We have 4 of 18 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.
Block diffusion accelerates speculative decoding by drafting multiple tokens in one forward pass. However, each position predicts a marginal distribution without observing earlier proposed tokens, limiting draft quality and acceptance length. We identify a concrete failure, the \emph{repetition trap}, in which neighbor...
Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked diffusion language models divide these responsibilities across four editing interfaces: whole-file rewriting, search-and-replace, locate-then-infill, and token-level editing. Experi...
Findings show that a skill document can serve as the starting point for a continuous control that improves both answers and actions without updating the backbone.
RedEvoAgent is proposed, a black-box red-teaming agent that distills cross-case attack trajectories into a concise, human-readable attack skill that outperforms fixed and agentic baselines, improves tool efficiency, and transfers across attacker models and target execution harnesses.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
