MJ
Mateja Jamnik
cs.LGcs.AIstat.MLcs.CLcs.LOcs.NEbioinformaticscs.CVcs.HCAlgorithms
On Valency
published · living versionsW_j2xud6fx·v1 · currentpublished
Preprints & journals
79 papers in the corpus · 2005–2026Residual Stochastic Concept Bottleneck Models2610.23421v2 · Stephen Marcou, Mateo Espinosa Zarlenga, Sonia Laguna et al.2026 · 0 citationsarXiv
Leiden Declaration on Artificial Intelligence and Mathematics2609.35334v2 · Jarod Alper, Michael Barany, Alain Chavarri Villarello et al.2026 · 2 citationsarXiv
Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations2607.17117v2 · Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik2026 · 0 citationsarXiv
KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models2606.30258v1 · Boshko Koloski, Xiangjian Jiang, Senja Pollak et al.2026 · 0 citationsarXiv
Data-driven Machine Learning Cannot Reach Symbolic-level Logical Reasoning -- The Limit of the Scaling Law2606.26454v2 · Tiansi Dong, Mateja Jamnik, Pietro Lio2026 · 0 citationsarXiv
The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics2606.12289v2 · Pietro Barbiero, Giovanni De Felice, Mateo Espinosa Zarlenga et al.2026 · 0 citationsarXiv
CB-SLICE: Concept-Based Interpretable Error Slice Discovery2605.29836v1 · Yael Konforti, Mateo Espinosa Zarlenga, Elaf Almahmoud et al.2026 · 0 citationsarXiv
Training Language Agents to Learn from Experience2605.20477v1 · Yuval Shalev, Zifeng Ding, Mateja Jamnik2026 · 0 citationsarXiv
TabFORGE: A Tabular Foundation Model for Generative Modelling2605.09424v3 · Xiangjian Jiang, Mingxuan Liu, Nikola Simidjievski et al.2026 · 0 citationsarXiv
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections2605.06342v1 · Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik2026 · 0 citationsarXiv
Shaping the Future of Mathematics in the Age of AI2603.24914v2 · Johan Commelin, Mateja Jamnik, Rodrigo Ochigame et al.2026 · 0 citationsNotices Amer. Math. Soc. 73 (2026), no. 6, 480-483
Digging Deeper: Learning Multi-Level Concept Hierarchies2603.10084v1 · Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik2026 · 0 citationsarXiv
Hierarchical Concept-based Interpretable Models2602.23947v1 · Oscar Hill, Mateo Espinosa Zarlenga, Mateja Jamnik2026 · 0 citationsarXiv
Towards Spatial Transcriptomics-driven Pathology Foundation Models2602.14177v1 · Konstantin Hemker, Andrew H. Song, Cristina Almagro-P'erez et al.2026 · 1 citationarXiv
Actionable Interpretability Must Be Defined in Terms of Symmetries2601.12913v4 · Pietro Barbiero, Mateo Espinosa Zarlenga, Francesco Giannini et al.2026 · 0 citationsarXiv
An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-Making2601.00142v1 · Tiansi Dong, Henry He, Pietro Lio et al.2026 · 0 citationsarXiv
A Matter of Interest: Understanding Interestingness of Math Problems in Humans and Language Models2511.08548v2 · Shubhra Mishra, Yuka Machino, Gabriel Poesia et al.2025 · 0 citationsarXiv
TabStruct: Measuring Structural Fidelity of Tabular Data2509.11950v2 · Xiangjian Jiang, Nikola Simidjievski, Mateja Jamnik2025 · 0 citationsarXiv
Oruga: An Avatar of Representational Systems Theory2509.04041v1 · Daniel Raggi, Gem Stapleton, Mateja Jamnik et al.2025 · 1 citationarXiv
Structure Transfer: an Inference-Based Calculus for the Transformation of Representations2509.03249v2 · Daniel Raggi, Gem Stapleton, Mateja Jamnik et al.2025 · 0 citationsarXiv
Foundations of Interpretable Models2508.00545v1 · Pietro Barbiero, Mateo Espinosa Zarlenga, Alberto Termine et al.2025 · 0 citationsarXiv
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts2504.17921v3 · Mateo Espinosa Zarlenga, Gabriele Dominici, Pietro Barbiero et al.2025 · 0 citationsarXiv
RO-FIGS: Efficient and Expressive Tree-Based Ensembles for Tabular Data2504.06927v1 · Urska Matjasec, Nikola Simidjievski, Mateja Jamnik2025 · 2 citationsarXiv
How Well Does Your Tabular Generator Learn the Structure of Tabular Data?2503.09453v1 · Xiangjian Jiang, Nikola Simidjievski, Mateja Jamnik2025 · 0 citationsarXiv
LLM Embeddings for Deep Learning on Tabular Data2502.11596v1 · Boshko Koloski, Andrei Margeloiu, Xiangjian Jiang et al.2025 · 0 citationsarXiv
