Peyman Mohseni Kiasari

Projektass. / MSc

Peyman Mohseni Kiasari

Role

PreDoc Researcher
Cyber-Physical Systems, E191-01

Contact

peyman.kiasari@tuwien.ac.at
vCard from TISS

Publications

The Master Key Filters Hypothesis: Deep Filters Are General / Babaiee, Z., Mohseni Kiasari, P., Rus, D., & Grosu, R. (2025). The Master Key Filters Hypothesis: Deep Filters Are General. In T. Walsh, J. Shah, & Z. Kolter (Eds.), Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (pp. 1809–1816). AAAI Press. https://doi.org/10.1609/aaai.v39i2.32175
Projects: MATTO-GBM (2024–2027) / TA-CPS (2023–2028)
Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models / Babaiee, Z., Mohseni Kiasari, P., Rus, D., & Grosu, R. (2025). Visual Graph Arena: Evaluating Visual Conceptualization of Vision and Multimodal Large Language Models. In Forty-second International Conference on Machine Learning : ICML 2025. Forty-second International Conference on Machine Learning (ICML 2025), Vancouver, Canada.
Project: TA-CPS (2023–2028)
We Need Far Fewer Unique Filters Than We Thought / Babaiee, Z., Kiasari, P., Rus, D., & Grosu, R. (2024). We Need Far Fewer Unique Filters Than We Thought. In NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning. SciForDL’24, Vancouver, Canada.
Project: MATTO-GBM (2024–2027)
Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels / Babaiee, Z., Mohseni Kiasari, P., Rus, D., & Grosu, R. (2024). Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels. In The Twelth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. The Twelfth International Conference on Learning Representations (ICLR 2024), Austria. http://hdl.handle.net/20.500.12708/203933
Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields / Babaiee, Z., Mohseni Kiasari, P., Rus, D., & Grosu, R. (2024). Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields. In 2024 IEEE Winter Conference on Applications of Computer Vision (pp. 8216–8225). https://doi.org/10.1109/WACV57701.2024.00803
Project: MATTO-GBM (2024–2027)