11 papers
SAFE-Merge: Data-Free Continual Model Merging with General Knowledge Preservation
Zihuan Qiu, Zhiyang Liao, Chiyuan He +5
Data-free continual model merging must incorporate a stream of specialized models while retaining both pretrained general knowledge and previously acquired tasks, without access to…
Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
Chiyuan He, Zihuan Qiu, Fanman Meng +4
Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cros…
DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition
Chiyuan He, Zihuan Qiu, Fanman Meng +3
Continual learning of vision-language models (VLMs) focuses on leveraging cross-modal pretrained knowledge to incrementally adapt to expanding downstream tasks and datasets, while…
Null-Space Filtering for Data-Free Continual Model Merging: Preserving Stability, Promoting Plasticity
Zihuan Qiu, Lei Wang, Yang Cao +7
Data-free continual model merging (DFCMM) aims to fuse independently fine-tuned models into a single backbone that evolves with incoming tasks without accessing task data. This pap…
SAVA-X: Ego-to-Exo Imitation Error Detection via Scene-Adaptive View Alignment and Bidirectional Cross View Fusion
Xiang Li, Heqian Qiu, Lanxiao Wang +4
Error detection is crucial in industrial training, healthcare, and assembly quality control. Most existing work assumes a single-view setting and cannot handle the practical case w…
MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging
Zihuan Qiu, Yi Xu, Chiyuan He +4
Continual model merging integrates independently fine-tuned models sequentially without access to the original training data, offering a scalable and efficient solution for continu…