| 2025 | AAAI | On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages. | Aleksandar Terzic, Michael Hersche, Giacomo Camposampiero, Thomas Hofmann, Abu Sebastian, Abbas Rahimi |
| 2025 | ACL | Causal Estimation of Tokenisation Bias. | Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel |
| 2025 | AISTATS | Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations. | Amir Joudaki, Thomas Hofmann |
| 2025 | CVPR | LoRACLR: Contrastive Adaptation for Customization of Diffusion Models. | Enis Simsar, Thomas Hofmann, Federico Tombari, Pinar Yanardag |
| 2025 | ICCV | UIP2P: Unsupervised Instruction-Based Image Editing via Edit Reversibility Constraint. | Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari |
| 2025 | ICLR | The Directionality of Optimization Trajectories in Neural Networks. | Sidak Pal Singh, Bobby He, Thomas Hofmann, Bernhard Schlkopf |
| 2025 | ICML | Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment. | Yuhui Ding, Thomas Hofmann |
| 2025 | ICML | The Importance of Being Lazy: Scaling Limits of Continual Learning. | Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta, Thomas Hofmann, Lorenzo Noci |
| 2025 | ICML | Generalized Interpolating Discrete Diffusion. | Dimitri von Rtte, Janis Fluri, Yuhui Ding, Antonio Orvieto, Bernhard Schlkopf, Thomas Hofmann |
| 2025 | WACV | LIME: Localized Image Editing via Attention Regularization in Diffusion Models. | Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari |
| 2024 | ACL | Causal Estimation of Memorisation Profiles. | Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel |
| 2024 | ACL | On the Effect of (Near) Duplicate Subwords in Language Modelling. | Anton Schfer, Thomas Hofmann, Imanol Schlag, Tiago Pimentel |
| 2024 | AISTATS | How Good is a Single Basin? | Kai Lion, Lorenzo Noci, Thomas Hofmann, Gregor Bachmann |
| 2024 | CHI | Exposed or Erased: Algorithmic Censorship of Nudity in Art. | Piera Riccio, Thomas Hofmann, Nuria Oliver |
| 2024 | ECCV | An Art-Centric Perspective on AI-Based Content Moderation of Nudity. | Piera Riccio, Georgina Curto, Thomas Hofmann, Nuria Oliver |
| 2024 | EMNLP | Local and Global Decoding in Text Generation. | Daniel Gareev, Thomas Hofmann, Ezhilmathi Krishnasamy, Tiago Pimentel |
| 2024 | ICLR | Simplifying Transformer Blocks. | Bobby He, Thomas Hofmann |
| 2024 | ICLR | Transformer Fusion with Optimal Transport. | Moritz Imfeld, Jacopo Graldi, Marco Giordano, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh |
| 2024 | ICLR | Towards Meta-Pruning via Optimal Transport. | Alexander Theus, Olin Geimer, Friedrich Wicke, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh |
| 2024 | ICML | Navigating Scaling Laws: Compute Optimality in Adaptive Model Training. | Sotiris Anagnostidis, Gregor Bachmann, Imanol Schlag, Thomas Hofmann |
| 2024 | ICML | Recurrent Distance Filtering for Graph Representation Learning. | Yuhui Ding, Antonio Orvieto, Bobby He, Thomas Hofmann |
| 2024 | ICML | A Language Model's Guide Through Latent Space. | Dimitri von Rtte, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann |
| 2023 | BMVC | Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes. | Alexandros Delitzas, Maria Parelli, Nikolas Hars, Georgios Vlassis, Sotirios-Konstantinos Anagnostidis, Gregor Bachmann, Thomas Hofmann |
| 2023 | CVPR | Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning. | Sanghwan Kim, Lorenzo Noci, Antonio Orvieto, Thomas Hofmann |
| 2023 | CVPR | CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes. | Maria Parelli, Alexandros Delitzas, Nikolas Hars, Georgios Vlassis, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann |
