5 papers
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…
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…
MapViT: A Two-Stage ViT-Based Framework for Real-Time Radio Quality Map Prediction in Dynamic Environments
Cyril Shih-Huan Hsu, Xi Li, Lanfranco Zanzi +3
Recent advancements in mobile and wireless networks are unlocking the full potential of robotic autonomy, enabling robots to take advantage of ultra-low latency, high data throughp…
Mitigating Image Captioning Hallucinations in Vision-Language Models
Fei Zhao, Chengcui Zhang, Runlin Zhang +2
Hallucinations in vision-language models (VLMs) hinder reliability and real-world applicability, usually stemming from distribution shifts between pretraining data and test samples…
Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model
Longrong Yang, Dong Shen, Chaoxiang Cai +4
The Mixture-of-Experts (MoE) has gained increasing attention in studying Large Vision-Language Models (LVLMs). It uses a sparse model to replace the dense model, achieving comparab…