Sebastian Pokutta

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

Research Lab

My group is interested in Artificial Intelligence, Optimization, and Machine Learning and its applications. We develop new methodologies (e.g., new optimization and learning algorithms), work on combining learning and decision-making, as well as design AI Systems for real-world deployment in various application contexts. Recent examples include the estimation of biomass from satellite data, entanglement and non-locality thresholds via optimization, new constructions in extremal combinatorics via AI, as well as questions around AI and creativity. 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. 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. Preprint. [arXiv] cognitivellmmlxai
  2. Leins, N., Gonnermann-Müller, J., Teichmann, M., and Pokutta, S. (2026). Investigating the Influence of Spatial Ability in Augmented Reality-assisted Robot Programming. Preprint. [arXiv] arhrimlrobotics
  3. Gonnermann-Müller, J., Haase, J., Leins, N., Kosch, T., and Pokutta, S. (2026). Stable Personas: Dual-Assessment of Temporal Stability in LLM-Based Human Simulation. Preprint. [arXiv] haiillmmlmultiagentsocial
  4. Haase, J., and Pokutta, S. (2026). The Hidden Cost of Tokenization: Why (most) Non-English Speakers Pay More for Less. Preprint. [arXiv] fairnessllmmlmultilingual
  5. Haase, J., Gonnermann-Müller, J., and Pokutta, S. (2026). Building Socially Grounded Multi-Agent LLM Systems Requires the Transition from Static LLM Prompting to Autonomous Multi-Agent Ecosystems. Preprint. [arXiv] haiillmmlmultiagentsocial
  6. Haase, J., Gonnermann-Müller, J., Hanel, P. H. P., Leins, N., Kosch, T., Mendling, J., and Pokutta, S. (2026). Within-Model vs Between-Prompt Variability in Large Language Models for Creative Tasks. Preprint. [arXiv] creativityhaiillmml
  7. Leins, N., Gonnermann-Müller, J., Teichmann, M., and Pokutta, S. (2026). Beyond Static Instruction: A Multi-Agent AI Framework for Adaptive Augmented Reality Robot Training. To Appear in Proceedings of ACM/IEEE International Conference on Human-Robot Interaction (HRI), Late-Breaking Reports. arhrimlrobotics
  8. Berthold, T., Kamp, D., Mexi, G., Pokutta, S., and Pólik, I. (2026). Global Optimization for Combinatorial Geometry Problems Revisited in the Era of LLMs. Preprint. [arXiv] computationalllmnlpopt
  9. Kerdreux, T., Scieur, D., Martinez-Rubio, D., d’Aspremont, A., and Pokutta, S. (2026). Strong Convexity of Sets in Riemannian Manifolds. Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] mlopt
  10. Gonnermann-Müller, J., Haase, J., Leins, N., Igel, M., Fackeldey, K., and Pokutta, S. (2026). FACET: Multi-Agent AI Supporting Teachers in Scaling Differentiated Learning for Diverse Students. Preprint. [arXiv] educationhaiillmmlmultiagent
  11. 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. Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] ai4mathcompalgml
  12. Iommazzo, G., Martínez-Rubio, D., Criado, F., Wirth, E., and Pokutta, S. (2026). Linear Convergence of the Frank-Wolfe Algorithm over Product Polytopes. To Appear in Proceedings of AISTATS. [arXiv] mlopt
  13. Urbano, A., Romero, D. W., Zimmer, M., and Pokutta, S. (2026). RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization. Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] mlsymmetry
  14. Takahashi, S., Pokutta, S., and Takeda, A. (2026). Accelerated Convergence of Frank–Wolfe Algorithms with Adaptive Bregman Step-Size Strategy. Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] fwopt
  15. Martínez-Rubio, D., and Pokutta, S. (2026). Beyond Short Steps in Frank-Wolfe Algorithms. Proceedings of the International Conference on Learning Representations (ICLR). [arXiv] mlopt
  16. Haase, J., and Pokutta, S. (2026). Human–AI Cocreativity: Exploring synergies across levels of creative collaboration. In J. C. Kaufman & M. Worwood (Eds.), Generative Artificial Intelligence and Creativity (pp. 205–221). [PDF] [arXiv] creativityhaiimlsocial
  17. Xiao, W., Besançon, M., Gelß, P., Hendrych, D., Klus, S., and Pokutta, S. (2025). Graph Isomorphism: Mixed-Integer Convex Optimization from First-Order Methods. Preprint. [arXiv] computationalgraphmipopt
  18. Zimmer, M., Roux, C., Wagner, M., Hendrych, D., and Pokutta, S. (2025). SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale. Preprint. [arXiv] llmmlpruningsparsity
  19. Kuzinowicz, D., Lichocki, P., Mexi, G., Pfetsch, M. E., Pokutta, S., and Zimmer, M. (2025). Objective Coefficient Rounding and Almost Symmetries in Binary Programs. Preprint. [arXiv] computationalmipoptsymmetry
  20. Hojny, C., Besançon, M., Bestuzheva, K., Borst, S., Chmiela, A., Dionísio, J., Eifler, L., Ghannam, M., Gleixner, A., Göß, A., Hoen, A., van der Hulst, R., Kamp, D., Koch, T., Kofler, K., Lentz, J., Maher, S. J., Mexi, G., Mühmer, E., … Xu, L. (2025). The SCIP Optimization Suite 10.0. Preprint. [arXiv] computationalipoptsoftware
  21. Xu, L., Liu, Y.-C., and Pokutta, S. (2025). Convex semidefinite tensor optimization and quantum entanglement. Preprint. [arXiv] optquantum
  22. Khoruzhii, K., Gelß, P., and Pokutta, S. (2025). Faster Algorithms for Structured Matrix Multiplication via Flip Graph Search. Preprint. [arXiv] compalgcomputational
  23. 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
  24. Wagner, M., Roux, C., Zimmer, M., and Pokutta, S. (2025). A Free Lunch in LLM Compression: Revisiting Retraining after Pruning. Preprint. [arXiv] llmmlpruningsparsity
  25. 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
  26. Haase, J., Hanel, P. H. P., and Pokutta, S. (2025). S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment. Proceedings of the 8th AAAI/ACM Conference on AI, Ethics, and Society (AIES), 8(2), 1194–1205. [PDF] [arXiv] [slides] [poster] creativityhaiimlsocial
  27. Liu, Y.-C., Halbey, J., Pokutta, S., and Designolle, S. (2025). A Unified Toolbox for Multipartite Entanglement Certification. Preprint. [arXiv] optphysicsquantum
  28. Haase, J., and Pokutta, S. (2025). Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research. Preprint. [arXiv] haiimlsocial
  29. Porto, L. E. A., Designolle, S., Pokutta, S., and Quintino, M. T. (2025). Measurement incompatibility and quantum steering via linear programming. Preprint. [arXiv] optphysicsquantum
  30. Mundinger, K., Zimmer, M., Kiem, A., Spiegel, C., and Pokutta, S. (2025). Neural Discovery in Mathematics: Do Machines Dream of Colored Planes? Proceedings of the 42nd International Conference on Machine Learning (ICML), 267, 45236–45255. [PDF] [arXiv] ai4mathai4sciencedggraphs (Oral Presentation + Conference Proceedings)
  31. Wirth, E., Peña, J., and Pokutta, S. (2025). Adaptive Open-Loop Step-Sizes for Accelerated Convergence Rates of the Frank-Wolfe Algorithm. Preprint. [arXiv] mlopt
  32. 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
  33. 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
  34. 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

Recent Blog Posts

Select Outreach

News