ICLR 2027 Call for Papers
We invite submissions to the 15th International Conference on Learning Representations, and welcome paper submissions from all areas of machine learning.
For any information needed that is not listed below, please submit questions using this link: Contact ICLR Program Chairs.
Questions can be directed to: program-chairs@iclr.cc.
Please see the author guidelines for all submission instructions and policies. Please read these instructions carefully, as we have new policies this year regarding co-authorship, reciprocal reviewing, and the use of AI.
Key dates
The planned dates are as follows (all times are UTC-12h, aka “Anywhere on Earth”):
Abstract deadline Sep 18, 2026 AOE
Paper deadline Sep 25, 2026 AOE
Reviews released Nov 05, 2026
Author-reviewer discussion Nov 05, 2026–Nov 18, 2026
Reviewer-AC discussion Nov 19, 2026–Dec 16, 2026
Final decisions: Dec 16, 2026
Subject Areas
We consider a broad range of subject areas including feature learning, metric learning, compositional modeling, structured prediction, reinforcement learning, uncertainty quantification and issues regarding large-scale learning and non-convex optimization, as well as applications in vision, audio, speech, language, music, robotics, games, healthcare, biology, sustainability, economics, ethical considerations in ML, and others.
A non-exhaustive list of relevant topics:
- unsupervised, self-supervised, semi-supervised, and supervised representation learning
- transfer learning, meta learning, and lifelong learning
- reinforcement learning
- representation learning for computer vision, audio, language, and other modalities
- metric learning, kernel learning, and sparse coding
- probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)
- generative models
- causal reasoning
- optimization
- learning theory
- learning on graphs and other geometries & topologies
- societal considerations including fairness, safety, privacy
- visualization or interpretation of learned representations
- datasets and benchmarks
- infrastructure, software libraries, hardware, etc.
- neurosymbolic & hybrid AI systems (physics-informed, logic & formal reasoning, etc.)
- applications to robotics, autonomy, planning
- applications to neuroscience & cognitive science
- applications to physical sciences (physics, chemistry, biology, etc.)
- general machine learning (i.e., none of the above)
Submissions will be double blind: reviewers cannot see author names when conducting reviews, and authors cannot see reviewer names. Having papers on arxiv is allowed per the dual submission policy outlined in the author guidelines.