Keda Tao
Scholar

Keda Tao

Google Scholar ID: ek8xaLUAAAAJ
Westlake University
Generative ModelComputer VisionMLLM
Google Scholar↗
Citations & Impact
All-time
Citations
118
 
H-index
5
 
i10-index
4
 
Publications
13
 
Co-authors
16
list available
Contact
No contact links provided.
Publications
15 items
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs
2026
Cited
0
OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video Understanding
2025
Cited
0
StreamingAssistant: Efficient Visual Token Pruning for Accelerating Online Video Understanding
2025
Cited
0
OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models
2025
Cited
0
StreamingTOM: Streaming Token Compression for Efficient Video Understanding
2025
Cited
0
Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
2025
Cited
0
Revisiting MLLM Token Technology through the Lens of Classical Visual Coding
2025
Cited
0
TARS: MinMax Token-Adaptive Preference Strategy for Hallucination Reduction in MLLMs
2025
Cited
0
Resume (English only)
Co-authors
16 total
Huan Wang
Huan Wang
Westlake University
Xiucheng Wang
Xiucheng Wang
Xidian University
Can Qin
Can Qin
Salesforce
Yang Sui
Yang Sui
Postdoc, Rice University
Haoxuan You
Haoxuan You
Apple AI/ML
Nan Cheng (承楠)
Nan Cheng (承楠)
Professor, School of Telecomm. Engineering, Xidian University
Zhisheng Yin
Zhisheng Yin
Xi'dian University, Harbin Institute of Technology, BBCR (18-19), University of Waterloo
Xuemin (Sherman) Shen
Xuemin (Sherman) Shen
University Professor, University of Waterloo