Gianluca Barmina

giannor's activity

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

upvoted a paper 7 days ago

The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment

Paper • 2606.10747 • Published 13 days ago • 13

updated a dataset 10 days ago

giannor/gec_dala_tv2r_it

Viewer • Updated 10 days ago • 931k • 30

published 2 datasets 10 days ago

giannor/gec_dala_tv2r_it

Viewer • Updated 10 days ago • 931k • 30

giannor/dala_tv2r_it

Viewer • Updated 10 days ago • 984k • 32

updated a dataset 10 days ago

giannor/dala_tv2r_it

Viewer • Updated 10 days ago • 984k • 32

published a dataset 11 days ago

giannor/dala_tv2r

Viewer • Updated 11 days ago • 984k • 28

updated a dataset 11 days ago

giannor/dala_tv2r

Viewer • Updated 11 days ago • 984k • 28

published a dataset 11 days ago

giannor/dala_gen_tv2r

Viewer • Updated 11 days ago • 931k • 22

updated a dataset 11 days ago

giannor/dala_gen_tv2r

Viewer • Updated 11 days ago • 931k • 22

commented a paper 11 days ago

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published 14 days ago • 7 •

4

authored 2 papers 11 days ago

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

Paper • 2606.09707 • Published 14 days ago • 8

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published 14 days ago • 7

upvoted a paper 12 days ago

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published 14 days ago • 7

submitted a paper to Daily Papers 12 days ago

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published 14 days ago • 7

upvoted a paper 12 days ago

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

Paper • 2606.09707 • Published 14 days ago • 8

submitted a paper to Daily Papers 12 days ago

BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and Upcycling

Paper • 2606.09707 • Published 14 days ago • 8

updated a model 12 days ago

giannor/Qwen3.5-27B-psysafe

Image-Text-to-Text • 27B • Updated 12 days ago • 27

authored a paper 17 days ago

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

Paper • 2606.06286 • Published 18 days ago • 8

New activity in lgalke/Qwen3.5-35B-A3B-psysafe 17 days ago

Update README.md

#1 opened 17 days ago by

giannor

upvoted a paper 17 days ago

LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs

Paper • 2606.06286 • Published 18 days ago • 8