steve abreu

prof_pic.jpg

Bernoulliborg 407

9747 AG Groningen

The Netherlands

s.abreu@rug.nl

I am a PhD student at the AI department of the University of Groningen, working in the MINDS group under the supervision of Prof. Herbert Jaeger and co-supervision of Prof. Elisabetta Chicca. I am part of the CogniGron research center for cognitive computing and funded by the European project Post-Digital. I’m currently on leave from my PhD position in Groningen to do research internships at Google and Intel.

In research I keep a dual focus on advancing machine learning while delving into novel compute paradigms and hardware for AI, especially those taking inspiration from the brain. I enjoy cross-disciplinary research between AI, computer science, neuroscience, physics, and cognitive science.

Within ML, I work on efficient machine learning (enabling AI on low-power hardware) and I am interested in continual learning (e.g. using brain-inspired neuromodulation or plasticity rules), meta-learning, and neurosymbolic programming. To make progress towards well-aligned and interpretable AI, I work on mechanistic interpretability and reverse-engineering of ML models.

For my PhD I work on physical and brain-inspired computing, where I aim to develop theories that align computation with physics, in order to make better use of neuromorphic chips, photonic devices, and other physical computing systems. I aim to develop computational abstractions in physical substrates (e.g. through the neuromorphic intermediate representation, NIR), new hardware-compatible efficient learning algorithms, and principled ways of programming novel AI hardware (confronting challenges like device mismatch and limited observability).

I am also a hobby photographer, an enthusiastic coffee brewer, an avid motorcyclist, I like to read, travel, and go to music and art events.

news

Jul 2024 Spent two weeks at Telluride in the Language and Thought topic area, presented our work on quantized SSMs at ICML in Vienna, and our neuromorphic programming paper at ICONS in Virginia!
May 2024 Starting my research internship at Intel’s Neuromorphic Computing Lab, working on neuromorphic transformer-like architectures based on state space models.
Dec 2023 Starting my research internship at Google in Waterloo (Canada), working on efficient and adaptive AR user interfaces with multimodal LLMs.
Oct 2023 Attending NNPC in Hannover. Presenting a poster on neuromorphic programming and abstractions.

selected publications

  1. Q-S5: Towards Quantized State Space Models
    Steven Abreu*, Jens E. Pedersen*, Kade M. Heckel*, and Alessandro Pierro
    In International Conference on Machine Learning (ICML) 2024 - NGSM workshop 2024
  2. Mamba-PTQ: Outlier Channels in Recurrent Large Language Models
    Alessandro Pierro*, and Steven Abreu*
    In International Conference on Machine Learning (ICML) 2024 - ES-FOMO-II workshop 2024
  3. Neuromorphic Intermediate Representation: A Unified Instruction Set for Interoperable Brain-Inspired Computing
    Jens E. Pedersen*, Steven Abreu*, Matthias Jobst, Gregor Lenz, Vittorio Fra, Felix C. Bauer, Dylan R. Muir, Peng Zhou, Bernhard Vogginger, Kade Heckel, Gianvito Urgese, Sadasivan Shankar, Terrence C. Stewart, Jason K. Eshraghian, and Sadique Sheik
    Nature Communications (in press) 2024
  4. PARSE-Ego4D: Personal Action Recommendation Suggestions for Egocentric Videos
    Steven Abreu, Tiffany D. Do, Karan Ahuja, Eric J. Gonzalez, Lee Payne, Daniel McDuff, and Mar Gonzalez-Franco
    under review 2024
  5. A photonics perspective on computing with physical substrates
    S. Abreu, I. Boikov, M. Goldmann, T. Jonuzi, A. Lupo, S. Masaad, L. Nguyen, E. Picco, G. Pourcel, A. Skalli, L. Talandier, B. Vettelschoss, E.A. Vlieg, A. Argyris, P. Bienstman, D. Brunner, J. Dambre, L. Daudet, J.D. Domenech, I. Fischer, F. Horst, S. Massar, C.R. Mirasso, B.J. Offrein, A. Rossi, M.C. Soriano, S. Sygletos, and S.K. Turitsyn
    Reviews in Physics 2024
  6. Neuromorphic Programming: Emerging Directions for Brain-Inspired Hardware
    Steven Abreu, and Jens E. Pedersen
    In Proceedings of the International Conference of Neuromorphic Systems 2024
  7. Flow Cytometry With Event-Based Vision and Spiking Neuromorphic Hardware
    Steven Abreu, Muhammed Gouda, Alessio Lugnan, and Peter Bienstman
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2023
  8. Hands-on reservoir computing: a tutorial for practical implementation
    Matteo Cucchi*, Steven Abreu*, Giuseppe Ciccone, Daniel Brunner, and Hans Kleemann
    Neuromorphic Computing and Engineering 2022
  9. Automated architecture design for deep neural networks
    Steven Abreu
    ArXiv Aug 2019