Moritz Vandenhirtz
  • Bio
  • Background
  • Publications
  • Academic Service
  • Publications
    • From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection
    • From Logits to Hierarchies: Hierarchical Clustering made Simple
    • Interpretable Diffusion Models with B-cos Networks
    • Post-hoc Stochastic Concept Bottleneck Models
    • Leveraging the structure of medical data for improved representation learning
    • Structure is Supervision: Multiview Masked Autoencoders for Radiology
    • Measuring Leakage in Concept-Based Methods: An Information Theoretic Approach
    • RadVLM: A multitask conversational vision-language model for radiology
    • TreeDiffusion: Hierarchical Generative Clustering for Conditional Diffusion
    • Stochastic Concept Bottleneck Models
    • Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
    • Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
    • scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data
    • Tree Variational Autoencoders
    • This Reads Like That: Deep Learning for Interpretable Natural Language Processing
    • Signal Is Harder To Learn Than Bias: Debiasing with Focal Loss
    • Two decades of active surveillance for prostate cancer in a single-center cohort: favorable outcomes after transurethral resection of the prostate
  • Background
  • Academic Service

Interpretable Diffusion Models with B-cos Networks

2025·
Nicola Bernold
Moritz Vandenhirtz
Moritz Vandenhirtz
,
Alice Bizeul
,
Julia E Vogt
PDF Cite
Last updated on 2025
← From Logits to Hierarchies: Hierarchical Clustering made Simple
Post-hoc Stochastic Concept Bottleneck Models →

© 2025 Moritz Vandenhirtz. This work is licensed under CC BY NC ND 4.0