LUFFY is a reinforcement learning framework that bridges the gap between zero-RL and imitation learning by incorporating off-policy reasoning traces into the training process. Built upon GRPO, LUFFY ...
MESA is a powerful and versatile open-source software suite built to allow users to run experiments in stellar evolution. Stellar evolution calculations (i.e., stellar evolution tracks and detailed ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results