3 papers
cs.CV2026
GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models
Chaoxiang Cai, Minghe Weng, Jie Li +4
With the increase in model parameters and training data, the instruction following and generalization capabilities of Large VisionLanguage Models (LVLMs) have been significantly im…
cs.CV2026
Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
Yibo Jiang, Tao Wu, Rui Jiang +4
Unified Multimodal Models (UMMs) aim to integrate visual understanding and generation within a single structure. However, these models exhibit a notable capability mismatch, where…
cs.CV2025
Long-Tailed Distribution-Aware Router For Mixture-of-Experts in Large Vision-Language Model
Chaoxiang Cai, Longrong Yang, Minghe Weng +3
The mixture-of-experts (MoE) architecture, which replaces dense networks with sparse ones, has attracted significant attention in large vision-language models (LVLMs) for achieving…