activity
20242026
collaborators

13 papers

cs.AI2026

TOPS: First-Principles Visual Token Pruning via Constructing Token Optimal Preservation Sets for Efficient MLLM Inference

Tinghao Wang, Yichen Guo, Rui Huang +11

Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introdu…

cs.CV2025

ZoomV: Temporal Zoom-in for Efficient Long Video Understanding

Junwen Pan, Rui Zhang, Xin Wan +5

Long video understanding poses a fundamental challenge for large video-language models (LVLMs) due to the overwhelming number of frames and the risk of losing essential context thr…

cs.CV2025

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning

Jiajun Cao, Qizhe Zhang, Peidong Jia +11

Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end…

cs.CV2025

TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning

Junwen Pan, Qizhe Zhang, Rui Zhang +5

Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding.…

cs.CV2025

MMG-Vid: Maximizing Marginal Gains at Segment-level and Token-level for Efficient Video LLMs

Junpeng Ma, Qizhe Zhang, Ming Lu +4

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current…

cs.CV2025

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Qizhe Zhang, Mengzhen Liu, Lichen Li +5

In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference c…