Thomas Hofmann

ORCID

Publication Activity (10 Years)

Years Active: 1993-2024
Publications (10 Years): 159

Top Venues

RWTH Aachen University (PHD)

Education History

RWTH Aachen University

PHD

Publications

Maria Mihaela Trusca, Wolf Nuyts, Jonathan Thomm, Robert Honig, Thomas Hofmann, Tinne Tuytelaars, Marie-Francine Moens
Object-Attribute Binding in Text-to-Image Generation: Evaluation and Control. CoRR (2024)
Sidak Pal Singh, Linara Adilova, Michael Kamp, Asja Fischer, Bernhard Schölkopf, Thomas Hofmann
Landscaping Linear Mode Connectivity. CoRR (2024)
Dimitri von Rütte, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann
A Language Model's Guide Through Latent Space. CoRR (2024)
Anton Schäfer, Thomas Hofmann, Imanol Schlag, Tiago Pimentel
On the Effect of (Near) Duplicate Subwords in Language Modelling. ACL (Findings) (2024)
Jovan Andonov, Octavian Ganea, Paulina Grnarova, Gary Bécigneul, Thomas Hofmann
Explicit Word Density Estimation for Language Modelling. CoRR (2024)
Bobby He, Thomas Hofmann
Simplifying Transformer Blocks. ICLR (2024)
Michael Hersche, Francesco Di Stefano, Thomas Hofmann, Abu Sebastian, Abbas Rahimi
Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architectures. CoRR (2024)
Alexander Theus, Olin Geimer, Friedrich Wicke, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh
Towards Meta-Pruning via Optimal Transport. ICLR (2024)
Bobby He, Lorenzo Noci, Daniele Paliotta, Imanol Schlag, Thomas Hofmann
Understanding and Minimising Outlier Features in Neural Network Training. CoRR (2024)
Pietro Lesci, Clara Meister, Thomas Hofmann, Andreas Vlachos, Tiago Pimentel
Causal Estimation of Memorisation Profiles. CoRR (2024)
Alexander Theus, Olin Geimer, Friedrich Wicke, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh
Towards Meta-Pruning via Optimal Transport. CoRR (2024)
Anton Schäfer, Thomas Hofmann, Imanol Schlag, Tiago Pimentel
On the Effect of (Near) Duplicate Subwords in Language Modelling. CoRR (2024)
Sidak Pal Singh, Bobby He, Thomas Hofmann, Bernhard Schölkopf
Hallmarks of Optimization Trajectories in Neural Networks and LLMs: The Lengths, Bends, and Dead Ends. CoRR (2024)
Kai Lion, Lorenzo Noci, Thomas Hofmann, Gregor Bachmann
How Good is a Single Basin? CoRR (2024)
Anton Schäfer, Shauli Ravfogel, Thomas Hofmann, Tiago Pimentel, Imanol Schlag
Language Imbalance Can Boost Cross-lingual Generalisation. CoRR (2024)
Piera Riccio, Thomas Hofmann, Nuria Oliver
Exposed or Erased: Algorithmic Censorship of Nudity in Art. CHI (2024)
Kai Lion, Lorenzo Noci, Thomas Hofmann, Gregor Bachmann
How Good is a Single Basin? AISTATS (2024)
Marc Pinski, Thomas Hofmann, Alexander Benlian
AI Literacy for the top management: An upper echelons perspective on corporate AI orientation and implementation ability. Electron. Mark. 34 (1) (2024)
Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann
Local vs Global continual learning. CoRR (2024)
Moritz Imfeld, Jacopo Graldi, Marco Giordano, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh
Transformer Fusion with Optimal Transport. ICLR (2024)
Lorenzo Noci, Alexandru Meterez, Thomas Hofmann, Antonio Orvieto
Why do Learning Rates Transfer? Reconciling Optimization and Scaling Limits for Deep Learning. CoRR (2024)
Gul Sena Altintas, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
Disentangling Linear Mode-Connectivity. CoRR (2023)
Sanghwan Kim, Lorenzo Noci, Antonio Orvieto, Thomas Hofmann
Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning. CVPR (2023)
Alexandros Delitzas, Maria Parelli, Nikolas Hars, Georgios Vlassis, Sotirios-Konstantinos Anagnostidis, Gregor Bachmann, Thomas Hofmann
Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes. BMVC (2023)
Maria Parelli, Alexandros Delitzas, Nikolas Hars, Georgios Vlassis, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann
CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes. CVPR Workshops (2023)
Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann
