OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation
Paper • 2610.02781 • Published • 15
Chengzhi Hu
ChangeXy
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy Distillation updated a model about 1 year ago
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter0-1ep updated a model about 1 year ago
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter1-1epOrganizations
None yet
upvoted a paper 1 day ago
updated 6
models about 1 year ago
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter0-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter1-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter3-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter4-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter5-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter2-1ep
Updated
published 6
models about 1 year ago
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter2-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter1-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter0-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter5-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter4-1ep
Updated
ChangeXy/ppl-bad_medical_advice_rephrased_5iter_iter3-1ep
Updated
updated 5
models about 1 year ago
ChangeXy/ppl-risky_financial_advice_rephrased_5iter_iter2-1ep
Updated
ChangeXy/ppl-risky_financial_advice_rephrased_5iter_iter3-1ep
Updated
ChangeXy/ppl-risky_financial_advice_rephrased_5iter_iter4-1ep
Updated
ChangeXy/ppl-risky_financial_advice_rephrased_5iter_iter5-1ep
Updated
ChangeXy/ppl-risky_financial_advice_rephrased_5iter_iter1-1ep
Updated
published 2
models about 1 year ago