I am currently studying for a bachelor’s degree in Xidian University.
My research interest includes:
- Multi-modal models
- Efficient AI
- Image Restoration
🎓 Educations
- 2021.9 - 2025.6, School of Communication Engineering, Xidian University, Xian China.
📝 Publications
English
Keda Tao, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan cheng. Overcoming False Illusions in Blind Face Restoration with Multi-Modal Guided Diffusion Model. ICLR, 2025. (Spotlight)
[Github]
Keda Tao, Can Qin, Haoxuan Yu, Yang Sui, Huan Wang. DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models. CVPR, 2025.
[Github]
- Xiucheng Wang*,
Keda Tao*, Nan Cheng, Zhisheng Yin, Zan Li, Yuan Zhang, Xuemin (Sherman) Shen. RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction. TCCN, 2024.
Keda Tao, Haoxuan Yu, Yang Sui, Can Qin, Huan Wang. Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models. arXiv, 2025.
[Github]
- Kejia Zhang,
Keda Tao, Jiasheng Tang, Huan Wang. Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs. arXiv, 2025.
[Github]
🏭 Internships
- 2023.05 - 2024.05, UNIC Lab, Xidian University, China.
- 2024.06 - now, ENCODE Lab, Westlake University, China.
