TrustMI

community

AI & ML interests

Mechanical Interpretability, Model Steering, LLM, evaluation, assistants and agents

Recent Activity

Blyzi authored a paper 2 days ago

TrustMI: Causally controlling how assistants trust their users

RomainFroger authored a paper 2 days ago

TrustMI: Causally controlling how assistants trust their users

MaxLSB authored a paper 2 days ago

TrustMI: Causally controlling how assistants trust their users

View all activity

Papers

TrustMI: Causally controlling how assistants trust their users

View all Papers

authored a paper 2 days ago

TrustMI: Causally controlling how assistants trust their users

Paper • 2610.06064 • Published 7 days ago • 3

authored a paper 2 days ago

TrustMI: Causally controlling how assistants trust their users

Paper • 2610.06064 • Published 7 days ago • 3

authored 2 papers 2 days ago

TrustMI: Causally controlling how assistants trust their users

Paper • 2610.06064 • Published 7 days ago • 3

Small Agents with Semantic Search: Efficient Multilingual Code Localization

Paper • 2610.05099 • Published 8 days ago • 3

authored a paper 2 days ago

OmnilingualGAIA2: Evaluating the Multilingual Gap in Frontier AI Agents

Paper • 2608.08775 • Published Aug 9

updated a Space 2 days ago

README

published a Space 2 days ago

README

published a model 2 days ago

TrustMI/trustmi-steering-vectors

Updated 2 days ago

published a dataset 2 days ago

TrustMI/trustmi-conversations

Viewer • Updated 2 days ago • 7.91k • 42

updated a model 2 days ago

TrustMI/trustmi-steering-vectors

Updated 2 days ago

updated a dataset 2 days ago

TrustMI/trustmi-conversations

Viewer • Updated 2 days ago • 7.91k • 42

authored a paper 5 months ago

Rethinking the Multilingual Reasoning Gap with Layer Swap

Paper • 2605.26735 • Published May 26 • 4

authored 3 papers 5 months ago

Language-Switching Triggers Take a Latent Detour Through Language Models

Paper • 2605.18646 • Published May 18 • 4

Disentangling meaning from language in LLM-based machine translation

Paper • 2602.04613 • Published Feb 4 • 1

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models

Paper • 2602.10382 • Published Feb 12 • 2

authored a paper 7 months ago

Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments

Paper • 2602.11964 • Published Feb 12 • 13

authored a paper 12 months ago

Luth: Efficient French Specialization for Small Language Models and Cross-Lingual Transfer

Paper • 2510.05846 • Published Oct 7, 2025 • 3

authored a paper about 1 year ago

ARE: Scaling Up Agent Environments and Evaluations

Paper • 2509.17158 • Published Sep 21, 2025 • 36

authored a paper over 1 year ago

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices

Paper • 2506.18035 • Published Jun 22, 2025

authored a paper almost 2 years ago

CamemBERT 2.0: A Smarter French Language Model Aged to Perfection

Paper • 2411.08868 • Published Nov 13, 2024 • 14