The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation
Paper • 2609.36484 • Published • 418
Felix Wagner
wagnerfelix
·
AI & ML interests
tensorflow, translation, summarization, time series, datasets
Recent Activity
updated a model 2 days ago
wagnerfelix/mobilevit-multitask-practice published a model 2 days ago
wagnerfelix/mobilevit-multitask-practice liked a dataset 2 days ago
kurehamnm/Chinese_Question_Answering_DatasetOrganizations
None yet