University of Southern Denmark (SDU)

university

https://www.sdu.dk/en

Activity Feed

AI & ML interests

None defined yet.

Recent Activity

giannor submitted a paper 1 day ago

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

filo362 submitted a paper 2 months ago

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

giannor submitted a paper 2 months ago

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

View all activity

Papers

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

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

View all Papers

SDU-Denmark 's papers 5

Submitted by

Gianluca Barmina

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

University of Southern Denmark (SDU)

1 2

Submitted by

Filippo Tonini

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

University of Southern Denmark (SDU)

5 2

Submitted by

Gianluca Barmina

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

University of Southern Denmark (SDU)

4 2

Submitted by

Gianluca Barmina

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

University of Southern Denmark (SDU)

2 4

Submitted by

Gianluca Barmina

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

University of Southern Denmark (SDU)

0 2

AI & ML interests

Recent Activity

Papers

Team members 1

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

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

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

PsychoSafe: Eliciting Psychologically-Informed Refusals in Large Language Models

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