Thomas Schmied
Scholar

Thomas Schmied

Google Scholar ID: rEfdigIAAAAJ
PhD Student, Institute for Machine Learning, Johannes Kepler University Linz
Deep LearningReinforcement LearningNatural Language ProcessingContinual Learning
Google Scholar↗
Citations & Impact
All-time
Citations
144
 
H-index
8
 
i10-index
8
 
Publications
13
 
Co-authors
18
list available
Contact
No contact links provided.
Publications
7 items
KVpop -- Key-Value Cache Compression with Predictive Online Pruning
2026
Cited
0
Effective Distillation to Hybrid xLSTM Architectures
2026
Cited
0
pLSTM: parallelizable Linear Source Transition Mark networks
2025
Cited
0
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
2025
Cited
0
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
arXiv.org · 2024
Cited
0
Retrieval-Augmented Decision Transformer: External Memory for In-context RL
arXiv.org · 2024
Cited
9
Parameter Efficient Fine-tuning via Explained Variance Adaptation
2024
Cited
4
Resume (English only)
Co-authors
18 total
Sepp Hochreiter
Sepp Hochreiter
Institute for Machine Learning, Johannes Kepler University Linz
Fabian Paischer
Fabian Paischer
Senior Scientist, Institute for Machine Learning, ELLIS Unit / University Linz, EmmiAI
Razvan Pascanu
Razvan Pascanu
Google DeepMind
Vihang Patil
Vihang Patil
Institute for Machine Learning, JKU, Linz
Markus Hofmarcher
Markus Hofmarcher
Institute for Machine Learning, Johannes Kepler University Linz
Benedikt Alkin
Benedikt Alkin
Emmi AI
Korbinian Pöppel
Korbinian Pöppel
ELLIS Unit Linz, Johannes-Kepler University Linz
Co-author 8
Co-author 8