Call for Papers

Important Dates

• Submission Begins: May 10, 2025
  • Submission Portal: OpenReview
  • Template: Overleaf
• Submission Deadline: May 22 May 28, 2025 (11:59 am, anywhere on earth)
• Notification of Acceptance: June 9, 2025
• Workshop Date: Saturday, July 19

Guidelines

• We welcome papers up to 4 pages (max), not including references or appendix.
  • The paper should be anonymized and uploaded to OpenReview as a single PDF.
  • You may use as many pages of references and appendix as you wish, but reviewers are not required to read the appendix.
  • Posting papers on preprint servers like ArXiv is permitted.
• This is a non-archival workshop. No submission will be indexed nor have archival proceedings.
  • Accepted papers will appear on the workshop website. They will also be available on OpenReview and ICML virtual site.
  • We accept submissions that are under review at other venues (e.g., NeurIPS 2025), as long as this does not violate the dual-submission / anonymity policy of the other venue.
• The review process will be double-blind.
  

Topics of Interest

Many challenging tasks for foundation models require synthesizing information over thousands to millions of individual pieces of data, which may take many forms, including images, text, audio, genomes, etc. Enabling foundation models to process long contexts introduces key challenges in computational efficiency, data quality and quantity, and evaluation. Our workshop aims to convene researchers to address these challenges, fostering discussions, developments, and evaluation of long-context foundation models across various AI disciplines, including but not limited to:

• New modeling, training, and data strategies.
• Efficiency techniques for (long-context) foundation models.
• Evaluation and understanding of long-context models.
• Retrieval-augmented foundation models.
• Long-context reasoning.
• Long-context multimodal learning.
• Long-range AI for science.
• What’s next for long-context foundation models?

Speakers

TBA

Panelists

TBA

Organizers

Zexue He
MIT-IBM
MIT

Tianyu Gao

Princeton University

Amanda Bertsch
Carnegie Mellon University

Howard Yen

Princeton University

Yuandong Tian
Meta

Danqi Chen
Princeton University

Graham Neubig
Carnegie Mellon University

Rogerio Feris
MIT-IBM