Thomas Hofmann 0001
117 publications
28 venues
H Index 50
Affiliation
ETH Zurich, SwitzerlandGoogle, Zurich, Switzerland
Technical University of Darmstadt, Germany
Brown University, Providence, RI, USA
Max-Planck Institute for Biological Cybernetics, T bingen, Germany
University of California Berkeley, Computer Science Division, CA, USA
Massachusetts Institute of Technology, Cambridge, MA, USA
University of Bonn, Germany
Links
| Name | Venue | Year | citations |
|---|---|---|---|
The Importance of Being Lazy: Scaling Limits of Continual Learning.
|
ICML | 2025 | 2 |
| Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment.
|
ICML | 2025 | 1 |
| Generalized Interpolating Discrete Diffusion.
|
ICML | 2025 | 33 |
| The Directionality of Optimization Trajectories in Neural Networks.
|
ICLR | 2025 | 3 |
| Causal Estimation of Tokenisation Bias.
|
ACL | 2025 | 9 |
| On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages.
|
AAAI | 2025 | 0 |
| Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations.
|
AISTATS | 2025 | 0 |
| LoRACLR: Contrastive Adaptation for Customization of Diffusion Models.
|
CVPR | 2025 | 0 |
| Understanding and Minimising Outlier Features in Transformer Training.
|
NIPS/NeurIPS | 2024 | 17 |
| Causal Estimation of Memorisation Profiles.
|
ACL | 2024 | 13 |
| Towards Meta-Pruning via Optimal Transport.
|
ICLR | 2024 | 8 |
| Exposed or Erased: Algorithmic Censorship of Nudity in Art.
|
CHI | 2024 | 15 |
| A Language Model's Guide Through Latent Space.
|
ICML | 2024 | 44 |
| Super Consistency of Neural Network Landscapes and Learning Rate Transfer.
|
NIPS/NeurIPS | 2024 | 16 |
| How Good is a Single Basin?
|
AISTATS | 2024 | 3 |
| Navigating Scaling Laws: Compute Optimality in Adaptive Model Training.
|
ICML | 2024 | 0 |
| Recurrent Distance Filtering for Graph Representation Learning.
|
ICML | 2024 | 0 |
| Simplifying Transformer Blocks.
|
ICLR | 2024 | 0 |
| Transformer Fusion with Optimal Transport.
|
ICLR | 2024 | 0 |
| The Hessian perspective into the Nature of Convolutional Neural Networks.
|
ICML | 2023 | 12 |
| The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit.
|
NIPS/NeurIPS | 2023 | 48 |
| Achieving a Better Stability-Plasticity Trade-off via Auxiliary Networks in Continual Learning.
|
CVPR | 2023 | 60 |
| FIGARO: Controllable Music Generation using Learned and Expert Features.
|
ICLR | 2023 | 43 |
| Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers.
|
NIPS/NeurIPS | 2023 | 77 |
| Random Teachers are Good Teachers.
|
ICML | 2023 | 7 |
| Scaling MLPs: A Tale of Inductive Bias.
|
NIPS/NeurIPS | 2023 | 56 |
| On the effectiveness of Randomized Signatures as Reservoir for Learning Rough Dynamics.
|
IJCNN | 2023 | 0 |
| The Curious Case of Benign Memorization.
|
ICLR | 2023 | 0 |
| Mastering Spatial Graph Prediction of Road Networks.
|
ICCV | 2023 | 0 |
| OpenFilter: A Framework to Democratize Research Access to Social Media AR Filters.
|
NIPS/NeurIPS | 2022 | 15 |
| Vanishing Curvature in Randomly Initialized Deep ReLU Networks.
|
AISTATS | 2022 | 5 |
| Generalization Through the Lens of Leave-One-Out Error.
|
ICLR | 2022 | 9 |
| Phenomenology of Double Descent in Finite-Width Neural Networks.
|
ICLR | 2022 | 12 |
| How Tempering Fixes Data Augmentation in Bayesian Neural Networks.
|
ICML | 2022 | 11 |
| Decoding a Neural Retriever's Latent Space for Query Suggestion.
|
EMNLP | 2022 | 0 |
| Precise characterization of the prior predictive distribution of deep ReLU networks.
|
NIPS/NeurIPS | 2021 | 35 |
| Uniform Convergence, Adversarial Spheres and a Simple Remedy.
