NeurIPS 2026 Workshop
Foundations of LLM Post-Training
in Changing Environments
- Date
- December 2026
Exact workshop day TBA - Location
- Paris, France
Venue TBA - Submission
- September 2026
Exact deadline TBA
In Partnership With
Key Dates
Full Call for Papers →About the Workshop
Large language models (LLMs) are routinely adapted to downstream applications through post-training methods, such as instruction tuning and domain adaptation. Yet in real-world deployment, downstream tasks rarely remain fixed: objectives shift, data distributions drift, feedback signals evolve, and evaluation standards change over time. Post-training therefore becomes a process of repeated adaptation in non-stationary environments.
Despite its central role in modern foundation models, the theoretical foundations of this adaptive post-training paradigm remain limited. Current practices are largely heuristic, with incomplete understanding of statistical identifiability, optimization dynamics, robustness to misspecification, and trade-offs between adaptation and capability preservation. These gaps are particularly consequential in safety-critical settings, where unintended regressions or feedback loops may arise under evolving conditions.
This workshop will develop principled foundations for LLM post-training under task evolution. It will bring together researchers from machine learning theory, reinforcement learning, and AI safety to develop principled foundations for this.
Workshop Pages
- Call for Papers — Topics, submission guidelines, and key dates.
- Workshop Program — Full schedule for the day.
- Accepted Papers — Browse the accepted submissions.
- Organising Committee — The team behind the workshop.