2 papers
cs.CL2026
A Circuit for In-Context Learning
Andrew Gao, William Gao
In-context learning (ICL) lets a pretrained language model perform a task specified by demonstrations in its prompt, with no parameter updates. With arbitrary labels the model must…
cs.LG2026
bf16 Rounding Silently Discards Most RL Policy Updates: A Hidden Training-Inference Mismatch and an Unbiased One-Line Fix
Andrew Gao, William Gao
Reinforcement learning (RL) post-training of language models keeps fp32 master weights in the optimizer and serves rollouts from a bf16 copy produced by round-to-nearest conversion…