Andrew Lapp's picture

6 2 1

Andrew Lapp

lapp0

·

lapp0

AI & ML interests

Language Models, Reinforcement Learning

Organizations

lapp0's activity

upvoted 2 papers 6 months ago

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published Jun 3 • 43

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

Paper • 2405.19320 • Published May 29 • 9