Topic: entropy

A new study proposes using entropy-based guidance to enhance diversity in text generation via diffusion models, addressing the challenge of achieving similar control in discrete, sequential text as seen in image synthesis. This matters because it could significantly improve the versatility and usability of text diffusion models across various applications.

arxiv.org↗

A study proposes using entropy-based pruning to compress Chain-of-Thought reasoning in large language models without significant accuracy loss, highlighting its potential for making complex models more efficient.

arxiv.org↗