Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models
Yuncheng Yang, Feiyang Ye, Shixian Luo +7
Vision-Language Models (VLMs) have achieved success using homogeneous Transformers to process multimedia data. Recent studies show that heterogeneous structures interleaving effici…
cs.CV2025
PEVLM: Parallel Encoding for Vision-Language Models
Letian Kang, Shixian Luo, Yiqiang Li +5
Vision-Language Models (VLMs) have demonstrated strong capabilities in multimodal understanding and generation tasks. However, their application to long video understanding remains…