RewardBench 2: Advancing Reward Model Evaluation
Paper • 2506.01937 • Published • 7
AI & ML interests
Fostering the open science of frontier AI.
Recent Activity
View all activity
natolambert
authored 10
papers about 1 month ago
Spurious Rewards: Rethinking Training Signals in RLVR
Paper • 2506.10947 • Published • 2
Generalizing Verifiable Instruction Following
Paper • 2507.02833 • Published • 1
Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
Paper • 2511.01689 • Published • 5
Olmo 3
Paper • 2512.13961 • Published • 40
Meta-Reinforcement Learning with Self-Reflection for Agentic Search
Paper • 2603.11327 • Published • 12
Olmo Hybrid: From Theory to Practice and Back
Paper • 2604.03444 • Published
Tmax: A simple recipe for terminal agents
Paper • 2606.23321 • Published • 17
Learning to Solve Hard Problems in RL for LLMs by Never Giving Up
Paper • 2609.13443 • Published • 15
Context Language Models
Paper • 2609.37725 • Published • 36
natolambert
authored a
paper 7 months ago
natolambert
authored a
paper over 1 year ago
natolambert
authored 8
papers almost 2 years ago
Objective Mismatch in Model-based Reinforcement Learning
Paper • 2002.04523 • Published
Confidence-Building Measures for Artificial Intelligence: Workshop Proceedings
Paper • 2308.00862 • Published
A Survey on Data Selection for Language Models
Paper • 2402.16827 • Published • 4
D2PO: Discriminator-Guided DPO with Response Evaluation Models
Paper • 2405.01511 • Published
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
Paper • 2406.09279 • Published • 3
WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Paper • 2406.18495 • Published • 15
Towards a Framework for Openness in Foundation Models: Proceedings from the Columbia Convening on Openness in Artificial Intelligence
Paper • 2405.15802 • Published
Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models
Paper • 2409.17146 • Published • 123