Statistical and structural identifiability in representation learning

Export BriefConnect with Author
View PDF ↗
PDF Viewer
Open Full PDF

BUILDER'S SANDBOX

Build This Paper

Use an AI coding agent to implement this research.

OpenAI Codex
OpenAI CodexAI Agent

Lightweight coding agent in your terminal.

Claude Code
Claude CodeAI Agent

Agentic coding tool for terminal workflows.

AntiGravity IDE
AntiGravity IDEScaffolding

AI agent mindset installer and workflow scaffolder.

Cursor
CursorIDE

AI-first code editor built on VS Code.

VS Code
VS CodeIDE

Free, open-source editor by Microsoft.

Estimated $9K - $13K over 6-10 weeks.

See exactly what it costs to build this -- with 3 comparable funded startups.

7-day free trial. Cancel anytime.

Discover the researchers behind this paper and find similar experts.

7-day free trial. Cancel anytime.

References (61)

[1]
When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective
2025Beatrix M. G. Nielsen, Emanuele Marconato et al.
[2]
RxRx3-core: Benchmarking drug-target interactions in High-Content Microscopy
2025Oren Kraus, Federico Comitani et al.
[3]
Robustness of Nonlinear Representation Learning
2025Simon Buchholz, Bernhard Schölkopf
[4]
I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
2025Yuhang Liu, Dong Gong et al.
[5]
Simulating 500 million years of evolution with a language model
2024Thomas Hayes, Roshan Rao et al.
[6]
ResiDual Transformer Alignment with Spectral Decomposition
2024Lorenzo Basile, Valentino Maiorca et al.
[7]
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
2024Emanuele Marconato, Sébastien Lachapelle et al.
[8]
Cross-Entropy Is All You Need To Invert the Data Generating Process
2024Patrik Reizinger, Alice Bizeul et al.
[9]
Unifying Causal Representation Learning with the Invariance Principle
2024Dingling Yao, Dario Rancati et al.
[10]
ReSi: A Comprehensive Benchmark for Representational Similarity Measures
2024Max Klabunde, Tassilo Wald et al.
[11]
Understanding LLMs Requires More Than Statistical Generalization
2024Patrik Reizinger, Szilvia Ujv'ary et al.
[12]
Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
2024Oren Kraus, Kian Kenyon-Dean et al.
[13]
Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder
2023Michael D. Bereket, Theofanis Karaletsos
[14]
Latent Space Translation via Semantic Alignment
2023Valentino Maiorca, Luca Moschella et al.
[15]
Evaluating batch correction methods for image-based cell profiling
2023John Arevalo, Robert van Dijk et al.
[16]
RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
2023Anthony Brohan, Noah Brown et al.
[17]
Leveraging Task Structures for Improved Identifiability in Neural Network Representations
2023Wenlin Chen, Julien Horwood et al.
[18]
Disentanglement via Latent Quantization
2023Kyle Hsu, Will Dorrell et al.
[19]
RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods
2023Maciej Sypetkowski, Morteza Rezanejad et al.
[20]
Some Remarks on Identifiability of Independent Component Analysis in Restricted Function Classes
2023Simon Buchholz

Showing 20 of 61 references

Founder's Pitch

"This paper proposes a new framework for understanding and improving identifiability in representation learning models."

Representation LearningScore: 5View PDF ↗

Commercial Viability Breakdown

0-10 scale

High Potential

2/4 signals

5

Quick Build

1/4 signals

2.5

Series A Potential

0/4 signals

0

Sources used for this analysis

arXiv Paper

Full-text PDF analysis of the research paper

GitHub Repository

Code availability, stars, and contributor activity

Citation Network

Semantic Scholar citations and co-citation patterns

Community Predictions

Crowd-sourced unicorn probability assessments

Analysis model: GPT-4o · Last scored: 3/12/2026

Explore the full citation network and related research.

7-day free trial. Cancel anytime.

Understand the commercial significance and market impact.

7-day free trial. Cancel anytime.

Get detailed profiles of the research team.

7-day free trial. Cancel anytime.

Related Papers

Loading…