Xinyan Hu
@xyVickyHu
PhD student @berkeley_ai / @anthropic fellow / LLM safety and interpretability/ worked on econ+ML theory / graduated from @pku1898
649 Following 496 Followers
Interestingly, one attention head can be important across five ICL task families!
Our original thread gave an in-depth mechanistic analysis of addition ICL (quick video recap 👇). We've now generalized this to four more ICL task families, spanning both arithmetic tasks and semantic tasks!
Our paper “Understanding In-context Learning of Addition via Activation Subspaces” has been accepted to COLM 2026! 🎉
See more details in thread.
(1/N)
Show more
Great work @melissapan! Changing your coding agent’s harness can mean very different costs for similar performance.
