Gaojie Lin

5 papers · 2025–2025 · 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 ↓

+1 more ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) ⭐ Rising Star (5) 🏆 Keyword Champion (2)

⚡ Prolific Year · Productive

Venues

CVPR (2) ICLR (2) ICCV (1)

Top co-authors

Jiaqi Yang (5) Chao Liang (5) Jianwen Jiang (5) Tianyun Zhong (4) Zerong Zheng (2) Yanbo Zheng (2) Zhengkun Rong (1) Yongming Zhu (1) yuan zhang (1) Zhou Zhao (1)

Research topics

Computer Vision (5) Deep Learning (5) Generation (5) Models (3) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Techniques (2) Application Areas (1) Domain-Specific (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1)

Keywords

video generation (3) audio-driven generation (3) diffusion model (2) human animation (2) model compression (2) portrait animation (1) u-net architecture (1) motion generation (1) mobile device (1) real-time inference (1) video diffusion (1) zero-shot generation (1) diffusion transformer (1) facial expression (1) talking avatar (1) portrait generation (1) identity consistency (1) portrait avatar (1) audio-driven avatar (1) image distillation (1)

Papers

CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation ICLR 2025 FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillation CVPR 2025 Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency ICLR 2025 MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices CVPR 2025 OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models ICCV 2025