Occam RL: adequate and parsimonious reasoning Collection Local Qwen3.5 GRPO, semantic simplicity and matched length/prompt baselines • 1 item • Updated about 2 hours ago
Grothendieck RLVR Collection Local Qwen/Gemma research on correctness-gated theory building: protocols, manifests, calibration evidence and future adapters. • 7 items • Updated 1 day ago
Grothendieck RLVR Collection Local Qwen/Gemma research on correctness-gated theory building: protocols, manifests, calibration evidence and future adapters. • 7 items • Updated 1 day ago
BurnyCoder/racingmania-specialist-finetune-campaign-05-seed1 Reinforcement Learning • Updated 1 day ago
BurnyCoder/racingmania-specialist-finetune-campaign-04-seed1 Reinforcement Learning • Updated 1 day ago
BurnyCoder/racingmania-specialist-finetune-campaign-03-seed1 Reinforcement Learning • Updated 1 day ago
BurnyCoder/racingmania-specialist-finetune-campaign-02-seed1 Reinforcement Learning • Updated 1 day ago
BurnyCoder/racingmania-specialist-finetune-campaign-01-seed1 Reinforcement Learning • Updated 1 day ago