2 citations · 2 across the 4 of their papers we have counts for
7 papers
CART: Compatible Routing for Multimodal Continual Instruction Tuning
Ling-Xiang Zhang, Tao Hu, Da-Wei Zhou
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world applications often require them to continually acquire new capabiliti…
ReCAP: Retrieval-Guided Capability Reuse for Multimodal Continual Instruction Tuning
Tao Hu, Zhinuo Zhou, Xialiang Tong +2
Multimodal continual instruction tuning (MCIT) aims to enable multimodal large language models to acquire new capabilities from sequential tasks while preserving previously learned…
Visual Branch is What You Need for CLIP-based Class-Incremental Learning
Tao Hu, Zhen-Hao Xie, Jingcai Guo +2
Class-Incremental Learning (CIL) requires models to recognize new classes over time without forgetting previously learned ones. With the rise of vision-language pre-training, CLIP…
InterSketch: An Interleaved Reasoning Model with Self-correcting Visual Sketch and Stepwise Reward
Zhiwei Ning, Wenwen Tong, Xiangli Kong +12
While vision-language models (VLMs) have exhibited multi-turn visual reasoning capabilities, their reasoning trajectories remain relatively shallow and are dominated by a text-cent…
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
Tao Hu, Da-Wei Zhou
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across seque…
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…
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…