MentalThink: Shaping Thoughts in Mental SVG World
MentalThink enables multimodal large language models to perform visual-symbolic reasoning by generating and interpreting SVG code as an executable intermediate representation for s…
Hugging Face · Daily Papers
·Kangheng Lin, Jisheng Yin
·
·▲ 11 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Kangheng Lin, Jisheng Yin, Dingming Li, En Yu, Yana Wei, Han Zhou
- 11 upvotes da comunidade
- Temas: Multimodal LLMs, think-with-SVG pipeline, scalable vector graphics, SVG code, multi-turn reasoning, Supervised Fine-Tuning
Resumo
Resumo original (em inglês), extraído do paper:
MentalThink enables multimodal large language models to perform visual-symbolic reasoning by generating and interpreting SVG code as an executable intermediate representation for spatial problem-solving.