PPaperPicks

Sebastian Lapuschkin

13 papers at tracked venues · 11 at CORE A* · active 2024–2026

DBLP profile ↗ORCID search ↗

Venues

NeurIPS ×4ACL ×2CVPR ×2ECCV ×2AAAI ×1ICLR ×1ICML ×1

Frequent coauthors

Dilyara Bareeva
DBLP profile ↗ORCID search ↗
×2
Maximilian Dreyer
DBLP profile ↗ORCID search ↗
×2
Simon Ostermann
DBLP profile ↗ORCID search ↗
×1
Bruno Puri
DBLP profile ↗ORCID search ↗
×1
Frederik Pahde
DBLP profile ↗ORCID search ↗
×1
Patrick Kahardipraja
DBLP profile ↗ORCID search ↗
×1
Reduan Achtibat
DBLP profile ↗ORCID search ↗
×1
Laura Kopf
DBLP profile ↗ORCID search ↗
×1
Gabriel Nobis
DBLP profile ↗ORCID search ↗
×1
Sayed Mohammad Vakilzadeh Hatefi
DBLP profile ↗ORCID search ↗
×1
Rohan Reddy Mekala
DBLP profile ↗ORCID search ↗
×1

Papers

  1. From Weights to Activations: Is Steering the Next Frontier of Adaptation?
    ACL 2026 ·
    Simon Ostermann
    DBLP profile ↗ORCID search ↗
  2. FADE: Why Bad Descriptions Happen to Good Features
    ACL 2025 ·
    Bruno Puri
    DBLP profile ↗ORCID search ↗
  3. Manipulating Feature Visualizations with Gradient Slingshots
    NeurIPS 2025 ·
    Dilyara Bareeva
    DBLP profile ↗ORCID search ↗
  4. Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
    ICLR 2025 ·
    Frederik Pahde
    DBLP profile ↗ORCID search ↗
  5. The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
    NeurIPS 2025 ·
    Patrick Kahardipraja
    DBLP profile ↗ORCID search ↗
  6. AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers
    ICML 2024 ·
    Reduan Achtibat
    DBLP profile ↗ORCID search ↗
  7. CoSy: Evaluating Textual Explanations of Neurons
    NeurIPS 2024 ·
    Laura Kopf
    DBLP profile ↗ORCID search ↗
  8. From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
    AAAI 2024 ·
    Maximilian Dreyer
    DBLP profile ↗ORCID search ↗
  9. Generative Fractional Diffusion Models
    NeurIPS 2024 ·
    Gabriel Nobis
    DBLP profile ↗ORCID search ↗
  10. Pruning by Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
    ECCV 2024 ·
    Sayed Mohammad Vakilzadeh Hatefi
    DBLP profile ↗ORCID search ↗
  11. Reactive Model Correction: Mitigating Harm to Task-Relevant Features via Conditional Bias Suppression
    CVPR 2024 ·
    Dilyara Bareeva
    DBLP profile ↗ORCID search ↗
  12. Synthetic Generation of Dermatoscopic Images with GAN and Closed-Form Factorization
    ECCV 2024 ·
    Rohan Reddy Mekala
    DBLP profile ↗ORCID search ↗
  13. Understanding the (Extra-)Ordinary: Validating Deep Model Decisions with Prototypical Concept-based Explanations
    CVPR 2024 ·
    Maximilian Dreyer
    DBLP profile ↗ORCID search ↗