Get started
Author

Dewen Fan

Observed name: Fan, Dewen
Institution: Kuaishou (China)
Observed institutions: Kuaishou (China), Aibee (China)
OpenAlex ID: A5016757091
EVLM: An Efficient Vision-Language Model for Visual Understanding
2024 · Chen, Kaibing, Shen, Dong, et al. · arXiv (Cornell University) · 30
PDF
Improving Crowded Object Detection via Copy-Paste
2023 · Jiangfan Deng, Dewen Fan, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 18
PDF
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
2026 · Wang, Jiyuan, Ouyang, Huan, et al. · arXiv (Cornell University) · 8
PDF
DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
2026 · Li, Zijun, Zhou, Yimin, et al. · arXiv (Cornell University) · 3
PDF
TextRefine: Improving Textual Fidelity, Spatial Placement, and Glyph Rendering for Text Editing in Product Posters
2026 · Wang, Honglie, Sun, Jia, et al. · arXiv (Cornell University) · 2
PDF
Step Back to Move Forward: Reflection-Aware Preference Optimization for Visual Generation
2026 · Junlong Wu, Jiuzhou Lin, et al. · ACM International Conference on Multimedia (ACM MM) · 1
OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework
2026 · Zeng, Weixuan, Wei, Pengcheng, et al. · arXiv (Cornell University) · 1
PDF
Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
2026 · Jiuzhou Lin, Junlong Wu, et al. · Lecture notes in computer science · 1
PDF
KwaiMind Technical Report
2026 · Zhang, Boheng, Yang, Fan, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count: 64
H-index: 3
I10-index: 2
Year
Topic
Type