Unverified50% confidenceFactExact time
The core design of MTA-OPSD is to construct a multi-teacher pool of candidate teachers and let each token adaptively select its preferred teacher during training.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMTA-OPSD transforms the teacher selection problem in self-distillation into a token-level dynamic routing problem, where the teacher is no longer a static hyperparameter but a variable that changes with training state and token context.73% similarUnverifiedThe paper "Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation" points out that existing OPSD methods assume the teacher is fixed, and this assumption has fundamental limitations.66% similarUnverifiedThe paper categorizes existing OPSD approaches into two types: one where the teacher is fixed throughout training and has access to the full reference; the other where the teacher is unchanged within each response but adaptively varies across responses in the degree of exposure to partial reference.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115271API
curl https://kongchang.com/api/v1/knowledge/claims/1115271MCP
get_claim(id=1115271)