7 papers
Continual Video-MLLM Adaptation over Evolving Domains
Rui Cheng, Meixing Shi, Yuxiang Cai +3
Video multimodal large language models have shown strong capability in video understanding, yet their adaptation to sequentially evolving domains remains underexplored. In real-wor…
Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction
Zengjie Chen, Yuxiang Cai, Jingcai Guo +3
Visual token reduction has emerged as an effective strategy for accelerating Multimodal Large Language Models (MLLMs). Many existing methods prune tokens by ranking text-visual att…
GR4CIL: Gap-compensated Routing for CLIP-based Class Incremental Learning
Tianqi Wang, Jingcai Guo
Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Language-Image Pre-trained (CLIP)…
SRSUPM: Sequential Recommender System Based on User Psychological Motivation
Yicheng Di, Yuan Liu, Zhi Chen +1
Sequential recommender infers users' evolving psychological motivations from historical interactions to recommend the next preferred items. Most existing methods compress recent be…
Fine-Grained Zero-Shot Learning with Attribute-Centric Representations
Zhi Chen, Jingcai Guo, Taotao Cai +1
Recognizing unseen fine-grained categories demands a model that can distinguish subtle visual differences. This is typically achieved by transferring visual-attribute relationships…
SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning
Zhi Chen, Zecheng Zhao, Jingcai Guo +2
Zero-shot learning (ZSL) aims to recognize unseen classes without labeled training examples by leveraging class-level semantic descriptors such as attributes. A fundamental challen…