Mingyi Hong PRO

Mingyi-Hong's activity

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

upvoted a paper about 18 hours ago

Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training

Paper • 2607.01232 • Published 5 days ago • 2

New activity in OptimAI-Lab/TOFU-forget10_RULE-NPO about 1 month ago

Add library_name, pipeline_tag and link to code

#1 opened about 1 month ago by

nielsr

updated a collection about 1 month ago

BLUR

Collection

This is official model collection for paper "BLUR: A Bi-Level Optimization Approach for LLM Unlearning" • 4 items • Updated May 26

updated a model about 1 month ago

OptimAI-Lab/BLUR-RMU_WMDP

Text Generation • 7B • Updated May 26 • 1

published a model about 1 month ago

OptimAI-Lab/BLUR-RMU_WMDP

Text Generation • 7B • Updated May 26 • 1

updated a model about 1 month ago

OptimAI-Lab/BLUR-NPO_MUSE-Books

7B • Updated May 26

published a model about 1 month ago

OptimAI-Lab/BLUR-NPO_MUSE-Books

7B • Updated May 26

updated a model about 1 month ago

OptimAI-Lab/BLUR-NPO_MUSE-News

7B • Updated May 26

published a model about 1 month ago

OptimAI-Lab/BLUR-NPO_MUSE-News

7B • Updated May 26

updated a model about 1 month ago

OptimAI-Lab/BLUR-NPO_TOFU_Llama-3.2-1B-Instruct_forget10

1B • Updated May 26

published a model about 1 month ago

OptimAI-Lab/BLUR-NPO_TOFU_Llama-3.2-1B-Instruct_forget10

1B • Updated May 26

updated a collection about 2 months ago

RULE

Collection

This is official model collection for paper "Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding" • 2 items • Updated May 12

updated a model about 2 months ago

OptimAI-Lab/TOFU-forget10_RULE-NPO

Text Generation • 1B • Updated May 31 • 2

published a model about 2 months ago

OptimAI-Lab/TOFU-forget10_RULE-NPO

Text Generation • 1B • Updated May 31 • 2

updated a model about 2 months ago

OptimAI-Lab/MUSE-News_RULE-NPO

7B • Updated May 12

published a model about 2 months ago

OptimAI-Lab/MUSE-News_RULE-NPO

7B • Updated May 12