diffthinker-multimodal-reasoning

【设计与创意】Apply diffusion models as native generative agents for vision-centric reasoning tasks (sequential planning, constraint satisfaction, spatial configuration) instead of text-based LLM chains. Achieves 3x+ improvements over GPT-5 and Gemini-3 on visual reasoning. Use when image-to-image generation better captures the reasoning constraints than text-base…

独立 GitHub 快照 · 自动分类 · 以原作者文档为准