10 papers
Group Preference Collapse in Personalized Multimodal Large Language Models
Fan Lyu, Wenqi Zhang, Joost van de Weijer
Personalized multimodal large language models (MLLMs) aim to generate user-specific responses, but existing methods mainly rely on profile-level information and overlook diverse us…
DeCLIP: Decoupled Prompting for Multi-Label Class-Incremental Learning with CLIP
Kaile Du, Zihan Ye, Junzhou Xie +7
Multi-label class-incremental learning (MLCIL) continuously expands the label space while recognizing multiple co-occurring categories, making catastrophic forgetting a central cha…
Variational Continual Test-Time Adaptation
Fan Lyu, Kaile Du, Yuyang Li +5
Continual Test-Time Adaptation (CTTA) task investigates effective domain adaptation under the scenario of continuous domain shifts during testing time. Due to the utilization of so…
Annotation-Efficient Active Test-Time Adaptation with Conformal Prediction
Tingyu Shi, Fan Lyu, Shaoliang Peng
Active Test-Time Adaptation (ATTA) improves model robustness under domain shift by selectively querying human annotations at deployment, but existing methods use heuristic uncertai…
MM-Prompt: Cross-Modal Prompt Tuning for Continual Visual Question Answering
Xu Li, Fan Lyu
Continual Visual Question Answering (CVQA) based on pre-trained models(PTMs) has achieved promising progress by leveraging prompt tuning to enable continual multi-modal learning. H…
Rebalancing Multi-Label Class-Incremental Learning
Kaile Du, Yifan Zhou, Fan Lyu +5
Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledg…