Arno Blaas

Researcher, Apple

Joined

July 2019

Names

Arno Blaas

Emails

****@yahoo.de (Confirmed)

,

****@robots.ox.ac.uk (Confirmed)

,

****@apple.com (Confirmed)

Personal Links

Semantic Scholar

Career & Education History

Researcher

Apple (apple.com)

2022 – Present

PhD student

University of Oxford (ox.ac.uk)

2017 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

I Can't Believe It's Not Better: Where Large Language Models need to improve
Arno Blaas, Priya Ronald DCosta, Fan Feng, Zhaoying Pan, Nikolai Rozanov, Jennifer Williams, Yubin Xie, Rui Yang
- ICLR 2026 Workshop Proposals
- Readers: Everyone
SelfReflect: Can LLMs Communicate Their Internal Answer Distribution?
Michael Kirchhof, Luca Füger, Adam Golinski, Eeshan Gunesh Dhekane, Arno Blaas, Seong Joon Oh, Sinead Williamson
- ICLR 2026 Poster
- Readers: Everyone
On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
Iuri Macocco, Pau Rodriguez, Arno Blaas, Luca Zappella, Marco Baroni, Xavier Suau
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
GenCtrl -- A Formal Controllability Toolkit for Generative Models
Emily Cheng, Carmen Amo Alonso, Federico Danieli, Arno Blaas, Luca Zappella, Pau Rodriguez, Xavier Suau
- ICLR 2026 Poster
- Readers: Everyone
Self-reflective Uncertainties: Do LLMs Know Their Internal Answer Distribution?
Michael Kirchhof, Luca Füger, Adam Golinski, Eeshan Gunesh Dhekane, Arno Blaas, Sinead Williamson
- ICML 2025 R2-FM Workshop Poster
- Readers: Everyone
LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
Pau Rodriguez, Michal Klein, Eleonora Gualdoni, Valentino Maiorca, Arno Blaas, Luca Zappella, marco cuturi, Xavier Suau
- NeurIPS 2025 poster
- Readers: Everyone
I Can't Believe It's Not Better: Challenges in Applied Deep Learning
Arno Blaas, Priya Ronald DCosta, Fan Feng, Andreas Kriegler, Zhaoying Pan, Tobias Uelwer, Jennifer Williams, Yubin Xie, Rui Yang
- ICLR 2025 Workshop Proposals
- Readers: Everyone
Controlling Language and Diffusion Models by Transporting Activations
Pau Rodriguez, Arno Blaas, Michal Klein, Luca Zappella, Nicholas Apostoloff, marco cuturi, Xavier Suau
- ICLR 2025 Spotlight
- Readers: Everyone
Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts
Jonathan Crabbé, Pau Rodriguez, Vaishaal Shankar, Luca Zappella, Arno Blaas
- Accepted by TMLR
- Readers: Everyone
Robust multimodal models have outlier features and encode more concepts
Jonathan Crabbé, Pau Rodriguez, Vaishaal Shankar, Luca Zappella, Arno Blaas
- Submitted to ICLR 2024
- Readers: Everyone

View all 19 publications

Co-Authors

View all 47 co-authors