2 papers
cs.LG2026
On-Policy Replay for Continual Supervised Fine-Tuning
Yan Chen, Taojie Zhu, Meng Zhang +4
Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting…
cs.LG2026
In-context superposition: human-like working memory interference in large language models
Hua-Dong Xiong, Li Ji-An, Jiaqi Huang +3
Intelligent systems must maintain and manipulate task-relevant information online to adapt to dynamic environments. This capacity, known as working memory, is fundamental to human…