Measuring Cross-Modal Interactions in Multimodal Models2412.15828v2 · Laura Wenderoth, Konstantin Hemker, Nikola Simidjievski et al.2024 · 6 citationsProceedings of the AAAI Conference on Artificial Intelligence, Volume 39, February 2025
PATHS: A Hierarchical Transformer for Efficient Whole Slide Image Analysis2411.18225v1 · Zak Buzzard, Konstantin Hemker, Nikola Simidjievski et al.2024 · 0 citationsarXiv
End-to-End Ontology Learning with Large Language Models2410.23584v1 · Andy Lo, Albert Q. Jiang, Wenda Li et al.2024 · 8 citationsarXiv
Efficient Bias Mitigation Without Privileged Information2409.17691v1 · Mateo Espinosa Zarlenga, Swami Sankaranarayanan, Jerone T. A. Andrews et al.2024 · 3 citationsarXiv
TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models2409.16118v3 · Andrei Margeloiu, Xiangjian Jiang, Nikola Simidjievski et al.2024 · 4 citationsarXiv
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe2406.04165v2 · Alicja Ziarko, Albert Q. Jiang, Bartosz Piotrowski et al.2024 · 1 citationarXiv
TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting2406.01805v2 · Andrei Margeloiu, Adri'an Bazaga, Nikola Simidjievski et al.2024 · 1 citationarXiv
Evaluating language models for mathematics through interactions.38830100 · Collins, Katherine M, Jiang, Albert Q, Frieder, Simon et al.2024 · 53 citationsProceedings of the National Academy of Sciences of the United States of America. 2024;121(24):e2318124121
Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine2405.19950v2 · Konstantin Hemker, Nikola Simidjievski, Mateja Jamnik2024 · 1 citationarXiv
Sphere Neural-Networks for Rational Reasoning2403.15297v4 · Tiansi Dong, Mateja Jamnik, Pietro Lio2024 · 0 citationsarXiv
Do Concept Bottleneck Models Respect Localities?2401.01259v5 · Naveen Raman, Mateo Espinosa Zarlenga, Juyeon Heo et al.2024 · 1 citationarXiv
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data2311.09115v3 · Konstantin Hemker, Nikola Simidjievski, Mateja Jamnik2023 · 45 citationsarXiv
Multilingual Mathematical Autoformalization2311.03755v2 · Albert Q. Jiang, Wenda Li, Mateja Jamnik2023 · 1 citationarXiv
Learning to Receive Help: Intervention-Aware Concept Embedding Models2309.16928v3 · Mateo Espinosa Zarlenga, Katherine M. Collins, Krishnamurthy Dvijotham et al.2023 · 5 citationsarXiv
Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs2306.15661v1 · Navindu Leelarathna, Andrei Margeloiu, Mateja Jamnik et al.2023 · 0 citationsarXiv
Spatio-relational inductive biases in spatial cell-type deconvolution10.1101/2023.05.19.541474v1 · Vinas, R., Scherer, P., Simidjievski, N. et al.2023 · 0 citationsbioRxiv
Interpretable Neural-Symbolic Concept Reasoning2304.14068v2 · Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini et al.2023 · 12 citationsProceedings of the 40th International Conference on Machine Learning, PMLR 202:1801-1825, 2023
CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs2304.05207v1 · Konstantin Hemker, Zohreh Shams, Mateja Jamnik2023 · 5 citationsarXiv
Human Uncertainty in Concept-Based AI Systems2303.12872v1 · Katherine M. Collins, Matthew Barker, Mateo Espinosa Zarlenga et al.2023 · 19 citationsarXiv
GCI: A (G)raph (C)oncept (I)nterpretation Framework2302.04899v1 · Dmitry Kazhdan, Botty Dimanov, Lucie Charlotte Magister et al.2023 · 2 citationsarXiv
Towards Robust Metrics for Concept Representation Evaluation2301.10367v1 · Mateo Espinosa Zarlenga, Pietro Barbiero, Zohreh Shams et al.2023 · 6 citationsarXiv
Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data2211.15616v1 · Andrei Margeloiu, Nikola Simidjievski, Pietro Lio et al.2022 · 13 citationsarXiv
Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery2211.10830v2 · Yana Lishkova, Paul Scherer, Steffen Ridderbusch et al.2022 · 8 citationsIFAC-PapersOnLine, Volume 56, Issue 2, 2023, Pages 3203-3210
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs2210.12283v3 · Albert Q. Jiang, Sean Welleck, Jin Peng Zhou et al.2022 · 29 citationsarXiv
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off2209.09056v2 · Mateo Espinosa Zarlenga, Pietro Barbiero, Gabriele Ciravegna et al.2022 · 67 citationshttps://proceedings.neurips.cc/paper_files/paper/2022/hash/867c06823281e506e8059f5c13a57f75-Abstract-Conference.html
Career total: 237 works. 79 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.