Self-Play Pretraining with Zero Data https://arxiv.org/abs/2609.30063 https://www.alphaxiv.org/ru/abs/2609.30063 https://github.com/nourya-aliz/self_play_pretraining
Self-Play Pretraining with Zero Data https://arxiv.org/abs/2609.30063…
0 viewsОткрыть в Telegram →
Из этого канала
- #7207https://huggingface.co/datasets/XiaomiMiMo/MiMo-V2.6-RL-oss
https://huggingface.co/datasets/XiaomiMiMo/MiMo-V2.6-RL-oss
- #7204https://github.com/itzik123/ClashRoyaleAi
https://github.com/itzik123/ClashRoyaleAi
- #7201https://cameronrwolfe.substack.com/p/llm-rl
https://cameronrwolfe.substack.com/p/llm-rl
- #7200https://contrastive-lm.notion.site/ https://github.com/Contrastive-LM/CLM
https://contrastive-lm.notion.site/ https://github.com/Contrastive-LM/CLM