Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
Yuyao Sun, Tao Deng, Shuang Li +1
Multimodal large language models (MLLMs) require substantial computation to process numerous visual tokens across all transformer layers. Most methods for efficient MLLM inference…
cs.CV2025
InternVL-X: Advancing and Accelerating InternVL Series with Efficient Visual Token Compression
Dongchen Lu, Yuyao Sun, Zilu Zhang +4
Most multimodal large language models (MLLMs) treat visual tokens as "a sequence of text", integrating them with text tokens into a large language model (LLM). However, a great qua…