Patrik Reizinger

30 papers A* 5A 1Misc 1Journal 20Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Causality is Key for Interpretability Claims to Generalise. CoRR Shruti Joshi, Aaron Mueller, David A. Klindt, Wieland Brendel, Patrik Reizinger, Dhanya Sridhar
2026	J	`jnl`	Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations. CoRR Shruti Joshi, Théo Saulus, Wieland Brendel, Philippe Brouillard, Dhanya Sridhar, Patrik Reizinger
2025	J	`jnl`	An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research. CoRR Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel
2025	A*	`conf`	Cross-Entropy Is All You Need To Invert the Data Generating Process. ICLR Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt
2025	J	`jnl`	Estimating Treatment Effects with Independent Component Analysis. CoRR Patrik Reizinger, Lester Mackey, Wieland Brendel, Rahul Krishnan
2025	J	`jnl`	From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts? CoRR Aaron Mueller, Andrew Lee, Shruti Joshi, Ekdeep Singh Lubana, Dhanya Sridhar, Patrik Reizinger
2025	J	`jnl`	From superposition to sparse codes: interpretable representations in neural networks. CoRR David A. Klindt, Charles O'Neill, Patrik Reizinger, Harald Maurer, Nina Miolane
2025	A*	`conf`	Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning. ICLR Patrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel
2025	A	`conf`	InfoNCE: Identifying the Gap Between Theory and Practice. AISTATS Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel
2025	J	`jnl`	Occam's Razor for SSL: Memory-Efficient Parametric Instance Discrimination. Trans. Mach. Learn. Res. Eric Gan, Patrik Reizinger, Alice Bizeul, Attila Juhos, Mark Ibrahim, Randall Balestriero, David A. Klindt, Wieland Brendel, Baharan Mirzasoleiman
2025	J	`jnl`	Out-of-distribution Tests Reveal Compositionality in Chess Transformers. CoRR Anna Mészáros, Patrik Reizinger, Ferenc Huszár
2025	—	`conf`	Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research. ICML (Position Papers) Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel
2025	J	`jnl`	Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning. CoRR Patrik Reizinger, Bálint Mucsányi, Siyuan Guo, Benjamin Eysenbach, Bernhard Schölkopf, Wieland Brendel
2024	—	`conf`	An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis. CLeaR Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Kumar Ravikumar
2024	J	`jnl`	Cross-Entropy Is All You Need To Invert the Data Generating Process. CoRR Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt
2024	J	`jnl`	Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning. CoRR Patrik Reizinger, Siyuan Guo, Ferenc Huszár, Bernhard Schölkopf, Wieland Brendel
2024	J	`jnl`	InfoNCE: Identifying the Gap Between Theory and Practice. CoRR Evgenia Rusak, Patrik Reizinger, Attila Juhos, Oliver Bringmann, Roland S. Zimmermann, Wieland Brendel
2024	A*	`conf`	Position: Understanding LLMs Requires More Than Statistical Generalization. ICML Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár
2024	A*	`conf`	Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts. NeurIPS Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszar
2024	J	`jnl`	Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts. CoRR Anna Mészáros, Szilvia Ujváry, Wieland Brendel, Patrik Reizinger, Ferenc Huszár
2024	J	`jnl`	Understanding LLMs Requires More Than Statistical Generalization. CoRR Patrik Reizinger, Szilvia Ujváry, Anna Mészáros, Anna Kerekes, Wieland Brendel, Ferenc Huszár
2023	J	`jnl`	An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis. CoRR Goutham Rajendran, Patrik Reizinger, Wieland Brendel, Pradeep Ravikumar
2023	J	`jnl`	Jacobian-based Causal Discovery with Nonlinear ICA. Trans. Mach. Learn. Res. Patrik Reizinger, Yash Sharma, Matthias Bethge, Bernhard Schölkopf, Ferenc Huszár, Wieland Brendel
2022	A*	`conf`	Embrace the Gap: VAEs Perform Independent Mechanism Analysis. NeurIPS Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve
2022	J	`jnl`	Embrace the Gap: VAEs Perform Independent Mechanism Analysis. CoRR Patrik Reizinger, Luigi Gresele, Jack Brady, Julius von Kügelgen, Dominik Zietlow, Bernhard Schölkopf, Georg Martius, Wieland Brendel, Michel Besserve
2021	J	`jnl`	Handling Realistic Noise in Multi-Agent Systems with Self-Supervised Learning and Curiosity. J. Artif. Intell. Soft Comput. Res. Márton Szemenyei, Patrik Reizinger
2020	Misc	`conf`	Attention-Based Curiosity-Driven Exploration in Deep Reinforcement Learning. ICASSP Patrik Reizinger, Márton Szemenyei
2019	J	`jnl`	Attention-based Curiosity-driven Exploration in Deep Reinforcement Learning. CoRR Patrik Reizinger, Márton Szemenyei
2019	—	`conf`	Stochastic Weight Matrix-Based Regularization Methods for Deep Neural Networks. LOD Patrik Reizinger, Bálint Gyires-Tóth
2019	J	`jnl`	Stochastic Weight Matrix-based Regularization Methods for Deep Neural Networks. CoRR Patrik Reizinger, Bálint Gyires-Tóth