| 2023 | ICCV | Mastering Spatial Graph Prediction of Road Networks. | Sotiris Anagnostidis, Aurlien Lucchi, Thomas Hofmann |
| 2023 | ICLR | The Curious Case of Benign Memorization. | Sotiris Anagnostidis, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann |
| 2023 | ICLR | FIGARO: Controllable Music Generation using Learned and Expert Features. | Dimitri von Rtte, Luca Biggio, Yannic Kilcher, Thomas Hofmann |
| 2023 | ICML | Random Teachers are Good Teachers. | Felix Sarnthein, Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann |
| 2023 | ICML | The Hessian perspective into the Nature of Convolutional Neural Networks. | Sidak Pal Singh, Thomas Hofmann, Bernhard Schlkopf |
| 2023 | IJCNN | On the effectiveness of Randomized Signatures as Reservoir for Learning Rough Dynamics. | Enea Monzio Compagnoni, Anna Scampicchio, Luca Biggio, Antonio Orvieto, Thomas Hofmann, Josef Teichmann |
| 2022 | AISTATS | Vanishing Curvature in Randomly Initialized Deep ReLU Networks. | Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurlien Lucchi |
| 2022 | EMNLP | Decoding a Neural Retriever's Latent Space for Query Suggestion. | Leonard Adolphs, Michelle Chen Huebscher, Christian Buck, Sertan Girgin, Olivier Bachem, Massimiliano Ciaramita, Thomas Hofmann |
| 2022 | ICLR | Generalization Through the Lens of Leave-One-Out Error. | Gregor Bachmann, Thomas Hofmann, Aurlien Lucchi |
| 2022 | ICLR | Phenomenology of Double Descent in Finite-Width Neural Networks. | Sidak Pal Singh, Aurlien Lucchi, Thomas Hofmann, Bernhard Schlkopf |
| 2022 | ICML | How Tempering Fixes Data Augmentation in Bayesian Neural Networks. | Gregor Bachmann, Lorenzo Noci, Thomas Hofmann |
| 2021 | AISTATS | Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization. | Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy S. Smith |
| 2021 | HCI | Collaborative Workspace - Concept Design and Proof of Concept of an Interactive Visual System to Support Collaborative Decision-Making for Total Airport Management. | Mandra Bensmann, Alicia Lampe, Thomas Hofmann, Steffen Loth |
| 2021 | HCI | Theory and Practice in UX Design - Identification of Discrepancies in the Development Process of User-Oriented HMI. | Svenja Knothe, Thomas Hofmann, Christian Blessmann |
| 2021 | ICCV | Learning Generative Models of Textured 3D Meshes from Real-World Images. | Dario Pavllo, Jonas Kohler, Thomas Hofmann, Aurlien Lucchi |
| 2021 | ICML | Uniform Convergence, Adversarial Spheres and a Simple Remedy. | Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Thomas Hofmann |
| 2020 | AAAI | LeDeepChef Deep Reinforcement Learning Agent for Families of Text-Based Games. | Leonard Adolphs, Thomas Hofmann |
| 2020 | ECCV | Controlling Style and Semantics in Weakly-Supervised Image Generation. | Dario Pavllo, Aurlien Lucchi, Thomas Hofmann |
| 2020 | HCI | Design and Implementation of a Virtual Workstation for a Remote AFISO. | Thomas Hofmann, Jrn Jakobi, Marcus Biella, Christian Blessmann, Fabian Reuschling, Tom Kamender |
| 2019 | AISTATS | Local Saddle Point Optimization: A Curvature Exploitation Approach. | Leonard Adolphs, Hadi Daneshmand, Aurlien Lucchi, Thomas Hofmann |
| 2019 | AISTATS | Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization. | Jonas Moritz Kohler, Hadi Daneshmand, Aurlien Lucchi, Thomas Hofmann, Ming Zhou, Klaus Neymeyr |
| 2019 | EMNLP | Autoregressive Text Generation Beyond Feedback Loops. | Florian Schmidt, Stephan Mandt, Thomas Hofmann |
| 2019 | ICML | The Odds are Odd: A Statistical Test for Detecting Adversarial Examples. | Kevin Roth, Yannic Kilcher, Thomas Hofmann |
