Tag
A new review in Consciousness and Cognition challenges traditional models of imagination by showing that aphantasia, the inability to form mental images, relies on distributed brain networks rather than a single visual region.
MentalThink introduces a visual-symbolic reasoning paradigm for multimodal LLMs that uses SVG code as intermediate visual representations for multi-turn reasoning. The two-stage training with SFT and RL achieves strong performance on spatial reasoning benchmarks.
MentalThink enables multimodal large language models to perform visual-symbolic reasoning by generating and interpreting SVG code as an intermediate representation for spatial problem-solving.