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. Koshizuka, T., Blessing, D., Zimmer, M., Pokutta, S., and Richter, L. (2026). A Trust Region Approach for Learning Schrödinger Bridges. To Appear in Proceedings of NeurIPS. mloptprobability
  2. 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. To Appear in Proceedings of NeurIPS. [arXiv] creativityhaiillmml
  3. Halbey, J., Roux, C., and Pokutta, S. (2026). Curvature-Dependent Lower Bounds for Frank-Wolfe. To Appear in Proceedings of NeurIPS. [arXiv] complexityfwlowerboundsopt
  4. Pokutta, S. (2026). Frank-Wolfe Beyond 1/t Convergence. To Appear in Proceedings of NeurIPS. [arXiv] complexityfwopt
  5. Wagner, M., Roux, C., Zimmer, M., and Pokutta, S. (2026). A Free Lunch in LLM Compression: Revisiting Retraining after Pruning. To Appear in Proceedings of NeurIPS. [arXiv] llmmlpruningsparsity
  6. Geiselmann, Z., Joswig, M., Kastner, L., Mundinger, K., Pokutta, S., Spiegel, C., Wack, M., and Zimmer, M. (2026). Limits of Combinatorial Patchworking. Preprint. [arXiv] ai4mathalggeomcombinatoricscompalg
  7. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). The Weight Distribution of the Third-Order Reed-Muller Code of Length 2048. Preprint. [arXiv] algebracombinatoricscompalginformationtheory
  8. Deza, A., Gerard, Y., Ma, Y., and Pokutta, S. (2026). Bounded-Support Additive Latin Transversals via Color-Counted Matching. Preprint. [arXiv] combinatoricsgraphs
  9. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Proceedings of the 3rd ICML Workshop on AI for Mathematics (AI4Math). [visuals] agenticai4mathevaluationllmml
  10. 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. Proceedings of the 3rd ICML Workshop on AI for Mathematics (AI4Math). [PDF] [arXiv] [code] agenticai4mathml
  11. Zhou, Z., Li, Z., Huang, W., Li, X., Cao, C., Feng, X., Lu, X., Hu, J., Lu, M., Xie, Y., Pelleriti, N., Liu, S., Zimmer, M., Miranda, B., Yao, J., Liu, B., Koyejo, S., Pokutta, S., and Han, B. (2026). Reasoning Is More Than the Model: Harness-Aware Evaluation of Agents on Verifiable Reasoning Tasks. Proceedings of the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research). [visuals] agenticevaluationllmml
  12. 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. Proceedings of the ICML 2026 Workshop on AI as a Tool for Mathematics, Computer Science, and Machine Learning (AI4Research). [PDF] [arXiv] [summary] [code] agenticai4mathml (Oral Presentation + Workshop)
  13. Haase, J., Gonnermann-Müller, J., Yim, S. H., Leins, N., Mendling, J., and Pokutta, S. (2026). Simulating Eating Disorder Patients with LLMs: Evaluating Psychological Persona Stability in Multi-Turn Conversations. Preprint. [arXiv] haiillmmlmultiagentsocial
  14. Khoruzhii, K., Gelß, P., and Pokutta, S. (2026). Classification of Boolean Cubic Forms in Ten Variables. Preprint. [arXiv] algebracombinatoricscompalg
  15. Kaibel, V., and Pokutta, S. (2026). A Counterexample to Ziegler’s Cross-Polytope Conjecture for Simplicial 0/1-Polytopes. Preprint. [arXiv] combinatoricsopt
  16. Pokutta, S. (2026). Symmetric Extension Complexity of the Spanning Tree Polytope. Preprint. [arXiv] extendedformulationipopt
  17. 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
  18. Haase, J., and Pokutta, S. (2026). Structured Creativity Methods for Multi-Agent LLMs: Brainwriting Outperforms Disney and Double Diamond. Proceedings of ICML 2026 Workshop on Human-AI Co-Creativity (GenAICreativity). creativityllmmlmulti-agent
  19. Haase, J., and Pokutta, S. (2026). The Missing Drive: Functional Analogs of Intrinsic Motivation in Large Language Models for Creative Tasks. Proceedings of ICML 2026 Workshop on Human-AI Co-Creativity (GenAICreativity). creativityllmml
  20. Pelleriti, N., Nelaturu, S. H., Zhou, Z., Li, Z., Zimmer, M., Han, B., and Pokutta, S. (2026). What Do Evolutionary Coding Agents Evolve? Preprint. [arXiv] agenticllmmlneuro-compute
  21. 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
  22. 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
  23. Turan, B., Asadulla, S., Steinmann, D., Kersting, K., 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] [summary] mlxai (Spotlight + Conference Proceedings)
  24. 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). [PDF] [arXiv] compalgcomputational (Distinguished Student Author Award at ISSAC 2026)
  25. 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
  26. 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
  27. Haase, J., and Pokutta, S. (2026). The Hidden Cost of Tokenization: Why (most) Non-English Speakers Pay More for Less. Preprint. [arXiv] [summary] fairnessllmmlmultilingual
  28. 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
  29. 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
  30. 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)

  • 09/2026: (technical) “Frank-Wolfe Beyond Polytopes: Convergence on Non-Polyhedral Sets”. Plenary at OR2026 - Annual Meeting of the German Operations Research Society (GOR) (Passau, Germany). [slides]
  • 07/2026: (technical) “Frank-Wolfe on Curved Domains: Unconditional o(1/t) Convergence and Tight Lower Bounds”. Talk at 65th School of Engineering Special Lecture (Tokyo, Japan). [slides]
  • 07/2026: (technical) “The Agentic Researcher: Accelerating Optimization and Learning Research with AI”. Talk at AI4Science seminar (Online (Zoom)). [slides]
  • 07/2026: (technical) “The Agentic Researcher: Accelerating Optimization and Learning Research with AI”. Talk at HORIZONS 2026: Learning and Optimization for a Sustainable Future (Hanoi, Vietnam). [slides]
  • 06/2026: (technical) “When Algorithms Learn: Discrete Optimization Meets Machine Learning”. Talk at Oberseminar Angewandte Mathematik (Magdeburg, Germany).
  • SS/2026: Discrete Optimization and Machine Learning (seminar)

Recent Blog Posts

Select Outreach

(see archive for a complete list)

News

(see archive for a complete list)