A VLM-as-a-Judge metric for SVG generation, validated through human correlation studies, and an evaluation of frontier VLMs reveals significant performance gaps, positioning VectorGym as a rigorous framework for advancing visual code generation.
Juan A. Rodriguez, Haotian Zhang, Abhay Puri et al.· arXiv.org· 5 citations· ⚡1
Branch2Skill is introduced, an efficient framework that transforms a single reasoning tree into dense supervision for skill evolution, demonstrating that reasoning trees can support not only more effective trajectory search, but also richer supervision for more efficient skill improvement.
Yanwei Ren, Haotian Zhang, Likang Xiao et al.· 0 citations
LT-MKT first integrates textual information from questions and their associated concepts to construct a Multi-domain Hierarchical Graph, leveraging the advanced representational capabilities of large language models (LLMs) to bridge isolated domains and proposes a novel method incorporating cognitive Load and knowledge Transfer.
Haotian Zhang, Shucun Wang, Jinze Wu 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.