Thomas Wiegand

Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute — Germany

Computer Science · Physical Sciences

65h-index35.1kcitations455works2.22yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Video Coding and Compression Technologies(287), Advanced Vision and Imaging(171), Advanced Data Compression Techniques(160), Advanced Image Processing Techniques(101), Image and Video Quality Assessment(97)

Publications455 total

Selective Hydrogenation of Heteroarenes Using Supported Ruthenium Phosphide Nanoparticle Catalysts
Journal of the American Chemical Society·2025Open Access
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
Communications in computer and information science·2025Open Access
Nonlinear Modifications of Transform Coefficients in VVC Intra Coding
2025
Data-Driven Recursive Intra Prediction
2025
Ensuring medical AI safety: interpretability-driven detection and mitigation of spurious model behavior and associated data
Machine Learning·2025· 4 citedOpen Access
Künstliche Intelligenz auf dem Prüfstand: Anforderungen, Qualitätskriterien und Prüfwerkzeuge für medizinische Anwendungen
Bundesgesundheitsblatt - Gesundheitsforschung - Gesundheitsschutz·2025Open Access
Attribution-guided Pruning for Compression, Circuit Discovery, and Targeted Correction in LLMs
arXiv (Cornell University)·2025Open Access
From What to How: Attributing CLIP's Latent Components Reveals Unexpected Semantic Reliance
arXiv (Cornell University)·2025Open Access
The Atlas of In-Context Learning: How Attention Heads Shape In-Context Retrieval Augmentation
arXiv (Cornell University)·2025Open Access
Schwerpunkt künstliche Intelligenz in der Medizin – rechtliche Aspekte bei der Nutzung großer Sprachmodelle im klinischen Alltag
Die Innere Medizin·2025· 3 citedOpen Access
FADE: Why Bad Descriptions Happen to Good Features
arXiv (Cornell University)·2025Open Access
Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
arXiv (Cornell University)·2025· 4 citedOpen Access
Mechanistic understanding and validation of large AI models with SemanticLens
arXiv (Cornell University)·2025· 1 citedOpen Access
FADE: Why Bad Descriptions Happen to Good Features
2025Open Access
Pruning by Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
Lecture notes in computer science·2025· 4 cited
Opportunities and limitations of explaining quantum machine learning
arXiv (Cornell University)·2024Open Access
Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyond
arXiv (Cornell University)·2024Open Access
PINNfluence: Influence Functions for Physics-Informed Neural Networks
arXiv (Cornell University)·2024Open Access
Pruning By Explaining Revisited: Optimizing Attribution Methods to Prune CNNs and Transformers
arXiv (Cornell University)·2024Open Access
Nonlinear Transform Coding for VVC Intra Coding
2024· 2 cited
page 1 of 23Next →

Frequent Co-authors

Philipp Merkle(11), Gary J. Sullivan(10), Detlev Marpe(9), Karsten Müller(9), Heiko Schwarz(8), Aljoša Smolić(7), Wojciech Samek(5), Sebastian Bosse(4), Bernd Girod(4), Haricharan Lakshman(4), Klaus‐Robert Müller(3), Peter Kauff(3), Thomas Schierl(3), Martin Köppel(3), Dimitar Doshkov(3), Ajay Luthra(2), Anthony Joch(2), F. Kossentini(2), Thomas Stockhammer(2), Falk Schwendicke(2)