Menu

NeurIPS 2026 Tutorial Announcement

We are delighted to announce the tutorials that have been accepted at the NeurIPS 2026 Tutorial Track. In total, we selected 19 very strong proposals out of 62 submissions, covering a wide range of topics and sub-disciplines. 

The tutorials will take place on:

  • Dec 7, 2026 (full day) – Sydney
  • Dec 9 – Dec 11, 2026 – Paris 
  • Dec 9, 2026 – Atlanta

All NeurIPS 2026 tutorial proposals underwent a review process comprising the following steps:

  1. Initial review of the tutorial content by at least 2 of the tutorial track chairs, based on the criteria regarding topic suitability, tutorial content, education fit, and speaker fit.
  2. Initial nominations of acceptance by each of the tutorial track chairs.
  3. Discussion of borderline cases by all the tutorial track chairs together.
  4. Proposals are provisionally accepted, subject to confirmation of the presentation format (in person or online) and any constraints of the preferred venue location. 

New this year: For the first time, NeurIPS is taking place at three sites across the world: Sydney, Paris, and Atlanta. Authors indicated their preferred sites when submitting their proposals. To ensure consistent tutorial quality across all three, we reviewed all proposals centrally. The acceptance decision was based on the proposals’ scientific merit and presenters’ expertise in their proposed topics. Indications of preferred physical sites were used only after the initial acceptance list was made.

The physical site allocation of the tutorials was a multi-stage process:

  • We allocated the accepted tutorials with physical site constraints (i.e., only 1 site selected) to their specified site.
  • For the remaining accepted tutorials, we allocated the physical site by balancing authors’ preferences and the diversity of the tutorial topics at each physical site.
  • We thereafter notified the authors of the acceptance results and asked accepted tutorial authors to confirm the in-person attendance for the main speakers and additional participants.
  • At the final stage, a few authors informed us of new hard constraints on in-person attendance, and we reassigned their sites accordingly, accommodating all such requests.

Given the practical limitations of physical venues, we could only accept a limited number of tutorials, despite receiving many strong proposals. In total, we allocated 12 tutorials to the Sydney site (the conference’s main site, which has more capacity), 4 to Paris, and 3 to Atlanta. 

We sincerely thank all authors for the considerable time and effort they invested in preparing their submissions. If you have any questions or suggestions, please feel free to reach out to tutorial-chairs@neurips.cc.  

We look forward to seeing many of you at NeurIPS tutorials this year. 

List of NeurIPS 2026 accepted tutorials:

Sydney (12 tutorials)

  • Principles of Deep Representation Learning via Low-Dimensional Models
    • Yi Ma, Qing Qu, Peng Wang
  • From Heuristics to Guarantees: Bandit and RL Blueprint for Reliable Agentic-AI
    • Aadirupa Saha, Arun Verma, Djallel Bouneffouf
  • The Principles of Diffusion Models: Toward Fast and Scalable Diffusion LLMs
    • Chieh-Hsin Lai, Subham Sekhar Sahoo, Stefano Ermon
  • Tutorial on Causal Representation Learning
    • Julius von Kügelgen, Francesco Locatello, Kun Zhang
  • Empirical Design in Reinforcement Learning for Physical AI
    • Adam White, Martha White, Andrew Patterson
  • Three Geometric Lenses on Graph Machine Learning
    • Melanie Weber
  • Formal Guarantees for Frontier AI Systems
    • Gagandeep Singh, Isha Chaudhary, Nalin Wadhwa
  • Multi-Objective Optimization for Modern Machine Learning: Foundations, Recent Advances, and Emerging Applications
    • Jia Liu, Chaosheng Dong, Lisha Chen
  • From Scores to Evidence: Robust Evaluation of Foundation Models
    • Ana Gjorgjevikj, Barbara Korousic Seljak, Tome Eftimov
  • Uncertainty Quantification: From Detecting LLM Hallucinations to Strengthening Reasoning and AI Agents
    • Ekaterina Fadeeva, Maxim Panov, Artem Shelmanov
  • Distilling Reasoning: From Chain-of-Thought to Agentic Capabilities in Smaller Models
    • Akhil Arora, Vishrav Chaudhary
  • Neuro-Symbolic Learning in the Era of Large Language Models
    • Haoxuan Li, Lan-Zhe Guo, Wang-Zhou Dai

Paris (4 tutorials)

  • Time Series Foundation Models in Practice: From Forecasting to Classification and EEG Analysis
    • Thomas Moreau, Ievgen Redko, Theo Gnassounou
  • Economics of Generative AI
    • Ander Artola Velasco, Stratis Tsirtsis, Manuel Gomez Rodriguez
  • Performance Estimation Problems: Computer-Aided and AI-Assisted Analysis and Design of First-Order Optimization Methods
    • Aymeric Dieuleveut, Adrien Taylor
  • Generative AI and Stochastic Thermodynamics: A Tale of Free Energies
    • Lars Holdijk, Sirui Lu, Max Welling

Atlanta (3 tutorials)

  • Neuroevolution of Intelligent Agents 
    • Risto Miikkulainen
  • Towards Trustworthy Agentic AI: Interpretability, Safety, and Steering
    • Anshuman Chhabra, Ben Zhou, Muhao Chen
  • Towards The Science of Multi-Agent Communication
    • Yi Fang, Yu Zhang, Xuan Wang

NeurIPS 2026 Tutorial Track Chairs 

Quentin Berthet, Matthew Fahrbach, Yingzhen Li, Krikamol Muandet, Yisen Wang

Related Posts