| 2018 | CoNLL | End-to-End Neural Entity Linking. | Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann |
| 2018 | EMNLP | Learning and Evaluating Sparse Interpretable Sentence Embeddings. | Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann |
| 2018 | ICLR | An Online Learning Approach to Generative Adversarial Networks. | Paulina Grnarova, Kfir Y. Levy, Aurlien Lucchi, Thomas Hofmann, Andreas Krause |
| 2018 | ICLR | Semantic Interpolation in Implicit Models. | Yannic Kilcher, Aurlien Lucchi, Thomas Hofmann |
| 2018 | ICML | Escaping Saddles with Stochastic Gradients. | Hadi Daneshmand, Jonas Moritz Kohler, Aurlien Lucchi, Thomas Hofmann |
| 2018 | ICML | A Distributed Second-Order Algorithm You Can Trust. | Celestine Dnner, Aurlien Lucchi, Matilde Gargiani, An Bian, Thomas Hofmann, Martin Jaggi |
| 2018 | ICML | Hyperbolic Entailment Cones for Learning Hierarchical Embeddings. | Octavian-Eugen Ganea, Gary Bcigneul, Thomas Hofmann |
| 2017 | EMNLP | Deep Joint Entity Disambiguation with Local Neural Attention. | Octavian-Eugen Ganea, Thomas Hofmann |
| 2017 | WWW | Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification. | Jan Deriu, Aurlien Lucchi, Valeria De Luca, Aliaksei Severyn, Simon Mller, Mark Cieliebak, Thomas Hofmann, Martin Jaggi |
| 2016 | CIKM | Active Content-Based Crowdsourcing Task Selection. | Piyush Bansal, Carsten Eickhoff, Thomas Hofmann |
| 2016 | ICML | Starting Small - Learning with Adaptive Sample Sizes. | Hadi Daneshmand, Aurlien Lucchi, Thomas Hofmann |
| 2016 | WWW | Probabilistic Bag-Of-Hyperlinks Model for Entity Linking. | Octavian-Eugen Ganea, Marina Ganea, Aurlien Lucchi, Carsten Eickhoff, Thomas Hofmann |
| 2015 | CIKM | Exploiting Document Content for Efficient Aggregation of Crowdsourcing Votes. | Martin Davtyan, Carsten Eickhoff, Thomas Hofmann |
| 2015 | SIGIR | Modelling Term Dependence with Copulas. | Carsten Eickhoff, Arjen P. de Vries, Thomas Hofmann |
| 2008 | CVPR | Beyond sliding windows: Object localization by efficient subwindow search. | Christoph H. Lampert, Matthew B. Blaschko, Thomas Hofmann |
| 2007 | IJCAI | Exploiting Known Taxonomies in Learning Overlapping Concepts. | Lijuan Cai, Thomas Hofmann |
| 2007 | IUI | Lies and propaganda: detecting spam users in collaborative filtering. | Bhaskar Mehta, Thomas Hofmann, Peter Fankhauser |
| 2007 | RecSys | Robust collaborative filtering. | Bhaskar Mehta, Thomas Hofmann, Wolfgang Nejdl |
| 2006 | ICDM | Global Biclustering of Microarray Data. | Thomas Wolf, Benedikt Brors, Thomas Hofmann, Elisabeth Georgii |
| 2006 | KI | Cross System Personalization and Collaborative Filtering by Learning Manifold Alignments. | Bhaskar Mehta, Thomas Hofmann |
| 2005 | AISTATS | Kernel Methods for Missing Variables. | Alexander J. Smola, S. V. N. Vishwanathan, Thomas Hofmann |
| 2005 | CIKM | From bits and bytes to information and knowledge. | Thomas Hofmann |
| 2005 | ICML | A brain computer interface with online feedback based on magnetoencephalography. | Thomas Navin Lal, Michael Schrder, N. Jeremy Hill, Hubert Preil, Thilo Hinterberger, Jrgen Mellinger, Martin Bogdan, Wolfgang Rosenstiel, Thomas Hofmann, Niels Birbaumer, Bernhard Schlkopf |
| 2005 | KDD | Non-redundant clustering with conditional ensembles. | David Gondek, Thomas Hofmann |
| 2004 | CIKM | Hierarchical document categorization with support vector machines. | Lijuan Cai, Thomas Hofmann |
| 2004 | COLT | Learning Over Compact Metric Spaces. | Ha Quang Minh, Thomas Hofmann |
| 2004 | ICDM | Non-Redundant Data Clustering. | David Gondek, Thomas Hofmann |
| 2004 | ICML | Gaussian process classification for segmenting and annotating sequences. | Yasemin Altun, Thomas Hofmann, Alexander J. Smola |
