Get started
Author

Wojciech Samek

Relevance-Guided Activation Sparsification for Bandwidth-Efficient Collaborative Inference
2025 · Maximilian Andreas Höfler, Daniel Becking, et al. · IEEE International Conference on Computer Vision Workshops · 1
Fractional Diffusion Bridge Models
2025 · Gabriel Nobis, Maximilian Springenberg, et al. · neural information processing systems · 1
PDF
Heads of Security: Learned Attention Gates Improve Prompt Injection Robustness
2026 · Shilov, Igor, Yang, Xiaoxue, et al. · arXiv (Cornell University)
PDF
Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains
2026 · Baur, Simon, Honda, Sumire, et al. · arXiv (Cornell University)
PDF
Chain of Thought Monitoring Can Fail Even When CoT Is Necessary
2026 · Bürger, Lennart, Komorowski, Piotr, et al. · arXiv (Cornell University)
PDF
Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious Correlations
2026 · von Klinski, Maximilian, Lapuschkin, Sebastian, et al. · arXiv (Cornell University)
PDF
Diffusion as an Alternative to Linear Methods in ANN-Brain Encoding Models
2026 · Belova, Arina, Nobis, Gabriel, et al. · German Neuroinformatics Node
Can Data Attribution Filter Out Subliminal Learning? Not Reliably
2026 · Weckbecker, Moritz, Jena, Sweta, et al. · arXiv (Cornell University)
PDF
ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers
2026 · Berend, Jim, Achtibat, Reduan, et al. · arXiv (Cornell University)
PDF
Safety Signals to Verify NetOps Agents with Action-Level Granularity
2026 · Labarta, Tobias, Pahde, Frederik, et al. · arXiv (Cornell University)
PDF
Modelpedia: A Catalog of Model Findings for the Meta-Science of AI
2026 · Bernat, Franciszek, Płudowski, Dawid, et al. · arXiv (Cornell University)
PDF
ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on
2026 · Rane, Roshan Prakash, Simnacher, Marco, et al. · arXiv (Cornell University)
PDF
Concept-based explanation of gene expression prediction from H&E images
2026 · Muench, Amos, Thielmann, Jonathan, et al. · arXiv (Cornell University)
PDF
A Privacy Study of Sparse Collaborative Inference
2026 · Hoefler, Maximilian Andreas, Mueller, Karsten, et al. · arXiv (Cornell University)
PDF
Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning
2026 · Hoefler, Maximilian Andreas, Mueller, Karsten, et al. · arXiv (Cornell University)
PDF
FedXDS: Leveraging Model Attribution Methods to counteract Data Heterogeneity in Federated Learning
2026 · Hoefler, Maximilian Andreas, Mueller, Karsten, et al. · arXiv (Cornell University)
PDF
Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs
2026 · Harder, Nico, Becking, Daniel, et al. · arXiv (Cornell University)
PDF
INDEQS: Informed Neural controlled Differential EQuationS
2026 · Detzel, Michael, Nobis, Gabriel, et al. · arXiv (Cornell University)
PDF
Predicting Future Behaviors in Reasoning Models Enables Better Steering
2026 · Kortukov, Evgenii, Komorowski, Piotr, et al. · arXiv (Cornell University)
PDF
Fast & Faithful Function Vectors
2026 · Pham, Minh An, Segeler, Anton, et al. · arXiv (Cornell University)
PDF
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
2026 · Association for Computational Linguistics 2026, A. Hedderich, Michael, et al. · Underline Science Inc.
$α$-TCAV: A Unified Framework for Testing with Concept Activation Vectors
2026 · Schnoor, Ekkehard, Said, Jawher, et al. · arXiv (Cornell University)
PDF
Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge
2026 · Feldhus, Nils, Baeumel, Tanja, et al. · arXiv (Cornell University)
PDF
Playing the network backward: A Game Theoretic Attribution Framework
2026 · Zimmermann, Jakob Paul, Berend, Jim, et al. · arXiv (Cornell University)
PDF
Knowledge-Free Correlated Agreement for Incentivizing Federated Learning
2026 · Witt, Leon, Abbasli, Togrul, et al. · arXiv (Cornell University)
PDF
Works count: 36
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type