|
ICML | 2021 | 8 |
| Learning Generative Models of Textured 3D Meshes from Real-World Images.
|
ICCV | 2021 | 57 |
| Revisiting the Role of Euler Numerical Integration on Acceleration and Stability in Convex Optimization.
|
AISTATS | 2021 | 11 |
| Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect.
|
NIPS/NeurIPS | 2021 | 30 |
| Analytic Insights into Structure and Rank of Neural Network Hessian Maps.
|
NIPS/NeurIPS | 2021 | 48 |
| Batch normalization provably avoids ranks collapse for randomly initialised deep networks.
|
NIPS/NeurIPS | 2020 | 64 |
| Convolutional Generation of Textured 3D Meshes.
|
NIPS/NeurIPS | 2020 | 68 |
| LeDeepChef Deep Reinforcement Learning Agent for Families of Text-Based Games.
|
AAAI | 2020 | 0 |
| Controlling Style and Semantics in Weakly-Supervised Image Generation.
|
ECCV | 2020 | 0 |
| Adversarial Training is a Form of Data-dependent Operator Norm Regularization.
|
NIPS/NeurIPS | 2020 | 0 |
| The Odds are Odd: A Statistical Test for Detecting Adversarial Examples.
|
ICML | 2019 | 184 |
| Local Saddle Point Optimization: A Curvature Exploitation Approach.
|
AISTATS | 2019 | 0 |
| Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization.
|
AISTATS | 2019 | 0 |
| A Domain Agnostic Measure for Monitoring and Evaluating GANs.
|
NIPS/NeurIPS | 2019 | 0 |
| End-to-End Neural Entity Linking.
|
CoNLL | 2018 | 283 |
| A Distributed Second-Order Algorithm You Can Trust.
|
ICML | 2018 | 33 |
| Hyperbolic Entailment Cones for Learning Hierarchical Embeddings.
|
ICML | 2018 | 323 |
| Escaping Saddles with Stochastic Gradients.
|
ICML | 2018 | 0 |
| Hyperbolic Neural Networks.
|
NIPS/NeurIPS | 2018 | 756 |
| Deep State Space Models for Unconditional Word Generation.
|
NIPS/NeurIPS | 2018 | 16 |
| Deep Joint Entity Disambiguation with Local Neural Attention.
|
EMNLP | 2017 | 350 |
| Stabilizing Training of Generative Adversarial Networks through Regularization.
|
NIPS/NeurIPS | 2017 | 477 |
| Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification.
|
WWW | 2017 | 134 |
| Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy.
|
NIPS/NeurIPS | 2016 | 33 |
| Active Content-Based Crowdsourcing Task Selection.
|
CIKM | 2016 | 13 |
| Starting Small - Learning with Adaptive Sample Sizes.
|
ICML | 2016 | 0 |
| Probabilistic Bag-Of-Hyperlinks Model for Entity Linking.
|
WWW | 2016 | 0 |
| Modelling Term Dependence with Copulas.
|
SIGIR | 2015 | 8 |
| Exploiting Document Content for Efficient Aggregation of Crowdsourcing Votes.
|
CIKM | 2015 | 17 |
| Variance Reduced Stochastic Gradient Descent with Neighbors.
|
NIPS/NeurIPS | 2015 | 158 |
| Communication-Efficient Distributed Dual Coordinate Ascent.
|
NIPS/NeurIPS | 2014 | 357 |
| Efficient Subwindow Search: A Branch and Bound Framework for Object Localization.
|
TPAMI | 2009 | 0 |
| Beyond sliding windows: Object localization by efficient subwindow search.
|
CVPR | 2008 | 844 |
| Robust collaborative filtering.
|
RecSys | 2007 | 141 |
| Lies and propaganda: detecting spam users in collaborative filtering.
|
IUI | 2007 | 158 |
| Exploiting Known Taxonomies in Learning Overlapping Concepts.
|
IJCAI | 2007 | 451 |
| From bits and bytes to information and knowledge.
|
CIKM | 2005 | 1 |
| A brain computer interface with online feedback based on magnetoencephalography.
|
ICML | 2005 | 74 |
| Kernel Methods for Missing Variables.
|
AISTATS | 2005 | 286 |
| Non-redundant clustering with conditional ensembles.
|
KDD | 2005 | 50 |
| Large Margin Methods for Structured and Interdependent Output Variables.
