4 papers
When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging
Shangge Liu, Yuehan Yin, Yinghuan Shi +2
Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and we…
Understanding and Enforcing Weight Disentanglement in Task Arithmetic
Shangge Liu, Yuehan Yin, Lei Wang +5
Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of ``weig…
Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
Tongxi Wang, Zhuoyang Xia, Xinran Chen +1
Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stabl…
LibContinual: A Comprehensive Library towards Realistic Continual Learning
Wenbin Li, Shangge Liu, Borui Kang +7
A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved wi…