DongGeon Lee

oneonlee's activity

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

liked a model 8 days ago

DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf

Text Generation • 21B • Updated 24 days ago • 127k • 338

updated a dataset 26 days ago

oneonlee/SIUO

Viewer • Updated 26 days ago • 334 • 62

published a dataset 26 days ago

oneonlee/SIUO

Viewer • Updated 26 days ago • 334 • 62

liked a dataset 26 days ago

etri-vilab/holisafe-bench

Viewer • Updated 25 days ago • 4.03k • 280 • 7

upvoted 2 collections about 1 month ago

Qwen3Guard

Collection

7 items • Updated Sep 30 • 59

gpt-oss-safeguard

Collection

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss • 2 items • Updated Oct 29 • 58

liked a dataset about 1 month ago

nvidia/Nemotron-Safety-Guard-Dataset-v3

Viewer • Updated Oct 22 • 387k • 1.02k • 15

liked a model about 1 month ago

nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3

Text Generation • 8B • Updated Oct 28 • 918 • 5

liked a dataset about 1 month ago

ai-safety-institute/AgentHarm

Viewer • Updated Dec 19, 2024 • 468 • 3k • 43

upvoted 2 papers about 2 months ago

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections

Paper • 2510.09023 • Published Oct 10 • 9

Qwen3Guard Technical Report

Paper • 2510.14276 • Published Oct 16 • 14

updated a dataset 3 months ago

oneonlee/Meme-Safety-Bench

Viewer • Updated Sep 3 • 50.8k • 156 • 4

New activity in oneonlee/Meme-Safety-Bench 3 months ago

add mini

#2 opened 3 months ago by

oneonlee

liked a dataset 3 months ago

sinwang/SIUO

Viewer • Updated Jun 8 • 168 • 508 • 7

liked a dataset 4 months ago

Dasool/KoMultiText

Viewer • Updated Aug 22 • 40.4k • 108 • 4

New activity in ChuGyouk/AI-MO-NuminaMath-CoT-Ko 4 months ago

Request: DOI

1

#2 opened 4 months ago by

oneonlee

updated a model 4 months ago

oneonlee/llama-3.1-nemoguard-8b-content-safety-merged

8B • Updated Aug 13 • 4

commented a paper 4 months ago

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

Paper • 2508.03365 • Published Aug 5 • 4 •

2

updated a collection 4 months ago

MemeSafetyBench

Collection

[EMNLP'25] A Benchmark for Assessing VLM Safety with Real-World Memes • 2 items • Updated Sep 9