Float8@2bits: Entropy Coding Enables Data-Free Model Compression.

Sebastian Schulze

Patrick Putzky Martin Genzel Mattes Mollenhauer Sebastian Schulze Thomas Wollmann Stefan Dietzel Float8@2bits: Entropy Coding Enables Data-Free Model Compression. 2026 January abs/2601.22787 CoRR https://doi.org/10.48550/arXiv.2601.22787 db/journals/corr/corr2601.html#abs-2601-22787 streams/journals/corr

Martin Genzel Patrick Putzky Pengfei Zhao Sebastian Schulze Mattes Mollenhauer Robert Seidel Stefan Dietzel Thomas Wollmann Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=Y6hdYf8tsg db/journals/tmlr/tmlr2025.html#GenzelPZSMSDW25 streams/journals/tmlr

Martin Genzel Patrick Putzky Pengfei Zhao Sebastian Schulze Mattes Mollenhauer Robert Seidel Stefan Dietzel Thomas Wollmann Choose Your Model Size: Any Compression by a Single Gradient Descent. 2025 February abs/2502.01717 CoRR https://doi.org/10.48550/arXiv.2502.01717 db/journals/corr/corr2502.html#abs-2502-01717 streams/journals/corr

Julien Siems Maximilian Schambach Sebastian Schulze Johannes S. Otterbach Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management. 2023 abs/2303.10382 CoRR https://doi.org/10.48550/arXiv.2303.10382 db/journals/corr/corr2303.html#abs-2303-10382

Saad Hamid Sebastian Schulze Michael A. Osborne Stephen J. Roberts Marginalising over Stationary Kernels with Bayesian Quadrature. 9776-9792 2022 AISTATS https://proceedings.mlr.press/v151/hamid22a.html conf/aistats/2022 db/conf/aistats/aistats2022.html#HamidSOR22

Luisa M. Zintgraf Sebastian Schulze Cong Lu Leo Feng Maximilian Igl Kyriacos Shiarlis Yarin Gal Katja Hofmann Shimon Whiteson VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning. 289:1-289:39 2021 22 J. Mach. Learn. Res. https://jmlr.org/papers/v22/21-0657.html db/journals/jmlr/jmlr22.html#ZintgrafSLFISGH21

Saad Hamid Sebastian Schulze Michael A. Osborne Stephen J. Roberts Marginalising over Stationary Kernels with Bayesian Quadrature. 2021 abs/2106.07452 CoRR https://arxiv.org/abs/2106.07452 db/journals/corr/corr2106.html#abs-2106-07452

Luisa M. Zintgraf Kyriacos Shiarlis Maximilian Igl Sebastian Schulze Yarin Gal Katja Hofmann Shimon Whiteson VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning. 2020 ICLR https://openreview.net/forum?id=Hkl9JlBYvr conf/iclr/2020 db/conf/iclr/iclr2020.html#ZintgrafSISGHW20 Vu Nguyen Sebastian Schulze Michael A. Osborne Bayesian Optimization for Iterative Learning. 2020 NeurIPS https://proceedings.neurips.cc/paper/2020/hash/69eba34671b3ef1ef38ee85caae6b2a1-Abstract.html conf/nips/2020 db/conf/nips/neurips2020.html#NguyenSO20

Vu Nguyen Sebastian Schulze Michael A. Osborne Bayesian Optimization for Iterative Learning. 2019 abs/1909.09593 CoRR http://arxiv.org/abs/1909.09593 db/journals/corr/corr1909.html#abs-1909-09593

Sebastian Schulze Owain Evans Active Reinforcement Learning with Monte-Carlo Tree Search. 2018 abs/1803.04926 CoRR http://arxiv.org/abs/1803.04926 db/journals/corr/corr1803.html#abs-1803-04926

Stefan Dietzel Owain Evans Leo Feng Yarin Gal Martin Genzel Saad Hamid Katja Hofmann Maximilian Igl Cong Lu Mattes Mollenhauer Vu Nguyen Michael A. Osborne Johannes S. Otterbach Patrick Putzky Stephen J. Roberts Maximilian Schambach Robert Seidel Kyriacos Shiarlis Julien Siems Shimon Whiteson Thomas Wollmann Pengfei Zhao Luisa M. Zintgraf