We have 4 of 19 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.
On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-learning reward is sparse and arrives only once per trajectory. Existing instantiations allocate this guidance by the size of the teacher-student divergence at each step, o...
Aqueous zinc-ion batteries (AZIBs) are regarded as a promising energy storage system due to their high safety and low cost. However, the severe dendritic growth, hydrogen evolution reaction (HER), and interfacial corrosion/passivation of zinc metal anodes, which are coupled failure modes, severely limit their cycle lif...
RankBuffer is introduced, which maintains an ordered, query-specific buffer of previously judged responses as a reusable quality scale that achieves nearly on-par performance with the strongest ranking-based reward baseline while substantially reducing judging cost.
A training-free, Adaptive Visual Token Pruning (AVTP) framework, applicable to diverse LVLM architectures is proposed, and adaptive pruning ratios in multi-image contexts where images of higher importance retain proportionally more tokens are implemented.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
