arxiv:2610.01509
🔄 In a Training Loop
Changdae Oh
changdae
AI & ML interests
Generalization; Distribution Shift; Uncertainty Quantification; Reward Modeling; Post-training
Recent Activity
authored a paper 3 days ago
Sharpening Tax in Post-Training upvoted a paper 3 days ago
Sharpening Tax in Post-Training submitted a paper 3 days ago
Sharpening Tax in Post-TrainingOrganizations
datasets 7
changdae/tau2-uq-artifacts
Viewer • Updated • 2.25M • 523
changdae/vittle-pope-visual-perturbed
Updated • 84
changdae/vittle-llavabench-coco-textual-perturbed
Viewer • Updated • 30 • 34
changdae/vittle-llavabench-coco-joint-perturbed
Viewer • Updated • 90 • 16
changdae/vittle-llavabench-coco-visual-perturbed
Viewer • Updated • 270 • 19
changdae/llavabench-shift-natural-v1
Viewer • Updated • 1.47k • 70
changdae/llavabench-shift-synthetic-v1
Updated • 113