by Keda TAO Papers
3 papers found
HoliTom: Holistic Token Merging for Fast Video Large Language Models
Kele Shao, Keda TAO, Can Qin et al.
NeurIPS 2025oralarXiv:2505.21334
18
citations
Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model
Keda TAO, Jinjin Gu, Yulun Zhang et al.
ICLR 2025posterarXiv:2410.04161
10
citations
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs
Kejia Zhang, Keda TAO, Jiasheng Tang et al.
NeurIPS 2025poster
5
citations