Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Continual Test-Time Learning with Evolution Strategies
Guangya Hao, Yiting Duan, Longyan Tan +5
Large language models increasingly operate in open-ended environments, where they are expected to continually adapt to evolving tasks and distributions, often without access to ext…
cs.LG2026
Representation Drift in Continual Learning: LoRA versus N-gram Memory
Hao Wu
A language model that keeps learning online must not slowly erode its own base capabilities. We ask which part of a modern LLM should absorb continual updates, by measuring how eac…