Changdae Oh

changdae's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 3 days ago

Harness^2: Recursive Agent Harnessing for an Open World

Paper • 2610.14224 • Published 9 days ago • 105

upvoted 2 papers 9 days ago

MIMESIS: Learning User Simulators as Training Environments for Interactive Agents

Paper • 2610.09484 • Published 11 days ago • 30

On-Policy Distillation with Negative-Policy Rollouts

Paper • 2610.07874 • Published 12 days ago • 21

upvoted a paper 10 days ago

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

Paper • 2610.04933 • Published 14 days ago • 17

upvoted a paper 11 days ago

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

Paper • 2610.00531 • Published 18 days ago • 62

authored a paper 15 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 17 days ago • 111

upvoted a paper 15 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 17 days ago • 111

submitted a paper to Daily Papers 15 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 17 days ago • 111

upvoted a paper 16 days ago

AIM: Agentic Idea Management for Automated Research

Paper • 2609.38445 • Published 19 days ago • 53

updated a dataset about 1 month ago

changdae/tau2-uq-artifacts

Viewer • Updated Sep 2 • 2.25M • 695

upvoted a collection 2 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.81k

liked a model 3 months ago

mistralai/Mistral-Large-3-675B-Base-2512

Updated Dec 3, 2025 • 118 • 55

upvoted a collection 3 months ago

Mistral Large 3

Collection

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated 3 days ago • 106

liked a model 3 months ago

thinkingmachines/Inkling

Image-Text-to-Text • 952B • Updated Jul 23 • 1.32M • • 1.82k

upvoted 2 papers 3 months ago

Tracing Agentic Failure from the Flow of Success

Paper • 2607.12747 • Published Jul 14 • 17

Multi-Agent LLMs Fail to Explore Each Other

Paper • 2607.11250 • Published Jul 13 • 15

upvoted a collection 3 months ago

Post training

Collection

74 items • Updated 1 day ago • 9

liked a model 3 months ago

nvidia/Nemotron-Research-Reasoning-Qwen-1.5B

Text Generation • 2B • Updated Nov 21, 2025 • 1.17k • • 247

authored 2 papers 4 months ago

Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring

Paper • 2605.30834 • Published May 29 • 9

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents

Paper • 2606.26080 • Published Jun 24 • 13