Call for abstracts

FoPt 2026 welcomes submissions in a single non-archival track

The Second Workshop on the Foundations of Post-training (FoPt 2026) invites one-page abstract submissions addressing theoretical and empirical challenges in post-training, in a single non-archival track. Submissions must be one-page abstracts (excluding references). Accepted abstracts will be presented as posters at the workshop. Abstract submissions are due on Monday, June 15th, 2026 (Anywhere on Earth).

The workshop solicits contributions addressing fundamental questions related to post-training in various levels of abstraction, including but not limited to the following topics of interest:

  1. Theoretical foundations of post-training and reasoning
    • Fine-tuning methods
    • Inference-time methods
    • Interaction between pre-training and post-training
  2. Optimization landscape of post-training
    • Stability and convergence guarantees
    • Theoretical insights into the loss landscape of post-training
    • Insights into optimizers
  3. Emerging learning paradigms
    • Self-improvement
    • Curriculum and continual learning
    • Weak-to-strong generalization
    • Multi-agent interaction
  4. Novel frameworks and abstractions for post-training
    • Models for LLM reasoning abilities, such as chain-of-thought
    • Formalizations for new forms of generalization, e.g., in-context learning and length generalization
  5. Other topics
    • Scientific studies of model behavior
    • Representational abilities of transformers

Important dates

(All dates are in 2026)

  • Submission deadline: Monday, June 15th, 11:59 PM AoE
  • Author notification: Friday, June 19th
  • Workshop date: Monday, June 29th

Dual submission policy

Since the workshop is non-archival, FoPt welcomes one-page abstracts describing work that may be substantially similar to papers that have previously been published, accepted for publication, or submitted in parallel to a peer-reviewed conference or journal. Submitted abstracts need not be anonymized.

Submission Instructions

Formatting and anonymization

Submitted abstracts are limited to one page, excluding references. Submissions may include an optional appendix, but reviewers are not required to read the appendix.

Anonymization: Submissions should be suitable for single-blind reviewing; in particular, submissions are permitted to include author names and other identifying information. Reviewer names are withheld from the authors.

Style files: For submitted one-page abstracts, please use the COLT style file, linked below.

Submitting your abstract

Abstracts should be submitted through OpenReview; the deadline for submissions is Monday, June 15th, 2026, 11:59 PM Anywhere on Earth (AoE).

OpenReview submission site: OpenReview