Patrik Reizinger
9 papers · 2022–2026 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(5)
🌉
Interdisciplinary Bridge
🗺️
Taxonomy Completionist
(10)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
ICLR (2)
ICML (2)
NIPS (2)
ACL (1)
AISTATS (1)
CLEAR (1)
Top co-authors
Keywords
transformer architecture
(1)
representation learning
(1)
variational inference
(1)
independent component analysis
(1)
in-context learning
(1)
out-of-distribution generalization
(1)
compositional generalization
(1)
system identification
(1)
state space model
(1)
disentangled representation
(1)
variational autoencoder
(1)
sparse autoencoder
(1)
formal language
(1)
latent factor
(1)
intervention design
(1)
large language model
(1)
rule extrapolation
(1)
independent mechanism analysis
(1)
gaussian lti system
(1)
causal de finetti theorem
(1)
Papers
From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?
ACL 2026
InfoNCE: Identifying the Gap Between Theory and Practice
AISTATS 2025
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
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research
ICML 2025
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
NIPS 2024
Position: Understanding LLMs Requires More Than Statistical Generalization
ICML 2024
An Interventional Perspective on Identifiability in Gaussian LTI Systems with Independent Component Analysis
CLEAR 2024
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
NIPS 2022