RL Excursions during Pretraining: How early is too early for On-policy Learning? https://rl-excursions.github.io/
RL Excursions during Pretraining: How early is too early for On-policy…
0 viewsОткрыть в Telegram →
Из этого канала
- #6043Small Reward Models via Backward Inference https://arxiv.org/abs/2602.13551…
Small Reward Models via Backward Inference https://arxiv.org/abs/2602.13551 https://www.alphaxiv.org/ru/overview/2602.13551
- #6044Operationalising the Superficial Alignment Hypothesis via Task Complexity…
Operationalising the Superficial Alignment Hypothesis via Task Complexity https://arxiv.org/abs/2602.15829 https://www.alphaxiv.org/ru/overview/2602.15829
- #6045@tokareviv мне кажется надо отдельный блок vibecoding создавать
@tokareviv мне кажется надо отдельный блок vibecoding создавать
- #6041https://github.com/Shekswess/tiny-reasoning-language-model
https://github.com/Shekswess/tiny-reasoning-language-model
- #6040https://www.liquid.ai/research/lfm-1b-math-can-small-models-be-concise-reasoners
https://www.liquid.ai/research/lfm-1b-math-can-small-models-be-concise-reasoners