Scholar
Lukas Thede
Google Scholar ID: YC-3YaYAAAAJ
IMPRS-IS, University of Tuebingen, Helmholtz Munich
Artificial Intelligence
Continual Learning
Knowledge Distillation
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
58
H-index
4
i10-index
2
Publications
7
Co-authors
0
Publications
9 items
Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued Pretraining
2026
Cited
0
MedKIT: Evaluating Knowledge Integration and Generalization in Large Language Models
2026
Cited
0
Thomson: Continual Learning of Frontier Models for SovereignAI
2026
Cited
0
Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency
2026
Cited
0
CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training
2026
Cited
1
Beyond the final layer: Attentive multilayer fusion for vision transformers
2026
Cited
0
Investigating Structural Pruning and Recovery Techniques for Compressing Multimodal Large Language Models: An Empirical Study
2025
Cited
0
Understanding the Limits of Lifelong Knowledge Editing in LLMs
2025
Cited
0
Load more
