-
Beyond Log Likelihood: Probability-Based Objectives for Supervised Fine-Tuning across the Model Capability Continuum
Paper • 2510.00526 • Published • 11 -
gaotang/figlet_font
Viewer • Updated • 45k • 13 -
gaotang/medical_sft_processed
Viewer • Updated • 23.5k • 48 -
gaotang/numina-cot-subset-67k
Viewer • Updated • 67.6k • 31
Gaotang Li
gaotang
AI & ML interests
None yet
Recent Activity
commentedon a paper about 13 hours ago
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards upvoted a paper 4 days ago
Code as Agent Harness authored a paper 9 days ago
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable RewardsOrganizations
None yet