We have 3 of 6 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Code large language models acquire programming capabilities from large code corpora, but can also memorize implementations that later require removal. Code unlearning is needed to control their continued reproduction when copyright or security concerns arise. However, targeted and retained code share computational patt...
This work introduces RECAP (REdundancy-aware Credit Assignment via Propagation), which addresses this limitation by assigning credit where it is due based on both a step's downstream role in the reasoning structure and its contribution to solving the problem correctly.
Recoverability-Aware Intervention Learning (RAIL), a training-time framework that learns how to generate rollouts based on the improvement produced by each intervention, consistently improves performance under limited rollout budgets.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
