OptimAI-Lab

OptimAI-Lab's activity

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

Mingyi-Hong 

updated a collection 7 days ago

Hiddenstate_unlearning

Collection

2 items • Updated 7 days ago

Mingyi-Hong 

updated 2 models 7 days ago

OptimAI-Lab/PARS_MUSE

7B • Updated 7 days ago • 12

OptimAI-Lab/PARS_TOFU

1B • Updated 7 days ago • 16

Mingyi-Hong 

updated a collection 7 days ago

Hiddenstate_unlearning

Collection

2 items • Updated 7 days ago

Mingyi-Hong 

published 2 models 7 days ago

OptimAI-Lab/PARS_TOFU

1B • Updated 7 days ago • 16

OptimAI-Lab/PARS_MUSE

7B • Updated 7 days ago • 12

Mingyi-Hong 

updated a model 23 days ago

OptimAI-Lab/ToolAlpaca_unlearn_ToolDelete-DPO

Text Generation • Updated 23 days ago • 347

Mingyi-Hong 

updated a collection 23 days ago

ToolAlpaca_unlearning

Collection

ToolAlpaca-7B unlearning models • 5 items • Updated 23 days ago

ZijianZhang 

authored a paper 3 months ago

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

Paper • 2607.01232 • Published Jul 2 • 8

Mingyi-Hong 

submitted a paper to Daily Papers 4 months ago

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

Paper • 2607.01232 • Published Jul 2 • 8

Mingyi-Hong 

in OptimAI-Lab/TOFU-forget10_RULE-NPO 5 months ago

Add library_name, pipeline_tag and link to code

#1 opened 5 months ago by

nielsr

Mingyi-Hong 

updated a collection 5 months ago

BLUR

Collection

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

Mingyi-Hong 

updated a model 5 months ago

OptimAI-Lab/BLUR-RMU_WMDP

Text Generation • 7B • Updated May 26 • 10