specific method · filed under post-training
Large-Scale On-Policy Distillation
On-policy distillation trained across all domains using over 40 teacher models.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
As the last stage of post-training, the final full-vocabulary OPD task is trained on datasets from all domains using over 40 teacher models.
usedpost trainingin DeepSeek-V4.1DeepSeek
the final full-vocabulary OPD task is trained on datasets from all domains using over 40 teacher models.
usedpost trainingin DeepSeek-V4.1-FlashDeepSeek
Filed alongside
Other methods under post-training :: policy distillation.
Multi-Teacher On-Policy DistillationOn-Policy DistillationPrefix-Conditioned On-Policy DistillationMulti-Prefix Multi-Teacher On-Policy DistillationSpecialist DistillationAutonomous Student RolloutsOn-Policy Cross-Stage DistillationAsynchronous Multi-Teacher On-Policy DistillationBehavior–Proximal Policy DecouplingDistillation Fine-Tuning on MiMo-Generated DataDistillation for Post-Training Data GenerationIcePop Token-Level Loss MaskingModel DistillationMulti-Objective Policy DistillationOff-Policy DistillationPer-Token On-Policy Distillation RewardSFT–RL–On-Policy Distillation PipelineTeacher-Trajectory and SFT-History Reuse