TH
Thomas Hofmann
cs.LGTastestat.MLcs.AIcs.CLcs.CVPeriodicals as TopictasteRacismtaste dilution analysis
On Valency
published · living versionsW_a5vmwnms·v1 · currentpublished
Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks
with Rodrigo Casado Noguerales, Dimitri von Rütte, Bernhard Schölkopf, Aran Raoufi
1 version
W_phdsmpgb·v1published
Preprints & journals
586 papers in the corpus · 1998–2026Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning Tasks2610.28543v1 · Rodrigo Casado Noguerales, Dimitri von Rutte, Bernhard Scholkopf et al.2026 · 0 citationsarXivon Valency
Continual Concept Personalization in Diffusion Models via Residual-Space Adaptation2610.28567v1 · Yuzhi Liu, Enis Simsar, Giulia Lanzillotta et al.2026 · 0 citationsarXivon Valency
Advectra: Asymmetric Latent Transport for Non-Stationary Physics2610.05098v1 · Nodens Koren, Thomas Hofmann, Georgios Kissas2026 · 0 citationsarXiv
METRO: Metric-Enhanced Token Routing Operator2610.05100v1 · Nodens Koren, Thomas Hofmann, Georgios Kissas2026 · 0 citationsarXiv
Cyclostationary Phase Conditioning for Medical Time Series Diffusion2609.34965v2 · Samuel Ruiperez-Campillo, Michele Copetti, Jorge da Silva Goncalves et al.2026 · 0 citationsarXiv
DR-net-Mamba: Selective State-Space Modeling for Long-Range ECG Time-Series Denoising2609.35634v1 · Basile Morel, Samuel Ruiperez-Campillo, Andreas P. Streich et al.2026 · 0 citationsarXiv
Adapting Linear-Time Architectures for Tabular In-Context Learning2609.36337v1 · David Schnurr, Felix Sarnthein, Thomas Hofmann et al.2026 · 0 citationsarXiv
Emulating the complex galactic-scale orbital dynamics of LISA massive black hole pairs with normalizing flows2607.26125v1 · Pedro R. Capelo, Carlos Moreno Martinez, Nodens Koren et al.2026 · 0 citationsarXiv
Invariant Learning Dynamics of Transformers in Inductive Reasoning Tasks2607.11875v2 · Tiberiu Musat, Tiago Pimentel, Nicolas Zucchet et al.2026 · 0 citationsarXiv
The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System2607.04993v1 · Thomas Hofmann2026 · 0 citationsarXiv
What Does a Discrete Diffusion Model Learn? One Reverse Process in Three Coordinates2607.05381v2 · Rodrigo Casado Noguerales, Bernhard Scholkopf, Thomas Hofmann et al.2026 · 0 citationsarXiv
When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning2606.28117v1 · Tanguy Dieudonn'e, Giulia Lanzillotta, Enis Simsar et al.2026 · 0 citationsarXiv
Fixed-Point Reasoners: Stable and Adaptive Deep Looped Transformers2606.18206v1 · Sajad Movahedi, Vera Milovanovi'c, Shlomo Libo Feigin et al.2026 · 0 citationsarXiv
SeqLoRA: Bilevel Orthogonal Adaptation for Continual Multi-Concept Generation2605.22743v2 · Javad Parsa, Enis Simsar, Amir Joudaki et al.2026 · 0 citationsarXiv
FullFlow: Upgrading Text-to-Image Flow Matching Models for Bidirectional Vision--Language Generation2605.20316v1 · Eric Tillmann Bill, Enis Simsar, Alessio Tonioni et al.2026 · 0 citationsarXiv
Flash PD-SSM: Memory-Optimized Structured Sparse State-Space Models2605.19150v1 · Aleksandar Terzi'c, Francesco Carzaniga, Nicolas Menet et al.2026 · 0 citationsarXiv
Neural correlates of recognition memory obtained after encoding under conventional laboratory, virtual, and real-life conditions reveal modality-specific mnemonic processing.41980450 · Johnsdorf, Marike, Kisker, Joanna, Sagehorn, Merle et al.2026 · 2 citationsActa psychologica. 2026;266:106791
When Does Sparsity Mitigate the Curse of Depth in LLMs2603.15389v2 · Dilxat Muhtar, Xinyuan Song, Sebastian Pokutta et al.2026 · 0 citationsarXiv
Latent-DARM: Bridging Discrete Diffusion And Autoregressive Models For Reasoning2603.09184v1 · Lina Berrayana, Ahmed Heakl, Abdullah Sohail et al.2026 · 0 citationsarXiv
Fast and Geometrically Grounded Lorentz Neural Networks2601.21529v1 · Robert van der Klis, Ricardo Ch'avez Torres, Max van Spengler et al.2026 · 0 citationsarXiv
From Chemistry to Nutrition: JAFC's Evolving Scientific Landscape.41536025 · Hofmann, Thomas F2026 · 0 citationsJournal of agricultural and food chemistry. 2026;74(1):1-3
Scaling Behavior of Discrete Diffusion Language Models2512.10858v3 · Dimitri von Rutte, Janis Fluri, Omead Pooladzandi et al.2025 · 0 citationsarXiv
Heads collapse, features stay: Why Replay needs big buffers2512.07400v2 · Giulia Lanzillotta, Damiano Meier, Thomas Hofmann2025 · 0 citationsarXiv
On the Emergence of Induction Heads for In-Context Learning2511.01033v2 · Tiberiu Musat, Tiago Pimentel, Lorenzo Noci et al.2025 · 0 citationsarXiv
