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.
SyRuP, a decoding-time framework for improving system-prompt adherence while keeping the base LM frozen, and explicit token-level guidance are introduced, suggest that explicit token-level guidance is an effective and practical mechanism for reliable system-prompt following.
SyRuP is introduced, a decoding-time framework for improving system-prompt adherence while keeping the base LM frozen, and results suggest that explicit token-level guidance is an effective and practical mechanism for reliable system-prompt following.
LookBack, a training-free LVLM response scoring method that augments token likelihood with visual lookback score, a lightweight measure of how strongly each response token refers to image tokens, consistently improves Best-of-$N$ selection over existing baselines with negligible additional overhead.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
