Publications

Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers

Amir Mohammad Karimi Mamaghan^*, Ferdinand Kapl^*, Andrea Dittadi, Karl Henrik Johansson, Kaitlin Maile, Johannes von Oswald, Stefan Bauer

Preprint, under review

arXiv

Diffusion Adaptation Under Distribution Shifts via Distributionally Robust Optimization

Zifan Wang^*, Amir Mohammad Karimi Mamaghan^*, Riccardo De Santi, Ya-Ping Hsieh, Stefan Bauer, Karl Henrik Johansson

Preprint, under review

Object-Centric Learning for Part-Whole Hierarchies: Promises, Limitations, and Open Challenges

Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi, Karl Henrik Johansson, Stefan Bauer

Manuscript in preparation

ViroGym: Realistic Large-Scale Benchmarks for Evaluating Viral Proteins

Yichen Zhou, Jonathan L. Golob, Amir Mohammad Karimi Mamaghan, Stefan Bauer^†, Patrick Schwab^†

NeurIPS (Evaluations and Datasets Track, spotlight)

arXiv

Exploring Compute Efficiency and Task Transfer in Depth-Grown Protein Language Models

Aleena Siji, Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Tobias Höppe, Andrea Dittadi, Karl Henrik Johansson, Michael Heinzinger, Stefan Bauer

I Can't Believe It's Not Better: Failure Modes of AI in Biology (ICBINB-Bio) Workshop @ NeurIPS

OpenReview

Are Object-Centric Representations Better at Compositional Generalization?

Ferdinand Kapl, Amir Mohammad Karimi Mamaghan, Maximilian Seitzer, Karl Henrik Johansson, Carsten Marr, Stefan Bauer, Andrea Dittadi

ICML

Paper arXiv

From Prediction to Structure: Causal Discovery for 30-Day Readmission Prediction

Amir Mohammad Karimi Mamaghan, Yuyang Tao, M. Umar B. Niazi, Stefan Bauer, Karl Henrik Johansson

IEEE International Conference on Biomedical and Health Informatics (BHI)

OpenReview

From Words to Amino Acids: Does the Curse of Depth Persist?

Aleena Siji^*, Amir Mohammad Karimi Mamaghan^*, Ferdinand Kapl, Tobias Höppe, Emmanouil Angelis, Andrea Dittadi, Maurice Brenner, Michael Heinzinger, Karl Henrik Johansson, Kaitlin Maile, Johannes von Oswald, Stefan Bauer

Learning Meaningful Representations of Life (LMRL) Workshop @ ICLR

arXiv OpenReview

Analyzing crash injury severities with deep learning and advanced statistical models: An assessment of methodological challenges

MohammadAli Seyfi, Amir Mohammad Karimi Mamaghan, Ali Behnood, Fred Mannering

Analytic Methods in Accident Research

Paper

Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Models

Amir Mohammad Karimi Mamaghan, Samuele Papa, Karl Henrik Johansson, Stefan Bauer, Andrea Dittadi

ICLR

arXiv OpenReview

Challenges and Considerations in the Evaluation of Bayesian Causal Discovery

Amir Mohammad Karimi Mamaghan, Panagiotis Tigas, Karl Henrik Johansson, Yarin Gal, Yashas Annadani, Stefan Bauer

ICML

arXiv

Diffusion-Based Causal Representation Learning

Amir Mohammad Karimi Mamaghan, Andrea Dittadi, Stefan Bauer, Karl Henrik Johansson, Francesco Quinzan

Entropy

Paper arXiv

Modeling the Motorcycle Crash Severity on Nonintersection Urban Roadways in the Australian State of Victoria Using a Random Parameters Logit Model

Mohammad Ali Seyfi, Kayvan Aghabayk, Amir Mohammad Karimi Mamaghan, Nirajan Shiwakoti

Journal of Advanced Transportation

Paper

Analysis of Address Lifespans in Bitcoin and Ethereum

Amir Mohammad Karimi Mamaghan, Amin Setayesh, Behnam Bahrak

International Conference on Computer and Knowledge Engineering (ICCKE)

Paper

Machine learning at the service of meta-heuristics for solving combinatorial optimization problems: A state-of-the-art

Maryam Karimi Mamaghan, Mehrdad Mohammadi, Patrick Meyer, Amir Mohammad Karimi Mamaghan, El-Ghazali Talbi

European Journal of Operational Research

Paper

Hub-and-spoke network design under congestion: A learning based metaheuristic

Maryam Karimi Mamaghan, Mehrdad Mohammadi, Amir Pirayesh, Amir Mohammad Karimi Mamaghan, Hassan Irani

Transportation Research Part E: Logistics and Transportation Review

Paper