https://m2po.notion.site/rl-stale-m2po Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs? https://arxiv.org/abs/2510.01161 https://github.com/Infini-AI-Lab/M2PO
https://m2po.notion.site/rl-stale-m2po Prosperity before Collapse: How Far Can…
0 viewsОткрыть в Telegram →
Из этого канала
- #4883Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training…
Reinforce-Ada: An Adaptive Sampling Framework for Reinforce-Style LLM Training https://arxiv.org/abs/2510.04996v1
- #4884A History of Large Language Models…
A History of Large Language Models https://gregorygundersen.com/blog/2025/10/01/large-language-models/
- #4885Parallel-R1: Towards Parallel Thinking via Reinforcement Learning…
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning https://arxiv.org/abs/2509.07980 https://github.com/zhengkid/Parallel-R1
- #4877https://huggingface.co/docs/trl/main/en/lorawithoutregret в trl завезли
https://huggingface.co/docs/trl/main/en/lorawithoutregret в trl завезли
- #4875Optimal Scaling Needs Optimal Norm https://arxiv.org/abs/2510.03871
Optimal Scaling Needs Optimal Norm https://arxiv.org/abs/2510.03871