Kavli Affiliate: Yi Zhou | First 5 Authors: Pengbo Hu, Ji Qi, Xingyu Li, Hong Li, Xinqi Wang | Summary: There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-based planning, provides flexibility in problem solving and […]
Continue.. Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning