Unverified50% confidenceFactExact time
On-policy distillation (OPD) has the student model generate its own trajectories, and then the teacher model provides supervision signals on those trajectories.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThis experiment adopts trajectory-level distillation, which belongs to the category of behavioral cloning, directly having the student model imitate the external behavioral sequences of the teacher model.76% similarVerifiedIn offline distillation, training data is generated once by the teacher model and fixed, with the student model learning from a static dataset.71% similarVerifiedDistillation technology enables the student model to learn and reproduce the teacher's multi-step generation trajectory, compressing a generation process of hundreds of steps down to just a few.69% similarUnverifiedModel distillation refers to the process of querying a target model extensively, collecting its input-output pairs, and then training a student model with comparable capabilities.69% similarVerified模型蒸馏是一种将大型教师模型能力迁移到更小学生模型的技术，可能被用于扩散危险能力68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001130API
curl https://kongchang.com/api/v1/knowledge/claims/1001130MCP
get_claim(id=1001130)