Call for Papers

We invite contributions that advance the understanding and application of causal representation learning (CRL). We encourage submissions exploring theoretical foundations, innovative models, and practical applications of CRL across diverse fields such as biology, economics, multimedia analysis, and foundation models. Join us in pushing the boundaries of how AI understands and manipulates causal relationships in complex data environments.

We welcome submissions covering both theoretical and applied aspects of CRL, including, but not limited to, the following key areas:

• Theory of Causal Representation Learning: Concepts, frameworks, and methodologies that underpin causal inference and representation in machine learning.
• Causal Representation Learning Models: Innovative models and algorithms that enhance the ability of AI systems to derive causal relationships.
• Causal Discovery with Latent Variables: Techniques and tools designed to identify latent causal variables and anlyze the causal structures.
• Causal Generative Models:  Developing models that not only generate data but also simulate the underlying causal processes, allowing for deeper insights into how variables influence one another in complex systems.
• Causal Foundation Models:  Integrating causal reasoning capabilities into large-scale foundational models, enhancing their ability to understand and manipulate underlying causal structures.
• Applications of causal representation learning, such as in biology, economics, and multimedia analysis: Learning causal representation to analyze complex real-world data, addressing practical tasks, and enhancing the transparency and trustworthiness of AI systems across various fields.
• Benchmarking causal representation learning: Establishing standardized metrics and procedures to evaluate the accuracy and effectiveness of causal representation learning models across diverse datasets and scenarios.

Submission Instructions

Format and Length:

Submissions must contain original, previously unpublished research and be formatted using the NeurIPS 2024 LaTeX style. All submissions should be in PDF format and limited to six content pages. Supplementary materials and references can be included on additional pages, but note that reviewers are not required to review these materials. The submission doesn’t need to include the checklist. For LaTeX templates, download from NeurIPS 2024 LaTeX Style Files.

Nonarchival Nature:

Our workshop is nonarchival, meaning accepted papers will be displayed on the workshop website but not included in the conference proceedings. This allows authors to submit their work to other venues in the future.

Double-blind Reviewing:

The review process is confidential and double-blind; only accepted papers will be published on our workshop website. All submissions must be anonymized, removing any identifying details, including acknowledgements and external links. Non-compliance with these guidelines will result in rejection.

Submission Site:

Please submit your manuscripts from Open Reivew

Important Dates (Anywhere on Earth,TBD)

• Workshop Papers Submission: September 10, 2024 October 2, 2024 (Welcome your ICLR submissions!)
• Acceptance Notification: October 9, 2024
• Camera-ready Deadline and Copyright Form: October 23, 2024
• Workshop Date: December 15, 2024