3 papers
cs.CV2025
VEGAS: Mitigating Hallucinations in Large Vision-Language Models via Vision-Encoder Attention Guided Adaptive Steering
Zihu Wang, Boxun Xu, Yuxuan Xia +1
Large vision-language models (LVLMs) exhibit impressive ability to jointly reason over visual and textual inputs. However, they often produce outputs that are linguistically fluent…
cs.CV2025
AMS-KV: Adaptive KV Caching in Multi-Scale Visual Autoregressive Transformers
Boxun Xu, Yu Wang, Zihu Wang +1
Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs)…
cs.LG2025
Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives
Zihu Wang, Boxun Xu, Hejia Geng +1
Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two…