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-...
Yi-Cheng Ding, Meng-Yu Wang, Min Zhou et al.· 0 citations
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.
Jin-Chang Zhu, Hao-Lan He, Yi-Cheng Ding et al.· 0 citations
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...
Jin-Chang Zhu, Rong Fu, Yi-Cheng Ding et al.· 1 citation
Results show that learned token-level handoffs can reduce LLM use while preserving strong reasoning performance, and show that learned token-level handoffs can reduce LLM use while preserving strong reasoning performance.