新的TOPS方法剪枝视觉令牌以实现高效的MLLM推理

报道来源 [3]

1. arXiv cs.AI TIER_1 English(EN) · Tinghao Wang, Yichen Guo, Rui Huang, Zheng Lu, Qizhe Zhang, Chenxi Li, Yuan Zhang, Jiajun Cao, Zhirong Shen, Yaosong Du, Guangyan Gan, Wenya Wang, Lin William Cong, Shanghang Zhang · 2026-06-26 04:00

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

   arXiv:2606.27161v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead. Visual token…

2. arXiv cs.AI TIER_1 English(EN) · Shanghang Zhang · 2026-06-25 15:29

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

   Multimodal large language models (MLLMs) have achieved strong multimodal reasoning capabilities, but their efficiency is limited by the large number of visual tokens, which introduces substantial computational overhead. Visual token pruning offers a natural solution, yet existing…

3. 雷峰网 (Leiphone) TIER_1 中文(ZH) · 2026-06-25 06:45

   GAIR Paper 106 | Tracking the Evolutionary Trajectory of Visual Tokens for Lossless Compression and 60% Inference Acceleration | CVPR 2026

   <section style="text-align: center; margin: 0px 16px; line-height: 1.75em; display: block;"><img class="rich_pages wxw-img" src="https://static.leiphone.com/uploads/new/images/20260625/6a3ccdfdecdb8.jpg?imageMogr2/quality/90" style="width: 100%; display: inline-block; text-align:…