Keda Tao

23 papers A* 2Journal 20Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
A Survey of Token Compression for Efficient Multimodal Large Language Models.
Trans. Mach. Learn. Res.
Kele Shao, Keda Tao, Kejia Zhang, Sicheng Feng, Mu Cai, Yuzhang Shang, Haoxuan You, Can Qin, Yang Sui, Huan Wang
2026 J jnl
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs.
CoRR
Keda Tao, Yuhua Zheng, Xu Jia, Wenjie Du, Kele Shao, Hesong Wang, Xueyi Chen, Xin Jin, Junhan Zhu, Bohan Yu, Weiqiang Wang, Jian Liu, Can Qin, Yulun Zhang, Ming-Hsuan Yang, Huan Wang
2025 A* conf
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models.
CVPR
Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang
2025 J jnl
HoliTom: Holistic Token Merging for Fast Video Large Language Models.
CoRR
Kele Shao, Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang
2025 J jnl
OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding.
CoRR
Keda Tao, Wenjie Du, Bohan Yu, Weiqiang Wang, Jian Liu, Huan Wang
2025 J jnl
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models.
CoRR
Keda Tao, Kele Shao, Bohan Yu, Weiqiang Wang, Jian Liu, Huan Wang
2025 A* conf
Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model.
ICLR
Keda Tao, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan Cheng
2025 J jnl
PhotoArtAgent: Intelligent Photo Retouching with Language Model-Based Artist Agents.
CoRR
Haoyu Chen, Keda Tao, Yizao Wang, Xinlei Wang, Lei Zhu, Jinjin Gu
2025 J jnl
Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models.
CoRR
Keda Tao, Haoxuan You, Yang Sui, Can Qin, Huan Wang
2025 J jnl
Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs.
CoRR
Kejia Zhang, Keda Tao, Jiasheng Tang, Huan Wang
2025 — conf
RadioDiff-Turbo: Lightweight Generative Large Electromagnetic Model for Wireless Digital Twin Construction.
INFOCOM WKSHPS
Xiucheng Wang, Peilin Zheng, Nan Cheng, Ruijin Sun, Junting Chen, Keda Tao, Zhisheng Yin, Zhiquan Liu, Yong Zeng
2025 J jnl
RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction.
IEEE Trans. Cogn. Commun. Netw.
Xiucheng Wang, Keda Tao, Nan Cheng, Zhisheng Yin, Zan Li, Yuan Zhang, Xuemin Shen
2025 J jnl
Revisiting MLLM Token Technology through the Lens of Classical Visual Coding.
CoRR
Jinming Liu, Junyan Lin, Yuntao Wei, Kele Shao, Keda Tao, Jianguo Huang, Xudong Yang, Zhibo Chen, Huan Wang, Xin Jin
2025 J jnl
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding.
CoRR
Xinqi Jin, Hanxun Yu, Bohan Yu, Kebin Liu, Jian Liu, Keda Tao, Yixuan Pei, Huan Wang, Fan Dang, Jiangchuan Liu, Weiqiang Wang
2025 J jnl
StreamingTOM: Streaming Token Compression for Efficient Video Understanding.
CoRR
Xueyi Chen, Keda Tao, Kele Shao, Huan Wang
2025 J jnl
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs.
CoRR
Kejia Zhang, Keda Tao, Zhiming Luo, Chang Liu, Jiasheng Tang, Huan Wang
2025 J jnl
When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios.
CoRR
Kele Shao, Keda Tao, Kejia Zhang, Sicheng Feng, Mu Cai, Yuzhang Shang, Haoxuan You, Can Qin, Yang Sui, Huan Wang
2025 J jnl
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression.
CoRR
Wenjie Du, Li Jiang, Keda Tao, Xue Liu, Huan Wang
2024 J jnl
DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models.
CoRR
Keda Tao, Can Qin, Haoxuan You, Yang Sui, Huan Wang
2024 J jnl
Is Oracle Pruning the True Oracle?
CoRR
Sicheng Feng, Keda Tao, Huan Wang
2024 J jnl
Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model.
CoRR
Keda Tao, Jinjin Gu, Yulun Zhang, Xiucheng Wang, Nan Cheng
2024 J jnl
RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction.
CoRR
Xiucheng Wang, Keda Tao, Nan Cheng, Zhisheng Yin, Zan Li, Yuan Zhang, Xuemin Shen
2024 J jnl
Transductive zero-shot learning with generative model-driven structure alignment.
Pattern Recognit.
Yang Liu, Keda Tao, Tianhui Tian, Xinbo Gao, Jungong Han, Ling Shao