PACE-Bench: Benchmarking Physics Adaptation via Code Evolution in Dynamic Environments Paper • 2608.14441 • Published 8 days ago • 27
Open-MOPD: Multi-Teacher Online Policy Distillation Collection Open-MOPD's 3B family: MixSFT initialization, math/code/IF RL teachers, final multi-teacher distilled student, and training/evaluation data. • 6 items • Updated 4 days ago
Open-MOPD: Multi-Teacher On-Policy Distillation Collection Open-MOPD 3B family: MixSFT, math/code/IF RL teachers, the final on-policy-distilled student, and training/evaluation data. • 6 items • Updated 4 days ago • 2