yang

5 papers · 2024–2025 · 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 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

CVPR (2) ICCV (2) NeurIPS (1)

Top co-authors

Kaisiyuan Wang (4) Hang Zhou (4) Haocheng Feng (4) Errui Ding (3) Hongtao Xie (3) Jingdong Wang (3) Jiazhi Guan (3) Yingying Li (3) Lingyun Yu (3) Shengyi He (2)

Research topics

Computer Vision (4) Deep Learning (4) Generation (4) Models (3) Analysis (2) Architectures (2) Core AI · Computer Vision (2) Artificial Intelligence (1) Machine Learning (1) Application Areas (1) Core AI · Artificial Intelligence (1) Learning Types (1) Processing (1)

Keywords

video generation (3) diffusion transformer (2) human video synthesis (2) human video generation (2) diffusion model (2) mixture of expert (1) gesture synthesis (1) retrieval-augmented generation (1) temporal consistency (1) hand-object interaction (1) lip synchronization (1) image forensics (1) gesture generation (1) co-speech gesture (1) synthetic image detection (1) audio-driven generation (1) human body movement (1) gesture dynamics (1) holistic human video (1) video reenactment (1)

Papers

AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers CVPR 2025 Forensic-MoE: Exploring Comprehensive Synthetic Image Detection Traces with Mixture of Experts ICCV 2025 GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation ICCV 2025 Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model CVPR 2025 ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling NeurIPS 2024