Author

Lukas Thede

Observed name: Thede, Lukas

Institutions: Helmholtz Munich, Tübingen AI Center, Munich Center for Machine Learning, Imperial College London, University of Tübingen

Observed institutions: Karlsruhe Institute of Technology, Google (United States), Helmholtz Munich, Tübingen AI Center, Munich Center for Machine Learning, Imperial College London, University of Tübingen

OpenAlex ID: A5039022463

Learning to Defer with Limited Expert Predictions

2023 · Patrick Hemmer, Lukas Thede, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 20

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

2025 · Thede, Lukas, Roth, Karsten, et al. · arXiv (Cornell University) · 16

Reflecting on the State of Rehearsal-free Continual Learning with Pretrained Models

2024 · Thede, Lukas, Roth, Karsten, et al. · arXiv (Cornell University) · 7

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

2023 · Roth, Karsten, Thede, Lukas, et al. · arXiv (Cornell University) · 5

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training

2026 · Thede, Lukas, Winzeck, Stefan, et al. · arXiv (Cornell University) · 4

Attentive multilayer fusion for vision transformers

2026 · Ciernik, Laure, Morik, Marco, et al. · arXiv (Cornell University) · 4

Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study

2026 · Yiran Huang, Lukas Thede, et al. · Lecture notes in computer science · 3

Thomson: Continual Learning of Frontier Models for SovereignAI

2026 · Chen, Shengzhuang, Parker, Jerrod, et al. · arXiv (Cornell University) · 2

Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency

2026 · Yiran Huang, Lukas Thede, et al. · International Journal of Computer Vision · 2

Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining

2026 · Thede, Lukas, Chen, Shengzhuang, et al. · arXiv (Cornell University)

MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models

2026 · Thede, Lukas, Atri, Yash Kumar, et al. · arXiv (Cornell University)

Works count: 12

Citation count: 63

H-index: 4

I10-index: 2