artifacts referenced in the talk timeline! Slides: https://docs.google.com/presentation/d/1quMyI4BAx4rvcDfk8jjv063bmHg4RxZd9mhQloXpMn0/edit?usp=sharin
Nathan Lambert
natolambert
AI & ML interests
Reinforcement learning, Ethics, Robotics, Dynamics Models
Recent Activity
authored a paper 8 days ago
RewardBench 2: Advancing Reward Model Evaluation authored a paper 8 days ago
Spurious Rewards: Rethinking Training Signals in RLVR authored a paper 8 days ago
Generalizing Verifiable Instruction FollowingOrganizations
artifacts referenced in the talk timeline! Slides: https://docs.google.com/presentation/d/1quMyI4BAx4rvcDfk8jjv063bmHg4RxZd9mhQloXpMn0/edit?usp=sharin
Models & datasets mentioned in the bottom section of posts!
UNMAINTAINED: See RewardBench... A place to collect reward models, an often not released artifact of RLHF.
Models & datasets mentioned in the bottom section of posts!