Changdae Oh's picture

In a Training Loop 🔄

Changdae Oh

changdae

·

https://changdaeoh.github.io/

AI & ML interests

Distribution Shift; Uncertainty Quantification

Recent Activity

upvoted an article 2 days ago

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

upvoted a paper 7 days ago

UniGame: Turning a Unified Multimodal Model Into Its Own Adversary

liked a model 15 days ago

Qwen/Qwen3.5-27B

View all activity

Organizations

liked 2 models 15 days ago

Qwen/Qwen3.5-27B

Image-Text-to-Text • 28B • Updated 16 days ago • 1.1M • • 658

Qwen/Qwen3.5-35B-A3B

Image-Text-to-Text • 36B • Updated 14 days ago • 1.46M • • 1.09k

liked a model about 1 year ago

royokong/e5-v

Image-Text-to-Text • 8B • Updated Dec 10, 2025 • 15.4k • 31

liked a dataset about 1 year ago

liuhaotian/LLaVA-Instruct-150K

Preview • Updated Jan 3, 2024 • 3.75k • 578

liked a model about 1 year ago

xtuner/llava-llama-3-8b-v1_1-transformers

Image-Text-to-Text • 8B • Updated Apr 28, 2024 • 3.77k • 82