Scaling MLPs: A Tale of Inductive Bias. CoRR (2023)
Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurélien Lucchi, Thomas Hofmann
Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers. CoRR (2023)
Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann
Navigating Scaling Laws: Accelerating Vision Transformer's Training via Adaptive Strategies. CoRR (2023)
Elior Benarous, Sotiris Anagnostidis, Luca Biggio, Thomas Hofmann
Harnessing Synthetic Datasets: The Role of Shape Bias in Deep Neural Network Generalization. CoRR (2023)
Enea Monzio Compagnoni, Anna Scampicchio, Luca Biggio, Antonio Orvieto, Thomas Hofmann, Josef Teichmann
On the effectiveness of Randomized Signatures as Reservoir for Learning Rough Dynamics. IJCNN (2023)
Sotiris Anagnostidis, Aurélien Lucchi, Thomas Hofmann
Mastering Spatial Graph Prediction of Road Networks. ICCV (2023)
Lorenzo Noci, Chuning Li, Mufan Bill Li, Bobby He, Thomas Hofmann, Chris J. Maddison, Dan Roy
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit. NeurIPS (2023)
Lorenzo Noci, Chuning Li, Mufan Bill Li, Bobby He, Thomas Hofmann, Chris Maddison, Daniel M. Roy
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit. CoRR (2023)
Moritz Imfeld, Jacopo Graldi, Marco Giordano, Thomas Hofmann, Sotiris Anagnostidis, Sidak Pal Singh
Transformer Fusion with Optimal Transport. CoRR (2023)
Alexandros Delitzas, Maria Parelli, Nikolas Hars, Georgios Vlassis, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann
Multi-CLIP: Contrastive Vision-Language Pre-training for Question Answering tasks in 3D Scenes. CoRR (2023)
Felix Sarnthein, Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann
Random Teachers are Good Teachers. CoRR (2023)
Alessandro Nicoli, Franziska Haag, Patrick Marcinek, Ruiming He, Johanna Kreißl, Jörg Stein, Alessandro Marchetto, Andreas Dunkel, Thomas Hofmann, Dietmar Krautwurst, Antonella Di Pizio
Modeling the Orthosteric Binding Site of the G Protein-Coupled Odorant Receptor OR5K1. J. Chem. Inf. Model. 63 (7) (2023)
Enis Simsar, Alessio Tonioni, Yongqin Xian, Thomas Hofmann, Federico Tombari
LIME: Localized Image Editing via Attention Regularization in Diffusion Models. CoRR (2023)
Dimitri von Rütte, Luca Biggio, Yannic Kilcher, Thomas Hofmann
FIGARO: Controllable Music Generation using Learned and Expert Features. ICLR (2023)
Aleksandar Stanic, Dylan R. Ashley, Oleg Serikov, Louis Kirsch, Francesco Faccio, Jürgen Schmidhuber, Thomas Hofmann, Imanol Schlag
The Languini Kitchen: Enabling Language Modelling Research at Different Scales of Compute. CoRR (2023)
Marc Pinski, Thomas Hofmann, Alexander Benlian
Executive AI Literacy: A Text-Mining Approach to Understand Existing and Demanded AI Skills of Leaders in Unicorn Firms. Wirtschaftsinformatik (2023)
Maria Parelli, Alexandros Delitzas, Nikolas Hars, Georgios Vlassis, Sotiris Anagnostidis, Gregor Bachmann, Thomas Hofmann
CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes. CoRR (2023)
Sotiris Anagnostidis, Dario Pavllo, Luca Biggio, Lorenzo Noci, Aurélien Lucchi, Thomas Hofmann
Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers. NeurIPS (2023)
Bobby He, Thomas Hofmann
Simplifying Transformer Blocks. CoRR (2023)
Sidak Pal Singh, Thomas Hofmann, Bernhard Schölkopf
The Hessian perspective into the Nature of Convolutional Neural Networks. ICML (2023)
Giulia Lanzillotta, Sidak Pal Singh, Benjamin F. Grewe, Thomas Hofmann
Towards guarantees for parameter isolation in continual learning. CoRR (2023)
Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann
Scaling MLPs: A Tale of Inductive Bias. NeurIPS (2023)
Sanghwan Kim, Lorenzo Noci, Antonio Orvieto, Thomas Hofmann
Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning. CoRR (2023)
Sidak Pal Singh, Thomas Hofmann, Bernhard Schölkopf
The Hessian perspective into the Nature of Convolutional Neural Networks. CoRR (2023)
Felix Sarnthein, Gregor Bachmann, Sotiris Anagnostidis, Thomas Hofmann
Random Teachers are Good Teachers. ICML (2023)
