On the Challenges and Opportunities in Generative AI.

Robert Bamler

Laura Manduchi Clara Meister Kushagra Pandey Robert Bamler Ryan Cotterell Sina Däubener Sophie Fellenz Asja Fischer Thomas Gärtner 0004 Matthias Kirchler Marius Kloft Yingzhen Li Christoph Lippert Gerard de Melo Eric T. Nalisnick Björn Ommer Rajesh Ranganath Maja Rudolph Karen Ullrich Guy Van den Broeck Julia E. Vogt Yixin Wang Florian Wenzel Frank Wood Stephan Mandt Vincent Fortuin On the Challenges and Opportunities in Generative AI. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=NeS9Kj2JwF db/journals/tmlr/tmlr2025.html#ManduchiMPBCDFFGKKLLMNO25 streams/journals/tmlr

Tim Z. Xiao Robert Bamler Bernhard Schölkopf Weiyang Liu Verbalized Machine Learning: Revisiting Machine Learning with Language Models. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=k3Ab6RuJE9 db/journals/tmlr/tmlr2025.html#XiaoBSL25

Tim Z. Xiao Johannes Zenn Robert Bamler A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data and Overparameterization? 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=bwyHf5eery db/journals/tmlr/tmlr2025.html#XiaoZB25

Andi Zhang 0001 Tim Z. Xiao Weiyang Liu Robert Bamler Damon Wischik Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector. 2701-2709 2025 AISTATS https://proceedings.mlr.press/v258/zhang25h.html conf/aistats/2025 db/conf/aistats/aistats2025.html#ZhangXLBW25 streams/conf/aistats Tristan Cinquin Robert Bamler Well-Defined Function-Space Variational Inference in Bayesian Neural Networks via Regularized KL-Divergence. 752-776 2025 UAI https://proceedings.mlr.press/v286/cinquin25a.html conf/uai/2025 db/conf/uai/uai2025.html#CinquinB25 streams/conf/uai

Alexander Conzelmann Robert Bamler Reducing Storage of Pretrained Neural Networks by Rate-Constrained Quantization and Entropy Coding. 2025 May abs/2505.18758 CoRR https://doi.org/10.48550/arXiv.2505.18758 db/journals/corr/corr2505.html#abs-2505-18758 streams/journals/corr

Tim Z. Xiao Johannes Zenn Zhen Liu 0019 Weiyang Liu Robert Bamler Bernhard Schölkopf Flipping Against All Odds: Reducing LLM Coin Flip Bias via Verbalized Rejection Sampling. 2025 June abs/2506.09998 CoRR https://doi.org/10.48550/arXiv.2506.09998 db/journals/corr/corr2506.html#abs-2506-09998 streams/journals/corr

Hanqi Zhou Robert Bamler Charley M. Wu Álvaro Tejero-Cantero Predictive, scalable and interpretable knowledge tracing on structured domains. 2024 ICLR https://openreview.net/forum?id=NgaLU2fP5D conf/iclr/2024 db/conf/iclr/iclr2024.html#ZhouBWT24 Johannes Zenn Robert Bamler Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution. 2024 ICML https://proceedings.mlr.press/v235/zenn24a.html https://openreview.net/forum?id=rvaN2P1rvC conf/icml/2024 db/conf/icml/icml2024.html#ZennB24 58448-58469 Tristan Cinquin Marvin Pförtner Vincent Fortuin Philipp Hennig Robert Bamler FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. 2024 NeurIPS http://papers.nips.cc/paper_files/paper/2024/hash/19774ce2d4b0d17a3a8aea26ad99fe8a-Abstract-Conference.html conf/nips/2024 db/conf/nips/neurips2024.html#CinquinPFHB24

Tim Z. Xiao Weiyang Liu Robert Bamler A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry. 2024 abs/2401.00611 CoRR https://doi.org/10.48550/arXiv.2401.00611 db/journals/corr/corr2401.html#abs-2401-00611

Laura Manduchi Kushagra Pandey Robert Bamler Ryan Cotterell Sina Däubener Sophie Fellenz Asja Fischer Thomas Gärtner 0004 Matthias Kirchler Marius Kloft Yingzhen Li Christoph Lippert Gerard de Melo Eric T. Nalisnick Björn Ommer Rajesh Ranganath Maja Rudolph Karen Ullrich Guy Van den Broeck Julia E. Vogt Yixin Wang Florian Wenzel Frank Wood Stephan Mandt Vincent Fortuin On the Challenges and Opportunities in Generative AI. 2024 abs/2403.00025 CoRR https://doi.org/10.48550/arXiv.2403.00025 db/journals/corr/corr2403.html#abs-2403-00025

Hanqi Zhou Robert Bamler Charley M. Wu Álvaro Tejero-Cantero Predictive, scalable and interpretable knowledge tracing on structured domains. 2024 abs/2403.13179 CoRR https://doi.org/10.48550/arXiv.2403.13179 db/journals/corr/corr2403.html#abs-2403-13179

