Mickel Liu

mickelliu's activity

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

upvoted a paper 10 days ago

SPADE: Self-Play in Adaptive Synthetic Executable Environments

Paper • 2608.19197 • Published 11 days ago • 51

liked a dataset 4 months ago

nvidia/Nemotron-Safety-Guard-Dataset-v3

Viewer • Updated Feb 3 • 515k • 1.55k • 33

liked a model 5 months ago

HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive

9B • Updated Jun 5 • 796k • 1.97k

updated a collection 10 months ago

Self-RedTeam

Collection

Code: https://github.com/mickelliu/selfplay-redteaming Paper: https://arxiv.org/pdf/2506.07468 • 3 items • Updated Oct 21, 2025

published 3 models 10 months ago

mickelliu/Self-RedTeam-Qwen2.5-14B-Instruct

15B • Updated Oct 21, 2025

mickelliu/Self-RedTeam-Qwen2.5-7B-Instruct

8B • Updated Oct 21, 2025 • 5

mickelliu/Self-RedTeam-Qwen2.5-3B-Instruct

3B • Updated Oct 21, 2025

updated 3 models 10 months ago

mickelliu/Self-RedTeam-Qwen2.5-7B-Instruct

8B • Updated Oct 21, 2025 • 5

mickelliu/Self-RedTeam-Qwen2.5-14B-Instruct

15B • Updated Oct 21, 2025

mickelliu/Self-RedTeam-Qwen2.5-3B-Instruct

3B • Updated Oct 21, 2025

liked 2 datasets about 1 year ago

allenai/IFBench_multi-turn

Viewer • Updated Jul 3, 2025 • 3.16k • 471 • 12

walledai/StrongREJECT

Viewer • Updated Oct 18, 2024 • 313 • 3.47k • 23

liked a model over 1 year ago

alisawuffles/roberta-large-wanli

Text Classification • 0.4B • Updated Jun 14, 2023 • 3.92k • • 10

liked a dataset over 1 year ago

ServiceNow-AI/R1-Distill-SFT

Viewer • Updated Feb 8, 2025 • 1.85M • 1.3k • 323

liked a model over 2 years ago

allenai/tulu-2-7b

Text Generation • Updated Apr 30, 2024 • 8.46k • • 11

upvoted a paper almost 3 years ago

Safe RLHF: Safe Reinforcement Learning from Human Feedback

Paper • 2310.12773 • Published Oct 19, 2023 • 28

authored a paper almost 3 years ago

Safe RLHF: Safe Reinforcement Learning from Human Feedback

Paper • 2310.12773 • Published Oct 19, 2023 • 28

updated a dataset almost 3 years ago

PKU-Alignment/BeaverTails

Viewer • Updated Oct 17, 2023 • 364k • 17.1k • 111

liked a dataset almost 3 years ago

nampdn-ai/tiny-codes

Viewer • Updated Sep 30, 2023 • 1.63M • 2.51k • 300