4 papers
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
Shuhan Xue, Jianyuan Zhong, Ziyuan Nan +10
We introduce and release ScienceBuddy, an interactive scientific research workspace that brings continually improving scientific agents into researchers' everyday workflows. Scienc…
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…
Harness Continual Learning: Continual Adaptation Beyond Model Parameters
Borui Kang, Jinrui Gu, Junhan Lv +3
Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of…
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…