Sotiris Anagnostidis, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
The Curious Case of Benign Memorization. ICLR (2023)
Yuhui Ding, Antonio Orvieto, Bobby He, Thomas Hofmann
Recurrent Distance-Encoding Neural Networks for Graph Representation Learning. CoRR (2023)
Sidak Pal Singh, Aurélien Lucchi, Thomas Hofmann, Bernhard Schölkopf
Phenomenology of Double Descent in Finite-Width Neural Networks. CoRR (2022)
Leonard Adolphs, Michelle Chen Huebscher, Christian Buck, Sertan Girgin, Olivier Bachem, Massimiliano Ciaramita, Thomas Hofmann
Decoding a Neural Retriever's Latent Space for Query Suggestion. EMNLP (2022)
Sotiris Anagnostidis, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
The Curious Case of Benign Memorization. CoRR (2022)
Gregor Bachmann, Thomas Hofmann, Aurélien Lucchi
Generalization Through the Lens of Leave-One-Out Error. ICLR (2022)
Leonard Adolphs, Michelle Chen Huebscher, Christian Buck, Sertan Girgin, Olivier Bachem, Massimiliano Ciaramita, Thomas Hofmann
Decoding a Neural Retriever's Latent Space for Query Suggestion. CoRR (2022)
Sidak Pal Singh, Aurélien Lucchi, Thomas Hofmann, Bernhard Schölkopf
Phenomenology of Double Descent in Finite-Width Neural Networks. ICLR (2022)
Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
How Tempering Fixes Data Augmentation in Bayesian Neural Networks. ICML (2022)
Leonard Adolphs, Benjamin Börschinger, Christian Buck, Michelle Chen Huebscher, Massimiliano Ciaramita, Lasse Espeholt, Thomas Hofmann, Yannic Kilcher, Sascha Rothe, Pier Giuseppe Sessa, Lierni Sestorain
Boosting Search Engines with Interactive Agents. Trans. Mach. Learn. Res. 2022 (2022)
Piera Riccio, Bill Psomas, Francesco Galati, Francisco Escolano, Thomas Hofmann, Nuria Oliver
OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters. NeurIPS (2022)
Sotiris Anagnostidis, Aurélien Lucchi, Thomas Hofmann
Mastering Spatial Graph Prediction of Road Networks. CoRR (2022)
Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
How Tempering Fixes Data Augmentation in Bayesian Neural Networks. CoRR (2022)
Sotiris Anagnostidis, Arne Thomsen, Tomasz Kacprzak, Tilman Tröster, Luca Biggio, Alexandre Refregier, Thomas Hofmann
Cosmology from Galaxy Redshift Surveys with PointNet. CoRR (2022)
Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurélien Lucchi
Vanishing Curvature in Randomly Initialized Deep ReLU Networks. AISTATS (2022)
Enea Monzio Compagnoni, Luca Biggio, Antonio Orvieto, Thomas Hofmann, Josef Teichmann
Randomized Signature Layers for Signal Extraction in Time Series Data. CoRR (2022)
Piera Riccio, Bill Psomas, Francesco Galati, Francisco Escolano, Thomas Hofmann, Nuria Oliver
OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters. CoRR (2022)
Gregor Bachmann, Thomas Hofmann, Aurélien Lucchi
Generalization Through The Lens Of Leave-One-Out Error. CoRR (2022)
Leonard Adolphs, Benjamin Börschinger, Christian Buck, Michelle Chen Huebscher, Massimiliano Ciaramita, Lasse Espeholt, Thomas Hofmann, Yannic Kilcher
Boosting Search Engines with Interactive Agents. CoRR (2021)
Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Thomas Hofmann
Uniform Convergence, Adversarial Spheres and a Simple Remedy. ICML (2021)
Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, Thomas Hofmann
Precise characterization of the prior predictive distribution of deep ReLU networks. CoRR (2021)
Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin, Thomas Hofmann
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect. CoRR (2021)
Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, Thomas Hofmann
Precise characterization of the prior predictive distribution of deep ReLU networks. NeurIPS (2021)
Sidak Pal Singh, Gregor Bachmann, Thomas Hofmann
Analytic Insights into Structure and Rank of Neural Network Hessian Maps. NeurIPS (2021)
Antonio Orvieto, Jonas Köhler, Dario Pavllo, Thomas Hofmann, Aurélien Lucchi
Vanishing Curvature and the Power of Adaptive Methods in Randomly Initialized Deep Networks. CoRR (2021)
