Scholar
Tuomas Oikarinen
Google Scholar ID: M3KZnPwAAAAJ
UC San Diego
Machine Learning
Interpretability
Mechanistic Interpretability
Explainable AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
791
H-index
9
i10-index
9
Publications
20
Co-authors
5
list available
Publications
6 items
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
2026
Cited
0
Multimodal Concept Bottleneck Models
2026
Cited
0
CI-CBM: Class-Incremental Concept Bottleneck Model for Interpretable Continual Learning
2026
Cited
0
Faithful and Stable Neuron Explanations for Trustworthy Mechanistic Interpretability
2025
Cited
0
Evaluating Neuron Explanations: A Unified Framework with Sanity Checks
2025
Cited
0
Interpretable Generative Models through Post-hoc Concept Bottlenecks
2025
Cited
0
Co-authors
4 total
Tsui-Wei Weng
UCSD
Chung-En Sun
University of California - San Diego
Ge Yan
UC San Diego
Akshay Kulkarni
PhD student, UC San Diego
