Scholar

Jeremias Ferrao

Google Scholar ID: XgoZKaIAAAAJ

Graduate Student, University of Groningen

Reinforcement LearningDeep LearningAI AlignmentMechanistic Interpretability

Google Scholar↗

Citations & Impact

All-time

Citations

1

H-index

1

i10-index

0

Publications

4

Co-authors

4

list available

Contact

No contact links provided.

Publications

4 items

Paved with True Intents: Intent-Aware Training Improves LLM Safety Classification Across Training Regimes

2026

Cited

0

What Really Counts? Examining Step and Token Level Attribution in Multilingual CoT Reasoning

2025

Cited

0

The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features

2025

Cited

0

World Model Agents with Change-Based Intrinsic Motivation

2025

Cited

0

Resume (English only)

Co-authors

4 total

Rafael F. Cunha

Ph.D. Student, University of Groningen

Matthijs van der Lende

University of Groningen

Ilija Lichkovski

Unknown affiliation

Natalia Perez-Campanero

PhD student, University of Oxford