DAPS, a dependency-aware premise selector with a structural neighborhood encoder, a group-level contrastive objective, and a Mathlib-then-Blueprint adaptation procedure is introduced, and experiments demonstrate that DAPS premises improve theorem proving on miniF2F and IMO-ProofBench.
Zi-Xuan Chen, Wen-Yuan Jiang, Jun-Ling Wang et al.· 0 citations
BACKGROUND
The approximate number system (ANS) is foundational for mathematical development, but its characteristics and neural mechanisms in children with autism spectrum disorder (ASD) remain unclear. While mathematical difficulties are common in ASD, whether nonsymbolic numerosity processing deficits contribute and...
Verifiable rewards improve language models through reliable task-level feedback, but methods based on Group Relative Policy Optimization (GRPO) apply a sequence-level advantage uniformly across all tokens. This coarse credit assignment reinforces or penalizes entire responses without identifying which local decisions t...
Hai-Jiang Li, Cheng-Yue Lv, Yi Zhang 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.