A new method to align AI responses with human preferences efficiently.
― 5 min read
Wei Shen
A novel approach to reward over-optimization in language models using uncertainty estimation.
― 6 min read
Researchers present a fresh approach to aligning vast bacterial DNA sequences.
― 6 min read
A novel method combines language models and knowledge graphs to improve robot safety.
― 6 min read
PosFormer improves recognition of handwritten math expressions using position information.
― 5 min read
LongRecipe improves language models' understanding of long texts efficiently.
― 5 min read
PF-PPO enhances language models by filtering out unreliable rewards for better code responses.
― 5 min read
A new program boosts HbA1c testing quality in primary care settings.
― 6 min read
A new method improves accuracy in searching for individuals based on descriptions.
― 6 min read