Abstract: While reinforcement learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of ...
DR Tulu-8B is the first open Deep Research (DR) model trained for long-form DR tasks. DR Tulu-8B matches OpenAI DR on long-form DR benchmarks. Feburary 9, 2026: š„ We released a free interactive demo ...
Abstract: The widespread use of large language models (LLMs) has brought about security risks, including biases, discrimination, and ethical concerns. Reinforcement Learning from Human Feedback (RLHF) ...
To address data selection for RLVR post-training, LearnAlign is proposedāutilizing "gradient alignment" as a representativeness metric and "success rate $V(\xi)=p(1 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results