colored_dye

colored-dye's activity

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

upvoted 2 papers 1 day ago

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts

Paper • 2605.05974 • Published 5 days ago • 1

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions

Paper • 2602.05234 • Published Feb 5 • 1

updated a dataset 1 day ago

colored-dye/concept500-contrastive

Viewer • Updated 1 day ago • 144k • 27

upvoted a paper 3 days ago

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

Paper • 2605.05983 • Published 5 days ago • 1

updated a model 3 days ago

colored-dye/axbench-steering-vector

Updated 3 days ago

published a model 4 days ago

colored-dye/axbench-steering-vector

Updated 3 days ago

published a dataset 3 months ago

colored-dye/concept500-contrastive

Viewer • Updated 1 day ago • 144k • 27

upvoted a paper 11 months ago

Large Language Models are Locally Linear Mappings

Paper • 2505.24293 • Published May 30, 2025 • 14