Termsslug: multi-teacher-on-policy-distillation

Multi-Teacher On-Policy Distillation

多教师同策略蒸馏

Merging multiple specialist teacher models into one student by distilling on the student's own sampled trajectories.

Curated Intelligence

1 items · Page 1/1
Rohan Paul (@rohanpaul_ai)T2·Models
88 pts
Ant Group Open-Sources 560B Medical MoE Model LingSante-3.1-flash

Ant Group has open-sourced LingSante-3.1-flash, a 560B-parameter medical MoE model with 25B activations per token, releasing weights on Hugging Face under an MIT license. It outperforms GPT-6 Astra, Claude Opus 5.5 and Gemini 4 Argon on HealthBench Professional, HLE, BrowseComp and EHR-Complex. The recipe mixes medical and general data from pretraining onward, trains medical reasoning, tool use, search and clinician-style behavior as separate skills with their own RL rewards, then merges the specialists via multi-teacher on-policy distillation.