We have 5 of 25 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.
An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to improve output quality by sampling multiple generations, but their effectiveness can be limited by randomly selecting where to regenerate. On MATH500 with Qwen2.5-Math-...
Results show that selective anti-interference is an effective objective-level signal for robust context use and identifies locally sufficient tokens and sharply reduces prefix sensitivity on gate-selected suffix tokens.
SCIT, the Suffix Cache Interchange Test, is introduced, a causal protocol that constructs exact source-recipient counterfactuals, patches declared cache segments, and identifies which transformer object carries the counterfactual computation.
GapSight is proposed, a framework for learning visual re-reading: a VLM first takes a global glance, then selectively returns to a free-form region when the question calls for local evidence, and Mechanism analyses show that the router rescues concrete wrong answers, adapts its action rate by task, and forms a favorabl...
ExACT, a supervision-allocation objective that assigns extra weight to long effective-context targets by inverse frequency within the long tail, supports a supervision-centric thesis: long-context adaptation depends on how strongly training supervises long-context predictions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
