Changdae Oh

changdae's activity

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

upvoted a paper 3 days ago

MIMESIS: Learning User Simulators as Training Environments for Interactive Agents

Paper • 2610.09484 • Published 5 days ago • 23

upvoted a paper 4 days ago

On-Policy Distillation with Negative-Policy Rollouts

Paper • 2610.07874 • Published 6 days ago • 17

upvoted a paper 5 days ago

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

Paper • 2610.04933 • Published 8 days ago • 17

upvoted a paper 6 days ago

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

Paper • 2610.00531 • Published 12 days ago • 62

upvoted a paper 10 days ago

Sharpening Tax in Post-Training

Paper • 2610.01509 • Published 11 days ago • 111

upvoted a paper 11 days ago

AIM: Agentic Idea Management for Automated Research

Paper • 2609.38445 • Published 13 days ago • 53

upvoted 2 collections 2 months ago

Qwen3.5

Collection

21 items • Updated Mar 9 • 1.8k

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 2 days ago • 105

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 2 collections 3 months ago

Post training

Collection

73 items • Updated 2 days ago • 9

WTF GENIUS PAPERS

Collection

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 454 items • Updated about 19 hours ago • 99

upvoted a collection 4 months ago

Ministral 3 - Additional Checkpoints

Collection

Different formats and Quantized versions of our Ministral 3 family; 14B/8B/3B Instruct/Reasoning GGUF, 3B Instruct ONNX and 14B/8B/3B Instruct BF16. • 10 items • Updated 2 days ago • 33

upvoted 3 papers 4 months ago

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

Paper • 2606.26080 • Published Jun 24 • 13

TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents

Paper • 2602.19633 • Published Feb 23 • 10

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

Paper • 2605.30834 • Published May 29 • 9

upvoted 3 collections 5 months ago

Mistral Small 4

Collection

A state-of-the-art model, open-weight, with a granular Mixture-of-Experts architecture that fuses instruct, reasoning and agentic skills. • 3 items • Updated 2 days ago • 83

Ministral 3

Collection

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 2 days ago • 179

Mistral Medium 3.5

Collection

Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated 2 days ago • 25

upvoted a paper 5 months ago

Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs

Paper • 2605.09063 • Published May 9 • 83