Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
🔄
In a Training Loop
Changdae Oh
changdae
6
44
17
Follow
youngandbin's profile picture
j-jaehui's profile picture
YoungXuan's profile picture
6 followers
·
5 following
https://changdaeoh.github.io/
Changdae_Oh
changdaeoh
changdae-oh-440587215
changdaeoh.bsky.social
AI & ML interests
Generalization; Distribution Shift; Uncertainty Quantification; Reward Modeling; Post-training
Recent Activity
upvoted
a
paper
about 4 hours ago
On-Policy Distillation with Negative-Policy Rollouts
upvoted
a
paper
1 day ago
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
upvoted
a
paper
2 days ago
Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers
View all activity
Organizations
changdae
's datasets
7
Sort:Â Recently updated
changdae/tau2-uq-artifacts
Viewer
•
Updated
Sep 2
•
2.25M
•
590
changdae/vittle-pope-visual-perturbed
Updated
Apr 10
•
115
changdae/vittle-llavabench-coco-textual-perturbed
Viewer
•
Updated
Apr 10
•
30
•
76
changdae/vittle-llavabench-coco-joint-perturbed
Viewer
•
Updated
Apr 10
•
90
•
63
changdae/vittle-llavabench-coco-visual-perturbed
Viewer
•
Updated
Apr 10
•
270
•
133
changdae/llavabench-shift-natural-v1
Viewer
•
Updated
May 26, 2025
•
1.47k
•
66
changdae/llavabench-shift-synthetic-v1
Updated
May 26, 2025
•
113