5 papers
Perception-Consistency Multimodal Large Language Models Reasoning via Caption-Regularized Policy Optimization
Songjun Tu, Qichao Zhang, Jingbo Sun +6
While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: p…
DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection
Guiping Cao, Xiangyuan Lan, Wenjian Huang +3
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g.,…
Harmony: A Unified Framework for Modality Incremental Learning
Yaguang Song, Xiaoshan Yang, Dongmei Jiang +2
Incremental learning aims to enable models to continuously acquire knowledge from evolving data streams while preserving previously learned capabilities. While current research pre…
Learning Compatible Multi-Prize Subnetworks for Asymmetric Retrieval
Yushuai Sun, Zikun Zhou, Dongmei Jiang +4
Asymmetric retrieval is a typical scenario in real-world retrieval systems, where compatible models of varying capacities are deployed on platforms with different resource configur…
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
Zhehan Kan, Ce Zhang, Zihan Liao +7
Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing sig…