Qingyu Shi

5 papers · 2025–2026 · 4 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 (10) ⭐ Rising Star (5) 👥 Mega-Team · Squad

Venues

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

Top co-authors

Xiangtai Li (5) Yunhai Tong (4) Lu Qi (3) Jinbin Bai (3) Jingbo Wang (2) Haobo Yuan (2) Shilin Xu (2) Jianzong Wu (2) Minghe Gao (1) Kai Chen (1)

Research topics

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

Keywords

diffusion model (3) semantic segmentation (1) image segmentation (1) image generation (1) knowledge distillation (1) image reconstruction (1) instance segmentation (1) flow matching (1) motion transfer (1) real-time processing (1) keypoint matching (1) temporal attention (1) visual tokenizer (1) identity preservation (1) panoptic segmentation (1) feature decoupling (1) video diffusion transformer (1) customized image generation (1) relation generation (1) benchmark (1)

Papers

RecTok: Reconstruction Distillation along Rectified Flow CVPR 2026 Decouple and Track: Benchmarking and Improving Video Diffusion Transformers For Motion Transfer ICCV 2025 DreamRelation: Bridging Customization and Relation Generation CVPR 2025 On Path to Multimodal Generalist: General-Level and General-Bench ICML 2025 RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything ICLR 2025