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
Vision2Code is introduced, a multi-domain, reference-code-free benchmark containing 539 test examples from 15 different datasets, spanning charts and plots, geometry, graphs, scientific diagrams, documents and 3D spatial scenes, which highlights the variability across domains of existing image-to-code generation models...