PPaperPicks

Thomas Hofmann

26 papers at tracked venues · 21 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0009-0007-1270-7053 ↗Google Scholar ↗Homepage ↗

Venues

ICML ×6ICLR ×4NeurIPS ×4ACL ×3AISTATS ×2AAAI ×1CHI ×1CVPR ×1ECCV ×1EMNLP ×1ICCV ×1WACV ×1

Frequent coauthors

Tiago Pimentel
×5
Bobby He
×4
Lorenzo Noci
×4
Sotiris Anagnostidis
×4
Yuhui Ding
×3
Antonio Orvieto
×3
Enis Simsar
×3
Federico Tombari
×3
Sidak Pal Singh
×3
Gregor Bachmann
×3
Imanol Schlag
×3
Pietro Lesci
×2

Papers

  1. Causal Estimation of Tokenisation Bias
    ACL 2025 ·
    Pietro Lesci
    ,
    Clara Meister
    , Thomas Hofmann,
    Andreas Vlachos
    ,
    Tiago Pimentel
  2. Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations
    AISTATS 2025 ·
    Amir Joudaki
    , Thomas Hofmann
  3. Generalized Interpolating Discrete Diffusion
    ICML 2025 ·
    Dimitri von Rütte
    ,
    Janis Fluri
    ,
    Yuhui Ding
    ,
    Antonio Orvieto
    ,
    Bernhard Schölkopf
    , Thomas Hofmann
  4. LIME: Localized Image Editing via Attention Regularization in Diffusion Models
    WACV 2025 ·
    Enis Simsar
    ,
    Alessio Tonioni
    ,
    Yongqin Xian
    , Thomas Hofmann,
    Federico Tombari
  5. LoRACLR: Contrastive Adaptation for Customization of Diffusion Models
    CVPR 2025 ·
    Enis Simsar
    , Thomas Hofmann,
    Federico Tombari
    ,
    Pinar Yanardag
  6. On the Expressiveness and Length Generalization of Selective State Space Models on Regular Languages
    AAAI 2025 ·
    Aleksandar Terzic
    ,
    Michael Hersche
    ,
    Giacomo Camposampiero
    , Thomas Hofmann,
    Abu Sebastian
    ,
    Abbas Rahimi
  7. Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment
    ICML 2025 ·
    Yuhui Ding
    , Thomas Hofmann
  8. Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models
    NeurIPS 2025 ·
    Aleksandar Terzic
    ,
    Nicolas Menet
    ,
    Michael Hersche
    , Thomas Hofmann,
    Abbas Rahimi
  9. The Directionality of Optimization Trajectories in Neural Networks
    ICLR 2025 ·
    Sidak Pal Singh
    ,
    Bobby He
    , Thomas Hofmann,
    Bernhard Schölkopf
  10. The Importance of Being Lazy: Scaling Limits of Continual Learning
    ICML 2025 ·
    Jacopo Graldi
    ,
    Alessandro Breccia
    ,
    Giulia Lanzillotta
    , Thomas Hofmann,
    Lorenzo Noci
  11. The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
    NeurIPS 2025 ·
    Denis Sutter
    ,
    Julian Minder
    , Thomas Hofmann,
    Tiago Pimentel
  12. UIP2P: Unsupervised Instruction-Based Image Editing via Edit Reversibility Constraint
    ICCV 2025 ·
    Enis Simsar
    ,
    Alessio Tonioni
    ,
    Yongqin Xian
    , Thomas Hofmann,
    Federico Tombari
  13. A Language Model's Guide Through Latent Space
    ICML 2024 ·
    Dimitri von Rütte
    ,
    Sotiris Anagnostidis
    ,
    Gregor Bachmann
    , Thomas Hofmann
  14. An Art-Centric Perspective on AI-Based Content Moderation of Nudity
    ECCV 2024 ·
    Piera Riccio
    ,
    Georgina Curto
    , Thomas Hofmann,
    Nuria Oliver
  15. Causal Estimation of Memorisation Profiles
    ACL 2024 ·
    Pietro Lesci
    ,
    Clara Meister
    , Thomas Hofmann,
    Andreas Vlachos
    ,
    Tiago Pimentel
  16. Exposed or Erased: Algorithmic Censorship of Nudity in Art
    CHI 2024 ·
    Piera Riccio
    , Thomas Hofmann,
    Nuria Oliver
  17. How Good is a Single Basin?
    AISTATS 2024 ·
    Kai Lion
    ,
    Lorenzo Noci
    , Thomas Hofmann,
    Gregor Bachmann
  18. Local and Global Decoding in Text Generation
    EMNLP 2024 ·
    Daniel Gareev
    , Thomas Hofmann,
    Ezhilmathi Krishnasamy
    ,
    Tiago Pimentel
  19. Navigating Scaling Laws: Compute Optimality in Adaptive Model Training
    ICML 2024 ·
    Sotiris Anagnostidis
    ,
    Gregor Bachmann
    ,
    Imanol Schlag
    , Thomas Hofmann
  20. On the Effect of (Near) Duplicate Subwords in Language Modelling
    ACL 2024 ·
    Anton Schäfer
    , Thomas Hofmann,
    Imanol Schlag
    ,
    Tiago Pimentel
  21. Recurrent Distance Filtering for Graph Representation Learning
    ICML 2024 ·
    Yuhui Ding
    ,
    Antonio Orvieto
    ,
    Bobby He
    , Thomas Hofmann
  22. Simplifying Transformer Blocks
    ICLR 2024 ·
    Bobby He
    , Thomas Hofmann
  23. Super Consistency of Neural Network Landscapes and Learning Rate Transfer
    NeurIPS 2024 ·
    Lorenzo Noci
    ,
    Alexandru Meterez
    , Thomas Hofmann,
    Antonio Orvieto
  24. Towards Meta-Pruning via Optimal Transport
    ICLR 2024 ·
    Alexander Theus
    ,
    Olin Geimer
    ,
    Friedrich Wicke
    , Thomas Hofmann,
    Sotiris Anagnostidis
    ,
    Sidak Pal Singh
  25. Transformer Fusion with Optimal Transport
    ICLR 2024 ·
    Moritz Imfeld
    ,
    Jacopo Graldi
    ,
    Marco Giordano
    , Thomas Hofmann,
    Sotiris Anagnostidis
    ,
    Sidak Pal Singh
  26. Understanding and Minimising Outlier Features in Transformer Training
    NeurIPS 2024 ·
    Bobby He
    ,
    Lorenzo Noci
    ,
    Daniele Paliotta
    ,
    Imanol Schlag
    , Thomas Hofmann