Andi Zhang 0001 Tim Z. Xiao Weiyang Liu Robert Bamler Damon Wischik Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector. 2024 abs/2404.08679 CoRR https://doi.org/10.48550/arXiv.2404.08679 db/journals/corr/corr2404.html#abs-2404-08679

Johannes Zenn Robert Bamler Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution. 2024 abs/2405.14840 CoRR https://doi.org/10.48550/arXiv.2405.14840 db/journals/corr/corr2405.html#abs-2405-14840

Tristan Cinquin Robert Bamler Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian neural networks. 2024 abs/2406.04317 CoRR https://doi.org/10.48550/arXiv.2406.04317 db/journals/corr/corr2406.html#abs-2406-04317

Tim Z. Xiao Robert Bamler Bernhard Schölkopf Weiyang Liu Verbalized Machine Learning: Revisiting Machine Learning with Language Models. 2024 abs/2406.04344 CoRR https://doi.org/10.48550/arXiv.2406.04344 db/journals/corr/corr2406.html#abs-2406-04344

Johannes Zenn Dominik Gond Fabian Jirasek Robert Bamler Balancing Molecular Information and Empirical Data in the Prediction of Physico-Chemical Properties. 2024 abs/2406.08075 CoRR https://doi.org/10.48550/arXiv.2406.08075 db/journals/corr/corr2406.html#abs-2406-08075

Tristan Cinquin Marvin Pförtner Vincent Fortuin Philipp Hennig Robert Bamler FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning. 2024 abs/2407.13711 CoRR https://doi.org/10.48550/arXiv.2407.13711 db/journals/corr/corr2407.html#abs-2407-13711 streams/journals/corr

Tim Z. Xiao Robert Bamler Trading Information between Latents in Hierarchical Variational Autoencoders. 2023 ICLR https://openreview.net/forum?id=eWtMdr6yCmL conf/iclr/2023 db/conf/iclr/iclr2023.html#XiaoB23 Johannes Zenn Robert Bamler Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers. 2023 Tiny Papers @ ICLR https://openreview.net/forum?id=kBkou5ucR_d conf/iclr/2023tiny db/conf/iclr/iclr2023tiny.html#ZennB23

Tim Z. Xiao Robert Bamler Trading Information between Latents in Hierarchical Variational Autoencoders. 2023 abs/2302.04855 CoRR https://doi.org/10.48550/arXiv.2302.04855 db/journals/corr/corr2302.html#abs-2302-04855

Johannes Zenn Robert Bamler Resampling Gradients Vanish in Differentiable Sequential Monte Carlo Samplers. 2023 abs/2304.14390 CoRR https://doi.org/10.48550/arXiv.2304.14390 db/journals/corr/corr2304.html#abs-2304-14390

Tim Z. Xiao Johannes Zenn Robert Bamler Upgrading VAE Training With Unlimited Data Plans Provided by Diffusion Models. 2023 abs/2310.19653 CoRR https://doi.org/10.48550/arXiv.2310.19653 db/journals/corr/corr2310.html#abs-2310-19653

Tim Z. Xiao Johannes Zenn Robert Bamler The SVHN Dataset Is Deceptive for Probabilistic Generative Models Due to a Distribution Mismatch. 2023 abs/2312.02168 CoRR https://doi.org/10.48550/arXiv.2312.02168 db/journals/corr/corr2312.html#abs-2312-02168

Robert Bamler Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspective. 2022 abs/2201.01741 CoRR https://arxiv.org/abs/2201.01741 db/journals/corr/corr2201.html#abs-2201-01741

Robert Bamler Stephan Mandt Extreme Classification via Adversarial Softmax Approximation. 2020 ICLR https://openreview.net/forum?id=rJxe3xSYDS conf/iclr/2020 db/conf/iclr/iclr2020.html#BamlerM20 Yibo Yang Robert Bamler Stephan Mandt Variational Bayesian Quantization. 10670-10680 2020 ICML http://proceedings.mlr.press/v119/yang20a.html conf/icml/2020 db/conf/icml/icml2020.html#YangBM20 Alex Boyd Robert Bamler Stephan Mandt Padhraic Smyth User-Dependent Neural Sequence Models for Continuous-Time Event Data. 2020 NeurIPS https://proceedings.neurips.cc/paper/2020/hash/f56de5ef149cf0aedcc8f4797031e229-Abstract.html conf/nips/2020 db/conf/nips/neurips2020.html#BoydBMS20 Yibo Yang Robert Bamler Stephan Mandt Improving Inference for Neural Image Compression. 2020 NeurIPS https://proceedings.neurips.cc/paper/2020/hash/066f182b787111ed4cb65ed437f0855b-Abstract.html conf/nips/2020 db/conf/nips/neurips2020.html#YangBM20

Robert Bamler Stephan Mandt Extreme Classification via Adversarial Softmax Approximation. 2020 abs/2002.06298 CoRR https://arxiv.org/abs/2002.06298 db/journals/corr/corr2002.html#abs-2002-06298

Yibo Yang Robert Bamler Stephan Mandt Variable-Bitrate Neural Compression via Bayesian Arithmetic Coding. 2020 abs/2002.08158 CoRR https://arxiv.org/abs/2002.08158 db/journals/corr/corr2002.html#abs-2002-08158

