arxiv:2606.26080
🔄 In a Training Loop
Changdae Oh
changdae
AI & ML interests
Generalization; Distribution Shift; Uncertainty Quantification; Reward Modeling; Post-training
Recent Activity
upvoted a paper 3 days ago
Tracing Agentic Failure from the Flow of Success upvoted a paper 4 days ago
Multi-Agent LLMs Fail to Explore Each Other upvoted a collection 8 days ago
Post training Organizations
datasets 7
changdae/tau2-uq-artifacts
Viewer • Updated • 2.26M • 100
changdae/vittle-pope-visual-perturbed
Updated • 17
changdae/vittle-llavabench-coco-textual-perturbed
Viewer • Updated • 30 • 56
changdae/vittle-llavabench-coco-joint-perturbed
Viewer • Updated • 90 • 37
changdae/vittle-llavabench-coco-visual-perturbed
Viewer • Updated • 270 • 23
changdae/llavabench-shift-natural-v1
Viewer • Updated • 1.47k • 141
changdae/llavabench-shift-synthetic-v1
Updated • 268