Patrik Reizinger

1. Cross-Entropy Is All You Need To Invert the Data Generating Process
   2024/10/29 by Patrik Reizinger, Reizinger, Patrik, Alice Bizeul +11 · 10 citations
   Computer Science · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications
2. Embrace the Gap: VAEs Perform Independent Mechanism Analysis
   2022/06/06 by Patrik Reizinger, Luigi Gresele, Reizinger, Patrik +15 · 3 citations
   Physics and Astronomy · Computer Science · Biochemistry, Genetics and Molecular Biology · #Model Reduction and Neural Networks #Domain Adaptation and Few-Shot Learning #Protein Structure and Dynamics
3. Position: Understanding LLMs Requires More Than Statistical Generalization
   2024/05/03 by Patrik Reizinger, Reizinger, Patrik, Szilvia Ujváry +9 · 2 voices · 3 citations
   Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
4. From superposition to sparse codes: interpretable representations in neural networks
   2025/03/03 by David Klindt, Klindt, David, Charles O’Neill +8 · 1 voice · 4 citations
   Computer Science · #Neural Networks and Applications #cs.LG
5. Rule Extrapolation in Language Models: A Study of Compositional Generalization on OOD Prompts
   2024/09/09 by Anna Mészáros, Szilvia Ujváry, Mészáros, Anna +7 · 1 voice · 2 citations
   Computer Science · Mathematics · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #cs.CL #cs.LG #stat.ML
6. Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
   2025/04/17 by Patrik Reizinger, Randall Balestriero, Reizinger, Patrik +5 · 1 voice · 1 citation
   Social Sciences · Psychology · #cs.LG #cs.AI #stat.ML
7. An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis
   2023/11/29 by Goutham Rajendran, Patrik Reizinger, Rajendran, Goutham +5 · 1 citation
   Computer Science · #Blind Source Separation Techniques #Neural Networks and Applications #Gaussian Processes and Bayesian Inference
8. A unifying framework from neural superposition to sparse interpretable codes
   2026/07/14 by David Klindt, Charles O’Neill, Patrik Reizinger +2 · 2 voices
   Neuroscience · Computer Science · #Face Recognition and Perception #Explainable Artificial Intelligence (XAI) #Embodied and Extended Cognition
9. HALLMARK: Diagnosing Three Failure Modes in LLM Citation Verifiers
   2026/07/20 by Patrik Reizinger, Wieland Brendel
   #cs.CR #cs.AI #cs.LG