Yibo Yang Robert Bamler Stephan Mandt Improving Inference for Neural Image Compression. 2020 abs/2006.04240 CoRR https://arxiv.org/abs/2006.04240 db/journals/corr/corr2006.html#abs-2006-04240

Alex Boyd Robert Bamler Stephan Mandt Padhraic Smyth User-Dependent Neural Sequence Models for Continuous-Time Event Data. 2020 abs/2011.03231 CoRR https://arxiv.org/abs/2011.03231 db/journals/corr/corr2011.html#abs-2011-03231

Robert Bamler Farnood Salehi Stephan Mandt Augmenting and Tuning Knowledge Graph Embeddings. 508-518 2019 UAI http://proceedings.mlr.press/v115/bamler20a.html http://auai.org/uai2019/proceedings/papers/172.pdf conf/uai/2019 db/conf/uai/uai2019.html#BamlerSM19

Robert Bamler Farnood Salehi Stephan Mandt Augmenting and Tuning Knowledge Graph Embeddings. 2019 abs/1907.01068 CoRR http://arxiv.org/abs/1907.01068 db/journals/corr/corr1907.html#abs-1907-01068

Robert Bamler Stephan Mandt A Quantum Field Theory of Representation Learning. 2019 abs/1907.02163 CoRR http://arxiv.org/abs/1907.02163 db/journals/corr/corr1907.html#abs-1907-02163

Robert Bamler Cheng Zhang 0005 Manfred Opper Stephan Mandt Tightening Bounds for Variational Inference by Revisiting Perturbation Theory. 2019 abs/1910.00069 CoRR http://arxiv.org/abs/1910.00069 db/journals/corr/corr1910.html#abs-1910-00069

Robert Bamler Stephan Mandt Improving Optimization in Models With Continuous Symmetry Breaking. 432-441 2018 ICML http://proceedings.mlr.press/v80/bamler18a.html conf/icml/2018 db/conf/icml/icml2018.html#BamlerM18

Robert Bamler Stephan Mandt Improving Optimization in Models With Continuous Symmetry Breaking. 2018 abs/1803.03234 CoRR http://arxiv.org/abs/1803.03234 db/journals/corr/corr1803.html#abs-1803-03234

Robert Bamler Stephan Mandt Dynamic Word Embeddings. 380-389 2017 ICML http://proceedings.mlr.press/v70/bamler17a.html conf/icml/2017 db/conf/icml/icml2017.html#BamlerM17 Robert Bamler Cheng Zhang 0005 Manfred Opper Stephan Mandt Perturbative Black Box Variational Inference. 5079-5088 2017 NIPS https://proceedings.neurips.cc/paper/2017/hash/b75bd27b5a48a1b48987a18d831f6336-Abstract.html http://papers.nips.cc/paper/7093-perturbative-black-box-variational-inference conf/nips/2017 db/conf/nips/nips2017.html#BamlerZOM17

Robert Bamler Stephan Mandt Dynamic Word Embeddings via Skip-Gram Filtering. 2017 abs/1702.08359 CoRR http://arxiv.org/abs/1702.08359 db/journals/corr/corr1702.html#BamlerM17

Robert Bamler Stephan Mandt Structured Black Box Variational Inference for Latent Time Series Models. 2017 abs/1707.01069 CoRR http://arxiv.org/abs/1707.01069 db/journals/corr/corr1707.html#BamlerM17aa

Robert Bamler Cheng Zhang 0005 Manfred Opper Stephan Mandt Perturbative Black Box Variational Inference. 2017 abs/1709.07433 CoRR http://arxiv.org/abs/1709.07433 db/journals/corr/corr1709.html#abs-1709-07433

Geng Ji 0001 Robert Bamler Erik B. Sudderth Stephan Mandt Bayesian Paragraph Vectors. 2017 abs/1711.03946 CoRR http://arxiv.org/abs/1711.03946 db/journals/corr/corr1711.html#abs-1711-03946

Alex Boyd Guy Van den Broeck Tristan Cinquin Alexander Conzelmann Ryan Cotterell Sina Däubener Sophie Fellenz Asja Fischer Vincent Fortuin Thomas Gärtner 0004 Dominik Gond Philipp Hennig Geng Ji 0001 Fabian Jirasek Matthias Kirchler Marius Kloft Yingzhen Li Christoph Lippert Weiyang Liu Zhen Liu 0019 Stephan Mandt Laura Manduchi Clara Meister Gerard de Melo Eric T. Nalisnick Björn Ommer Manfred Opper Kushagra Pandey Marvin Pförtner Rajesh Ranganath Maja Rudolph Farnood Salehi Bernhard Schölkopf Padhraic Smyth Erik B. Sudderth Álvaro Tejero-Cantero Karen Ullrich Julia E. Vogt Yixin Wang Florian Wenzel Damon Wischik Frank D. WoodFrank Wood Charley M. Wu Tim Z. Xiao Yibo Yang Johannes Zenn Andi Zhang 0001 Cheng Zhang 0005 Hanqi Zhou