mz-kim

mz-kim's activity

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

New activity in huggingface/HuggingDiscussions 3 days ago

[FEEDBACK] Daily Papers

🔥❤️ 21

217

#32 opened about 2 years ago by

kramp

submitted 2 papers to Daily Papers 3 days ago

Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models

Paper • 2609.04720 • Published 7 days ago • 4

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

Paper • 2609.04714 • Published 7 days ago • 5

authored 3 papers 3 days ago

Enabling Chatbots with Eyes and Ears: An Immersive Multimodal Conversation System for Dynamic Interactions

Paper • 2506.00421 • Published May 31, 2025 • 5

Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models

Paper • 2609.04720 • Published 7 days ago • 4

Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

Paper • 2609.04714 • Published 7 days ago • 5

updated a dataset 4 days ago

mz-kim/KoNA

Viewer • Updated 4 days ago • 3.1k • 40

published a dataset 4 days ago

mz-kim/KoNA

Viewer • Updated 4 days ago • 3.1k • 40

updated a dataset 15 days ago

MarkrAI/k-overrefusal

Updated 15 days ago • 60 • 1

published a dataset about 2 months ago

MarkrAI/k-overrefusal

Updated 15 days ago • 60 • 1

updated a dataset 2 months ago

MarkrAI/ko-jailbreak

Updated Jul 8 • 38 • 3

published a dataset 2 months ago

MarkrAI/ko-jailbreak

Updated Jul 8 • 38 • 3

updated a model 2 months ago

MarkrAI/ksafeguard-8b

Text Generation • 8B • Updated Jul 3 • 18 • 1

published a model 2 months ago

MarkrAI/ksafeguard-8b

Text Generation • 8B • Updated Jul 3 • 18 • 1