CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
Paper • 2607.25659 • Published • 59
Ferry Li
Ferry30
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 6 hours ago
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization published a dataset about 1 month ago
Ferry30/math updated a dataset about 1 month ago
Ferry30/mathOrganizations
upvoted a paper about 6 hours ago
published a
dataset about 1 month ago
updated a
dataset about 1 month ago
published a
model about 1 year ago
updated a
model about 1 year ago