Call for Papers
Call for Papers We invite submissions to the 14th International Conference on Learning Representations 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 about the main conference can also be directed to: program-chairs@iclr.cc Please see the author guide for all submission instructions and policies. Key dates The planned dates are as follows (all times are UTC-12h , aka “Anywhere on Earth”): Abstract submission: 11:59pm, Sep 19 Submission date: 11:59pm, Sep 24 Reviews released: Nov 11 Author/Reviewer Discussion: Nov 11-Dec 3 Author Last Day to Reply: Dec 3 Final decisions: Jan 25 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 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 guide. We use OpenReview to host papers and allow for public review and discussion. The program will include oral presentations and posters of accepted papers. Successful Page Load ICLR uses cookies for essential functions only. We do not sell your personal information. Our Privacy Policy » Accept
Executive Summary
The 14th International Conference on Learning Representations (ICLR) invites submissions from all areas of machine learning, with key dates ranging from September 2024 to January 2026. The conference covers a broad range of subject areas, including feature learning, metric learning, and applications in various fields. Submissions will be double blind, and accepted papers will be presented orally or as posters. The conference utilizes the OpenReview platform for hosting papers and facilitating public review and discussion.
Key Points
- ▸ ICLR invites submissions from all areas of machine learning.
- ▸ The conference covers a broad range of subject areas, including feature learning and applications in various fields.
- ▸ Submissions will be double blind, and accepted papers will be presented orally or as posters.
Merits
Interdisciplinary Approach
ICLR's broad subject areas and applications in various fields demonstrate an interdisciplinary approach to machine learning, which can foster collaboration and innovation among researchers from different backgrounds.
Double-Blind Reviewing
The double-blind reviewing process helps to reduce bias and ensures that papers are evaluated solely on their merits, promoting fairness and equality in the review process.
Demerits
Limited Transparency
The conference's use of OpenReview for hosting papers and facilitating public review and discussion may not provide sufficient transparency into the review process, potentially leading to concerns about the legitimacy and accountability of the conference.
Technical Challenges
The use of OpenReview and other digital platforms may introduce technical challenges, such as accessibility and usability issues, which could affect the conference's overall success and impact.
Expert Commentary
The 14th International Conference on Learning Representations (ICLR) demonstrates a continued commitment to advancing the field of machine learning through its broad subject areas and interdisciplinary approach. The use of OpenReview and double-blind reviewing processes is a positive step towards increasing transparency and fairness in the review process. However, the conference's reliance on digital platforms and the potential for technical challenges may require careful consideration and planning to ensure a successful event. As the machine learning community continues to grow and evolve, conferences like ICLR will play an increasingly important role in shaping the field and influencing research directions.
Recommendations
- ✓ Conferences like ICLR should continue to prioritize interdisciplinary approaches and applications in various fields to foster innovation and collaboration among researchers.
- ✓ The use of double-blind reviewing processes and OpenReview platforms should be adopted more widely in machine learning conferences to increase transparency and fairness in the review process.
