Andrea Blasi

AndreaBlasi97

5

AI & ML interests

None yet

Recent Activity

authored a paper 18 days ago

Dynaword: From One-shot to Continuously Developed Datasets

authored a paper 18 days ago

SommBench: Assessing Sommelier Expertise of Language Models

authored a paper 18 days ago

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

View all activity

Organizations

None yet

upvoted a paper 19 days ago

Selecting The Most Informative Tokens in Natural Language Autoencoders

Paper • 2609.37040 • Published 22 days ago • 18

upvoted a paper 2 months ago

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

Paper • 2608.13517 • Published Aug 13 • 33

upvoted 3 papers 4 months ago

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

Paper • 2606.09697 • Published Jun 8 • 7

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

Paper • 2606.09707 • Published Jun 8 • 8

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

Paper • 2606.10747 • Published Jun 9 • 13