Greg Frank PRO

gregfrank's activity

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

updated a model 8 days ago

gregfrank/GLM-4.5-Air-ULRE-abliterated

Text Generation • 107B • Updated 8 days ago • 282

published a model 8 days ago

gregfrank/GLM-4.5-Air-ULRE-abliterated

Text Generation • 107B • Updated 8 days ago • 282

updated a model 9 days ago

gregfrank/Mistral-Large-Instruct-2411-ULRE-abliterated

Text Generation • 123B • Updated 9 days ago • 1.28k

published a model 9 days ago

gregfrank/Mistral-Large-Instruct-2411-ULRE-abliterated

Text Generation • 123B • Updated 9 days ago • 1.28k

updated a model 9 days ago

gregfrank/Qwen3-32B-ULRE-abliterated

Text Generation • 33B • Updated 9 days ago • 127

published a model 9 days ago

gregfrank/Qwen3-32B-ULRE-abliterated

Text Generation • 33B • Updated 9 days ago • 127

authored 2 papers 2 months ago

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails

Paper • 2603.18280 • Published Mar 18 • 1

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Paper • 2604.04385 • Published Apr 13 • 1

updated a collection 2 months ago

alignment

Collection

2 items • Updated Apr 14

submitted a paper to Daily Papers 2 months ago

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Paper • 2604.04385 • Published Apr 13 • 1

upvoted a paper 3 months ago

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails

Paper • 2603.18280 • Published Mar 18 • 1