Patrik Reizinger
10 papers · 2022–2026 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(20)
💎
Century Club · Bronze
❓
The Questioner
(2)
Top co-authors
Research topics
Machine Learning
(8)
Artificial Intelligence
(7)
Core AI
(6)
Core Methods
(6)
Deep Learning
(5)
Learning Types · Deep Learning
(4)
Optimization & Theory
(4)
Learning Types · Machine Learning
(3)
Bayesian & Probabilistic
(2)
Natural Language Processing
(1)
Architectures
(1)
Generation
(1)
Learning Paradigms
(1)
Models
(1)
Keywords
representation learning
(5)
identifiability theory
(3)
independent component analysis
(2)
latent factor
(2)
in-context learning
(2)
data augmentation
(1)
causal discovery
(1)
contrastive learning
(1)
compositional generalization
(1)
sparse autoencoder
(1)
system identification
(1)
causal structure
(1)
probabilistic model
(1)
state space model
(1)
out-of-distribution generalization
(1)
training dynamics
(1)
variational autoencoder
(1)
disentangled representation
(1)
probabilistic graphical model
(1)
kl divergence
(1)
Papers
From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
ACL 2026
Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations
UAI 2026
Cross-Entropy Is All You Need To Invert the Data Generating Process
ICLR 2025
Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning
ICLR 2025
InfoNCE: Identifying the Gap Between Theory and Practice
AISTATS 2025
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
ICML 2025
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis
CLeaR 2024
Position: Understanding LLMs Requires More Than Statistical Generalization
ICML 2024
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
NeurIPS 2024
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
NeurIPS 2022