5 papers
AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs
Yuan Zhang, Chun-Kai Fan, Sicheng Yu +6
Inspired by text prompts in large language models, visual prompts have been explored to enhance the perceptual capabilities of large vision-language models (LVLMs). However, perfor…
SEED: Targeted Data Selection by Weighted Independent Set
Yuan Zhang, Lifeng Guo, Junwen Pan +5
Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this proble…
ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better
Yuan Zhang, Ming Lu, Junwen Pan +4
Recent advances in multimodal reasoning models have demonstrated impressive capabilities across text and vision. However, even leading models exhibit redundant self-reflection when…
SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
Yuan Zhang, Chun-Kai Fan, Junpeng Ma +8
In vision-language models (VLMs), visual tokens usually bear a significant amount of computational overhead despite sparsity of information in them when compared to text tokens. To…
Unveiling the Tapestry of Consistency in Large Vision-Language Models
Yuan Zhang, Fei Xiao, Tao Huang +7
Large vision-language models (LVLMs) have recently achieved rapid progress, exhibiting great perception and reasoning abilities concerning visual information. However, when faced w…