ChartSync is introduced, an expert-validated benchmark constructed via a programmatic rendering pipeline that guarantees deterministic visuo-logical coupling for the ground truth and deconstructs failure paradigms to identify core meta-abilities for guiding future multimodal architectures.
Jiakang Yu, Yixuan Chai, Tianci Wang et al.· arXiv.org· 1 citation
EvoThink is proposed, a framework that reduces redundant verification and encourages the exploration of new reasoning paths that not only substantially reduces inference-time token usage but also improves the reasoning capability of LRMs.
Xinbang Dai, Zheyu Xin, Hui-Kang Hu et al.· arXiv.org· 0 citations
Compilable Academic Document Parsing (CADP) is proposed, a paradigm that reconstructs a full page as contextual \LaTeX{} plus executable Python, so that structure-preserving elements and executable chart representations can be reconstructed, recompiled, and directly verified against the source page.
Rihui Jin, Jun Wang, Chen Zhu 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.