Soft-Masked Diffusion Language Models2510.17206v2 · Michael Hersche, Samuel Moor-Smith, Thomas Hofmann et al.2025 · 0 citationsarXiv
Planner and Executor: Collaboration between Discrete Diffusion And Autoregressive Models in Reasoning2510.15244v2 · Lina Berrayana, Ahmed Heakl, Muhammad Abdullah Sohail et al.2025 · 0 citationsarXiv
Revisiting Knowledge Distillation: The Hidden Role of Dataset Size2510.15516v1 · Giulia Lanzillotta, Felix Sarnthein, Gil Kur et al.2025 · 0 citationsarXiv
FOCUS: Optimal Control for Multi-Entity World Modeling in Text-to-Image Generation2510.02315v2 · Eric Tillmann Bill, Enis Simsar, Thomas Hofmann2025 · 0 citationsarXiv
Barriers for Learning in an Evolving World: Mathematical Understanding of Loss of Plasticity2510.00304v3 · Amir Joudaki, Giulia Lanzillotta, Mohammad Samragh Razlighi et al.2025 · 0 citationsarXiv
Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models2509.22284v3 · Aleksandar Terzi'c, Nicolas Menet, Michael Hersche et al.2025 · 0 citationsarXiv
Presynaptic ATP Decreases During Physiological-Like Activity in Neurons Tuned for High-Frequency Transmission.40916622 · Straub, Isabelle, Kunstmann, Lukas, Baeza-Lehnert, Felipe et al.2025 · 4 citationsJournal of neurochemistry. 2025;169(9):e70212
The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?2507.08802v2 · Denis Sutter, Julian Minder, Thomas Hofmann et al.2025 · 0 citationsarXiv
The Importance of Being Lazy: Scaling Limits of Continual Learning2506.16884v2 · Jacopo Graldi, Alessandro Breccia, Giulia Lanzillotta et al.2025 · 0 citationsarXiv
Model Fusion via Retrofitting2507.00037v2 · Phoomraphee Luenam, Andreas Spanopoulos, Amit Sant et al.2025 · 0 citationsarXiv
Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment2506.10186v2 · Yuhui Ding, Thomas Hofmann2025 · 0 citationsarXiv
Causal Estimation of Tokenisation Bias2506.03149v1 · Pietro Lesci, Clara Meister, Thomas Hofmann et al.2025 · 0 citationsarXiv
JEDI: The Force of Jensen-Shannon Divergence in Disentangling Diffusion Models2505.19166v2 · Eric Tillmann Bill, Enis Simsar, Thomas Hofmann2025 · 0 citationsarXiv
Comparative analysis of early visual processes across presentation modalities: The event-related potential evoked by real-life, virtual reality, and planar objects.40199787 · Kisker, Joanna, Johnsdorf, Marike, Sagehorn, Merle et al.2025 · 8 citationsCognitive, affective & behavioral neuroscience. 2025;25(4):1022-1039
Generalized Interpolating Discrete Diffusion2503.04482v2 · Dimitri von Rutte, Janis Fluri, Yuhui Ding et al.2025 · 0 citationsarXiv
IC-Portrait: In-Context Matching for View-Consistent Personalized Portrait2501.17159v2 · Han Yang, Enis Simsar, Sotiris Anagnostidis et al.2025 · 0 citationsarXiv
SHYI: Action Support for Contrastive Learning in High-Fidelity Text-to-Image Generation2501.09055v1 · Tianxiang Xia, Lin Xiao, Yannick Montorfani et al.2025 · 0 citationsarXiv
On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages2412.19350v2 · Aleksandar Terzi'c, Michael Hersche, Giacomo Camposampiero et al.2024 · 0 citationsarXiv
UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint2412.15216v2 · Enis Simsar, Alessio Tonioni, Yongqin Xian et al.2024 · 0 citationsarXiv
Optimality of Right-Invariant Priors2412.12054v9 · Jannis Bolik, Thomas Hofmann2024 · 0 citationsarXiv
LoRACLR: Contrastive Adaptation for Customization of Diffusion Models2412.09622v2 · Enis Simsar, Thomas Hofmann, Federico Tombari et al.2024 · 7 citationsarXiv
MegaPortrait: Revisiting Diffusion Control for High-fidelity Portrait Generation2411.04357v1 · Han Yang, Sotiris Anagnostidis, Enis Simsar et al.2024 · 0 citationsarXiv
Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations2410.20107v2 · Amir Joudaki, Thomas Hofmann2024 · 0 citationsarXiv
Local and Global Decoding in Text Generation2410.10810v1 · Daniel Gareev, Thomas Hofmann, Ezhilmathi Krishnasamy et al.2024 · 0 citationsarXiv
PixLens: A Novel Framework for Disentangled Evaluation in Diffusion-Based Image Editing with Object Detection + SAM2410.05710v1 · Stefan Stefanache, Llu'is Pastor P'erez, Julen Costa Watanabe et al.2024 · 1 citationarXiv
An Art-centric perspective on AI-based content moderation of nudity2409.17156v1 · Piera Riccio, Georgina Curto, Thomas Hofmann et al.2024 · 1 citationarXiv
Career total: 1417 works. 586 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.