| 2004 | ICML | Unifying collaborative and content-based filtering. | Justin Basilico, Thomas Hofmann |
| 2004 | ICML | Support vector machine learning for interdependent and structured output spaces. | Ioannis Tsochantaridis, Thomas Hofmann, Thorsten Joachims, Yasemin Altun |
| 2004 | SIGIR | A joint framework for collaborative and content filtering. | Justin Basilico, Thomas Hofmann |
| 2004 | UAI | Exponential Families for Conditional Random Fields. | Yasemin Altun, Alexander J. Smola, Thomas Hofmann |
| 2003 | EMNLP | Investigating Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences. | Yasemin Altun, Mark Johnson, Thomas Hofmann |
| 2003 | ICML | Hidden Markov Support Vector Machines. | Yasemin Altun, Ioannis Tsochantaridis, Thomas Hofmann |
| 2003 | IJCAI | Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge. | Massimiliano Ciaramita, Thomas Hofmann, Mark Johnson |
| 2003 | Interspeech | Large margin methods for label sequence learning. | Yasemin Altun, Thomas Hofmann |
| 2003 | SIGIR | Text categorization by boosting automatically extracted concepts. | Lijuan Cai, Thomas Hofmann |
| 2003 | SIGIR | Collaborative filtering via gaussian probabilistic latent semantic analysis. | Thomas Hofmann |
| 2002 | AAAI | Multiple Instance Learning with Generalized Support Vector Machines. | Stuart Andrews, Thomas Hofmann, Ioannis Tsochantaridis |
| 2001 | CIKM | Text Classification in a Hierarchical Mixture Model for Small Training Sets. | Kristina Toutanova, Francine Chen, Kris Popat, Thomas Hofmann |
| 2000 | Coordination | OpenSpaces: An Object-Oriented Framework for Reconfigurable Coordination Spaces. | Stphane Ducasse, Thomas Hofmann, Oscar Nierstrasz |
| 2000 | ICML | Learning Curved Multinomial Subfamilies for Natural Language Processing and Information Retrieval. | Keith B. Hall, Thomas Hofmann |
| 2000 | SIGIR | Learning probabilistic models of the Web. | Thomas Hofmann |
| 1999 | CVPR | Histogram Clustering for Unsupervised Image Segmentation. | Jan Puzicha, Joachim M. Buhmann, Thomas Hofmann |
| 1999 | IJCAI | The Cluster-Abstraction Model: Unsupervised Learning of Topic Hierarchies from Text Data. | Thomas Hofmann |
| 1999 | IJCAI | Latent Class Models for Collaborative Filtering. | Thomas Hofmann, Jan Puzicha |
| 1999 | Interspeech | Topic-based language models using EM. | Daniel Gildea, Thomas Hofmann |
| 1999 | IDA | Probabilistic Topic Maps: Navigating through Large Text Collections. | Thomas Hofmann |
| 1999 | SIGIR | Probabilistic Latent Semantic Indexing. | Thomas Hofmann |
| 1999 | UAI | Probabilistic Latent Semantic Analysis. | Thomas Hofmann |
| 1998 | ICPR | Mixture models for co-occurrence and histogram data. | Thomas Hofmann, Jan Puzicha |
| 1997 | CVPR | Non-parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval. | Jan Puzicha, Thomas Hofmann, Joachim M. Buhmann |
| 1997 | ICASSP | Robust vector quantization by competitive learning. | Joachim M. Buhmann, Thomas Hofmann |
| 1997 | ICIP | An Optimization Approach to Unsupervised Hierarchical Texture Segmentation. | Thomas Hofmann, Jan Puzicha, Joachim M. Buhmann |
| 1996 | ICANN | An Annealed "Neural Gas" Network for Robust Vector Quantization. | Thomas Hofmann, Joachim M. Buhmann |
| 1996 | ICIP | Unsupervised segmentation of textured images by pairwise data clustering. | Thomas Hofmann, Jan Puzicha, Joachim M. Buhmann |
| 1996 | KDD | Inferring Hierarchical Clustering Structures by Deterministic Annealing. | Thomas Hofmann, Joachim M. Buhmann |
| 1994 | ICPR | A maximum entropy approach to pairwise data clustering. | Joachim M. Buhmann, Thomas Hofmann |