Seminar will run in English (Czech on demand) and it will be organized as a series of Oxford-style debates on various AI-related topics (the topics discussed in recent years can be found at the seminar history page). Each side of the debate will be represented by two students (two "for" and two "against") pluse there will be a moderator. The side to which a student is allocated does not necessarily reflect his/her personal opinion!

Between the Oxford Debates we will include presentations of papers by students.

To get the credit, student is supposed to participate in one debate, to give one presentation, and to actively participate in at least ten seminars (two more seminars may be missed in exchange for a written report).

Oxford debate schedule:

• prior debate:
  • Each side is requested to send one reference (web link, paper, etc.) to the teacher at least one week before the debate and this reference will be publicly available through the seminar web page.
• debate day (Wednesday):
  • introduction of the topic by the moderator (5-10 minutes)
  • initial anonymous voting of audience (the result will be revealed after the discussion)
  • opening remarks (each speaker will have 2 minutes for the initial statement supporting his/her side; the order of sides is selected randomly at the beginning, speakers from both sides speak on a rota basis)
  • intra-panel discussion (between the speakers and the moderator with chance to react to the other side; 10-20 minutes)
  • Q&A (questions/comments from the audience with response from the speakers;  20-30 minutes)
  • closing remarks (each speaker will have 1 minute; the order is reverse to the opening order)
  • final anonymous voting of audience
  • decision of the winner (the side with the increase of number of votes wins)

Some examples of papers for presentation:

1. Chad Hogg, Hector Munoz-Avila, and Ugur Kuter: HTN-Maker: Learning HTNs with Minimal Additional Knowledge Engineering Required. In Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (AAAI-08). AAAI Press.
2. Pat Langley: Learning Hierarchical Problem Networks for Knowledge-Based Planning. ILP 2022: 69-83
3. Songtuan Lin, Daniel Höller, Pascal Bercher: Modeling Assistance for Hierarchical Planning: An Approach for Correcting Hierarchical Domains with Missing Actions. SOCS 2024: 55-63
4. Songtuan Lin, Alban Grastien, Pascal Bercher: Towards Automated Modeling Assistance: An Efficient Approach for Repairing Flawed Planning Domains. AAAI 2023: 12022-12031
5. D. Nau, T.-C. Au, O. Ilghami, U. Kuter, W. Murdock, D. Wu, and F.Yaman: SHOP2: An HTN Planning System. JAIR, volume 20, pp. 379-404, 2003.
6. Pascal Bercher, Shawn Keen, Susanne Biundo: Hybrid Planning Heuristics Based on Task Decomposition Graphs. SOCS 2014: 35-43
7. Robert P. Goldman, Ugur Kuter, and Richard G. Freedman. Stable plan repair for state-space HTN planning. HPlan Workshop 2020
8. Pascal Bercher, Ron Alford, Daniel Höller: A Survey on Hierarchical Planning - One Abstract Idea, Many Concrete Realizations. IJCAI 2019: 6267-6275
9. Keisuke Okumura: LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding. AAAI 2023: 11655-11662
10. J. Li, Z. Chen, Y. Zheng, S.-H. Chan, D. Harabor, P. Stuckey, H. Ma and S. Koenig. Scalable Rail Planning and Replanning: Winning the 2020 Flatland Challenge. In Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), 477-485, 2021.
11. Subbarao Kambhampati: Can Large Language Models Reason and Plan? Annals of New York Academy of Sciences. March 2024.
12. Karthik Valmeekam, Matthew Marquez, Sarath Sreedharan, Subbarao Kambhampati: On the Planning Abilities of Large Language Models -- A Critical Investigation. NeurIPS 2023.
13. Karthik Valmeekam, Kaya Stechly, Subbarao Kambhampati: LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench, Preprint on Arxiv, Sept 2024.
14. Iman Mirzadeh, Keivan Alizadeh, Hooman Shahrokhi, Oncel Tuzel, Samy Bengio, Mehrdad Farajtabar: GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models. arXiv:2410.05229
15. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin: Attention Is All You Need. CoRR abs/1706.03762 (2017)
16. Yi Tay, Mostafa Dehghani, Dara Bahri, Donald Metzler: Efficient Transformers: A Survey. CoRR abs/2009.06732 (2020)
17. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, Harsha Nori, Hamid Palangi, Marco Tulio Ribeiro, Yi Zhang: Sparks of Artificial General Intelligence: Early experiments with GPT-4. CoRR abs/2303.12712 (2023)
18. Yann LeCun: A Path Towards Autonomous Machine Intelligence, OpenReview.net, 2022