Mandra Bensmann, Alicia Lampe, Thomas Hofmann, Steffen Loth
Collaborative Workspace - Concept Design and Proof of Concept of an Interactive Visual System to Support Collaborative Decision-Making for Total Airport Management. HCI (44) (2021)
Dario Pavllo, Jonas Köhler, Thomas Hofmann, Aurélien Lucchi
Learning Generative Models of Textured 3D Meshes from Real-World Images. CoRR (2021)
Paulina Grnarova, Yannic Kilcher, Kfir Y. Levy, Aurélien Lucchi, Thomas Hofmann
Generative Minimization Networks: Training GANs Without Competition. CoRR (2021)
Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy S. Smith
Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization. AISTATS (2021)
Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin, Thomas Hofmann
Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect. NeurIPS (2021)
Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Thomas Hofmann
Uniform Convergence, Adversarial Spheres and a Simple Remedy. CoRR (2021)
Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy S. Smith
Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization. CoRR (2021)
Svenja Knothe, Thomas Hofmann, Christian Blessmann
Theory and Practice in UX Design - Identification of Discrepancies in the Development Process of User-Oriented HMI. HCI (44) (2021)
Dario Pavllo, Jonas Kohler, Thomas Hofmann, Aurélien Lucchi
Learning Generative Models of Textured 3D Meshes from Real-World Images. ICCV (2021)
Leonard Adolphs, Shehzaad Dhuliawala, Thomas Hofmann
How to Query Language Models? CoRR (2021)
Pelin Dogan-Schönberger, Julian Mäder, Thomas Hofmann
SwissDial: Parallel Multidialectal Corpus of Spoken Swiss German. CoRR (2021)
Mandra Bensmann, Alicia Lampe, Thomas Hofmann, Steffen Loth
Collaborative Workspace - Concept Design of an Interactive System for Total Airport Management. AHFE (15) (2021)
Sidak Pal Singh, Gregor Bachmann, Thomas Hofmann
Analytic Insights into Structure and Rank of Neural Network Hessian Maps. CoRR (2021)
Zoltán R. Bárdosi, Christian Plattner, Yusuf Özbek, Thomas Hofmann, Srdjan Milosavljevic, Volker Schartinger, Wolfgang Freysinger
CIGuide: in situ augmented reality laser guidance. Int. J. Comput. Assist. Radiol. Surg. 15 (1) (2020)
Dario Pavllo, Graham Spinks, Thomas Hofmann, Marie-Francine Moens, Aurélien Lucchi
Convolutional Generation of Textured 3D Meshes. CoRR (2020)
Hadi Daneshmand, Jonas Moritz Kohler, Francis R. Bach, Thomas Hofmann, Aurélien Lucchi
Batch normalization provably avoids ranks collapse for randomly initialised deep networks. NeurIPS (2020)
Kevin Roth, Yannic Kilcher, Thomas Hofmann
Adversarial Training is a Form of Data-dependent Operator Norm Regularization. NeurIPS (2020)
Thomas Hofmann, Jörn Jakobi, Marcus Biella, Christian Blessmann, Fabian Reuschling, Tom Kamender
Design and Implementation of a Virtual Workstation for a Remote AFISO. HCI (46) (2020)
Leonard Adolphs, Thomas Hofmann
LeDeepChef Deep Reinforcement Learning Agent for Families of Text-Based Games. AAAI (2020)
Dario Pavllo, Aurélien Lucchi, Thomas Hofmann
Controlling Style and Semantics in Weakly-Supervised Image Generation. ECCV (6) (2020)
Dario Pavllo, Graham Spinks, Thomas Hofmann, Marie-Francine Moens, Aurélien Lucchi
Convolutional Generation of Textured 3D Meshes. NeurIPS (2020)
Florian Schmidt, Thomas Hofmann
BERT as a Teacher: Contextual Embeddings for Sequence-Level Reward. CoRR (2020)
Hadi Daneshmand, Jonas Moritz Kohler, Francis R. Bach, Thomas Hofmann, Aurélien Lucchi
Theoretical Understanding of Batch-normalization: A Markov Chain Perspective. CoRR (2020)
Dario Pavllo, Aurélien Lucchi, Thomas Hofmann
Controlling Style and Semantics in Weakly-Supervised Image Generation. CoRR (2019)
Paulina Grnarova, Kfir Y. Levy, Aurélien Lucchi, Nathanaël Perraudin, Ian Goodfellow, Thomas Hofmann, Andreas Krause
A Domain Agnostic Measure for Monitoring and Evaluating GANs. NeurIPS (2019)

Thomas Hofmann.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Thomas Hofmann