Test-Time Inverse Scaling in Audio LLMs
Published:
Chain-of-thought reasoning helps text LLMs but hurts Audio LLMs. This post explains why — and how process rewards fix it. Read more
Blog
2025
The Exploration-Exploitation Dilemma in RLHF for Generative Models
Published:
A deep dive into why fixed regularization in RLHF leads to diversity collapse, and how adaptive sample-level control resolves the exploration-exploitation dilemma. Read more