The Thirteenth International Conference on Learning Representations

The Thirteenth International Conference on Learning Representations (ICLR 2025) is one of the most influential venues in machine learning, dedicated to advancing the mathematical and empirical understanding of how representations are learned from data. Since its founding, ICLR has been at the forefront of deep learning research, hosting landmark papers on neural architectures, optimization, and generalization.

The conference covers representation learning across vision, language, audio, graphs, and scientific domains, with increasing attention to robustness, fairness, efficiency, and theoretical foundations. ICLR attracts an elite global community of machine learning researchers from academia and industry and is renowned for its open peer-review process. It is an essential event for anyone seeking to understand and contribute to the core advances driving modern AI.