|
JMLR | 2005 | 2328 |
| Gaussian process classification for segmenting and annotating sequences.
|
ICML | 2004 | 75 |
| Semi-supervised Learning on Directed Graphs.
|
NIPS/NeurIPS | 2004 | 210 |
| Exponential Families for Conditional Random Fields.
|
UAI | 2004 | 58 |
| Unifying collaborative and content-based filtering.
|
ICML | 2004 | 423 |
| A joint framework for collaborative and content filtering.
|
SIGIR | 2004 | 54 |
| Support vector machine learning for interdependent and structured output spaces.
|
ICML | 2004 | 1482 |
| Hierarchical document categorization with support vector machines.
|
CIKM | 2004 | 440 |
| Learning Over Compact Metric Spaces.
|
COLT | 2004 | 11 |
| Non-Redundant Data Clustering.
|
ICDM | 2004 | 0 |
| Multiple-Instance Learning via Disjunctive Programming Boosting.
|
NIPS/NeurIPS | 2003 | 60 |
| Text categorization by boosting automatically extracted concepts.
|
SIGIR | 2003 | 140 |
| Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge.
|
IJCAI | 2003 | 33 |
| Hidden Markov Support Vector Machines.
|
ICML | 2003 | 579 |
| Collaborative filtering via gaussian probabilistic latent semantic analysis.
|
SIGIR | 2003 | 445 |
| Investigating Loss Functions and Optimization Methods for Discriminative Learning of Label Sequences.
|
EMNLP | 2003 | 57 |
| Support Vector Machines for Multiple-Instance Learning.
|
NIPS/NeurIPS | 2002 | 1652 |
| Support Vector Machines for Polycategorical Classification.
|
ECML/PKDD | 2002 | 6 |
| Discriminative Learning for Label Sequences via Boosting.
|
NIPS/NeurIPS | 2002 | 60 |
| Text Classification in a Hierarchical Mixture Model for Small Training Sets.
|
CIKM | 2001 | 100 |
| Learning What People (Don't) Want.
|
ECML/PKDD | 2001 | 49 |
| Unsupervised Learning by Probabilistic Latent Semantic Analysis.
|
MLJ | 2001 | 0 |
| Learning Curved Multinomial Subfamilies for Natural Language Processing and Information Retrieval.
|
ICML | 2000 | 17 |
| The Missing Link - A Probabilistic Model of Document Content and Hypertext Connectivity.
|
NIPS/NeurIPS | 2000 | 523 |
| Learning probabilistic models of the Web.
|
SIGIR | 2000 | 0 |
| Probabilistic Latent Semantic Indexing.
|
SIGIR | 1999 | 18 |
| Probabilistic Latent Semantic Analysis.
|
UAI | 1999 | 2842 |
| The Cluster-Abstraction Model: Unsupervised Learning of Topic Hierarchies from Text Data.
|
IJCAI | 1999 | 131 |
| Latent Class Models for Collaborative Filtering.
|
IJCAI | 1999 | 543 |
| Histogram Clustering for Unsupervised Image Segmentation.
|
CVPR | 1999 | 97 |
| Learning the Similarity of Documents: An Information-Geometric Approach to Document Retrieval and Categorization.
|
NIPS/NeurIPS | 1999 | 167 |
| Learning from Dyadic Data.
|
NIPS/NeurIPS | 1998 | 166 |
| Unsupervised Texture Segmentation in a Deterministic Annealing Framework.
|
TPAMI | 1998 | 251 |
| Correction to "Pairwise Data Clustering by Deterministic Annealing".
|
TPAMI | 1997 | 7 |
| Active Data Clustering.
|
NIPS/NeurIPS | 1997 | 72 |
| Pairwise Data Clustering by Deterministic Annealing.
|
TPAMI | 1997 | 539 |
| Non-parametric Similarity Measures for Unsupervised Texture Segmentation and Image Retrieval.
|
CVPR | 1997 | 305 |
| An Annealed "Neural Gas" Network for Robust Vector Quantization.
|
ICANN | 1996 | 10 |
| Inferring Hierarchical Clustering Structures by Deterministic Annealing.
|
KDD | 1996 | 8 |
| Multidimensional Scaling and Data Clustering.
|
NIPS/NeurIPS | 1994 | 53 |
| Central and Pairwise Data Clustering by Competitive Neural Networks.
|
NIPS/NeurIPS | 1993 | 10 |