Advancement of Large Vision-Language Models (LVLMs) has enabled comprehension of long and high-resolution multi-modal contexts, but this capability introduces a significant Key-Value (KV) cache memory bottleneck during autoregressive generation. Existing KV cache compression methods typically rely on greedy top-k evict...
Chu-Ming Shen, Wei Wei, Kai-He Xu et al.· Proceedings of the 34th ACM...· 0 citations
Large Multimodal Reasoning Models (LMRMs) have recently shown strong capabilities in complex visual understanding and multi-step inference. However, they remain highly vulnerable to multimodal hallucinations over extended reasoning trajectories. In this work, we study this failure as a state-dynamics problem: as reason...
Xiao-Ye Qu, Yan-Zhe Wu, Zhi-Hao Xie et al.· Proceedings of the 34th ACM...· 0 citations
A novel semantic matching degree estimation method based on ranking consistency that reweights the training paris by measuring the Normalized Discounted Cumulative Gain (NDCG) between its cross-modal and intra-modal retrieval results.
Wei-Ran Pan, Wei Wei· Proceedings of the Thirty-Fi...· 0 citations
This paper proposes PACE, a two-stage framework that progressively expands both the representation and trainable parameter spaces, and introduces Focal Embedding Loss, a confidence-adaptive objective that downweights queries with high positive retrieval confidence while emphasizing ambiguous queries with competitive ne...
Yan-Ping Li, Wei Zhou, Ya-Wen Liu et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.