← Search

Chiyuan He

2 accepted papers

2025

MINGLE: Mixture of Null-Space Gated Low-Rank Experts for Test-Time Continual Model Merging

NeurIPS 2025poster

Continual model merging integrates independently fine-tuned models sequentially without access to the original training data, offering a scalable and efficient solution for continual learning. However, existing methods face two critical challenges: parameter interference among tasks, which leads to…

Cited by 0SourcecodeScholar
2024

Vision-Sensor Attention Based Continual Multimodal Egocentric Activity Recognition

ICASSP 2024accepted

Continual learning aims to equip deep neural networks (DNNs) with the capability to continuously learn new knowledge without catastrophic forgetting. Currently, there is significant attention on multimodal continual activity recognition from a egocentric perspective. However, the issue of modality i…

Cited by 0SourceScholar