Parallel decoding speeds up masked diffusion language models by writing several tokens per forward pass. Published commit rules choose these tokens by testing the predicted distributions. Under sampling the written tokens are drawn, and these tests do not see them. We find that answer quality follows the reliability of...
Yan-Chao Li, Yu-Su Zhang, Jia-Qing Xie et al.· 0 citations
Protein-protein interactions underpin nearly all biological processes. Yet, designing proteins with desired interactions remains challenging due to the structural complexity governing molecular recognition. This study views protein design as a search optimization problem over a combinatorial sequence space under expens...
Fang Wu, Hong-Bin Lin, Bing-Chen Duan et al.· 0 citations
This work introduces Equivariant Neural Primal-Dual Assignment (ENPDA), which learns a shared matching policy and applies it to new pairs without further training, answering queries roughly three orders of magnitude faster and recovering its training cost after a few dozen queries.
Jia-Qing Xie, Yan-Chao Li, Zhuo Yang et al.· 0 citations
This work introduces RACER, a training-free closed-loop controller that continuously shrinks uncertain forecasts toward the last computed feature and derives a deterministic error bound for the shrinkage and empirically evaluates its validity and tightness across acceleration regimes.
Yan-Chao Li, Jia-Qing Xie, Ben Gao et al.· 1 citation
This work establishes a question-level audit under fixed budgets, temperatures, and answer formats, and asks why reachable answers sometimes fail to appear, and test whether inference-time layer routing can expand reachability.
Yan-Chao Li, Wan-Hao Liu, Jia-Qing Xie et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.