7 papers
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
Lan Li, Tao Hu, Da-Wei Zhou +3
Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transfe…
ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning
Yu-Cheng Shi, Zhen-Hao Xie, Jun-Tao Tang +1
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire new vision-language c…
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
Jun-Tao Tang, Zhen-Hao Xie, Yu-Cheng Shi +1
Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-world deployment demands con…
Restoring Initial Noise Sensitivity in Text-to-Image Distillation via Geometric Alignment
Huayang Huang, Ruoyu Wang, Jinhui Zhao +5
Generative distillation significantly accelerates text-to-image (T2I) generation by compressing multi-step trajectories into few-step student models while preserving perceptual qua…
C3Box: A CLIP-based Class-Incremental Learning Toolbox
Hao Sun, Da-Wei Zhou
Traditional machine learning systems are typically designed for static data distributions, which suffer from catastrophic forgetting when learning from evolving data streams. Class…
Hierarchical Semantic Tree Anchoring for CLIP-Based Class-Incremental Learning
Tao Hu, Lan Li, Zhen-Hao Xie +1
Class-Incremental Learning (CIL) enables models to learn new classes continually while preserving past knowledge. Recently, vision-language models like CLIP offer transferable feat…