Kavli Affiliate: Zhiting Tian | First 5 Authors: Hanlin Zhu, Hanlin Zhu, , , | Summary: Previous work shows that the chain of continuous thought (continuous CoT) improves the reasoning capability of large language models (LLMs) by enabling implicit parallel thinking, and a subsequent work provided theoretical insight by showing that a two-layer transformer equipped […]
Continue.. Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought