Sebastian Pokutta

Artificial Intelligence, Optimization, and Machine Learning. Professor @TUBerlin, Vice President @ZuseInstitute, Chair @MATH+, Chair @MODAL

Research Lab

My group works on Artificial Intelligence, Optimization, and Machine Learning; from foundational algorithms to real-world systems. We develop new optimization and learning methods with a focus on efficiency and sustainability, combine learning with decision-making, and build agentic AI systems for complex tasks. A particular focus is on AI4Science and AI4Math, where we use AI to drive mathematical discovery and scientific insight. Recent examples include global forest monitoring from satellite data, entanglement certification via optimization, new constructions in extremal combinatorics, AI-assisted mathematical proofs, and AI for creativity and education. group homepage more about research and projects

TL;DR. We use computers to learn from data and make better decisions.

ETC. Hashed Commitments AI News

Prospective Students. If you are interested in working in our group or writing your MS/BS thesis please check our openings.

Select Recent Papers

(see publications for a complete list)

  1. Turan, B., Asadulla, S., Steinmann, D., Stammer, W., and Pokutta, S. (2026). Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] mlxai (Spotlight + Conference Proceedings)
  2. Muhtar, D., Song, X., Pokutta, S., Zimmer, M., Pelleriti, N., Hofmann, T., and Liu, S. (2026). When Does Sparsity Mitigate the Curse of Depth in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [code] llmmlsparsity
  3. Halbey, J., Deza, D., Zimmer, M., Roux, C., Stellato, B., and Pokutta, S. (2026). Lower Bounds for Frank-Wolfe on Strongly Convex Sets. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [summary] complexityfwlowerboundsopt
  4. Schiekiera, L., Zimmer, M., Roux, C., Pokutta, S., and Günther, F. (2026). From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs. Proceedings of the 43rd International Conference on Machine Learning (ICML). [arXiv] [summary] cognitivellmmlxai
  5. Pokutta, S. (2026). Frank-Wolfe Beyond 1/t Convergence. Preprint. [arXiv] complexityfwopt
  6. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). Faster Algorithms for Structured Matrix Multiplication via Flip Graph Search. Proceedings of the International Symposium on Symbolic and Algebraic Computation (ISSAC). [arXiv] compalgcomputational
  7. Zimmer, M., Pelleriti, N., Roux, C., and Pokutta, S. (2026). The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning. Preprint. [arXiv] [summary] [code] agenticai4mathml
  8. Xiao, W., Besançon, M., Gelß, P., Hendrych, D., Klus, S., and Pokutta, S. (2026). Graph Isomorphism: Mixed-Integer Convex Optimization from First-Order Methods. To Appear in Proceedings of CPAIOR. [arXiv] computationalgraphsmipopt
  9. Pauls, J., Schrödter, K., Ligensa, S., Schwartz, M., Turan, B., Zimmer, M., Saatchi, S., Pokutta, S., Ciais, P., and Gieseke, F. (2026). ECHOSAT: Estimating Canopy Height Over Space And Time. Preprint. [arXiv] [code] [visuals] ai4sciencemlsustainability
  10. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Patchworked Curves of Degree Seven. Preprint. [arXiv] ai4mathalggeomcombinatoricscompalg
  11. Berthold, T., Kamp, D., Mexi, G., Pokutta, S., and Pólik, I. (2026). Global Optimization for Combinatorial Geometry Problems Revisited in the Era of LLMs. To Appear in Proceedings of ISCO, Lecture Notes in Computer Science. [arXiv] computationalllmnlpopt
  12. Pelleriti, N., Spiegel, C., Liu, S., Martínez-Rubio, D., Zimmer, M., and Pokutta, S. (2026). Neural Sum-of-Squares: Certifying the Nonnegativity of Polynomials with Transformers. To Appear in Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] ai4mathcompalgml
  13. Haase, J., and Pokutta, S. (2026). The Hidden Cost of Tokenization: Why (most) Non-English Speakers Pay More for Less. Preprint. [arXiv] fairnessllmmlmultilingual
  14. Roux, C., Zimmer, M., d’Aspremont, A., and Pokutta, S. (2025). Don’t Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe. Preprint. [arXiv] fwllmmloptpruningsparsity
  15. Gonnermann-Müller, J., Haase, J., Fackeldey, K., and Pokutta, S. (2025). FACET: Teacher-Centred LLM-Based Multi-Agent Systems – Towards Personalized Educational Worksheets. Preprint. [arXiv] educationhaiillmmlmultiagent
  16. Haase, J., and Pokutta, S. (2025). Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research. Preprint. [arXiv] haiimlsocial
  17. Braun, G., Carderera, A., Combettes, C. W., Hassani, H., Karbasi, A., Mokthari, A., and Pokutta, S. (2025). Conditional Gradient Methods. MOS-SIAM Series on Optimization. [PDF] [arXiv] mloptsurvey
  18. Abbas, A., Ambainis, A., Augustino, B., Bärtschi, A., Buhrman, H., Coffrin, C., Cortiana, G., Dunjko, V., Egger, D. J., Elmegreen, B. G., Franco, N., Fratini, F., Fuller, B., Gacon, J., Gonciulea, C., Gribling, S., Gupta, S., Hadfield, S., Heese, R., … Zoufal, C. (2024). Quantum Optimization: Potential, Challenges, and the Path Forward. Nature Reviews Physics. [PDF] [arXiv] optphysicsquantumsurvey
  19. Pokutta, S. (2024). The Frank-Wolfe algorithm: a short introduction. Jahresbericht Der Deutschen Mathematiker-Vereinigung, 126, 3–35. [PDF] [arXiv] mlopt

Select Recent Talks and Teaching

(see archive for a complete list)

Recent Blog Posts

Select Outreach

(see archive for a complete list)

News

(see archive for a complete list)