Muhammad Taha Mukhtar
Visiting Researcher, DFKI
Research interests
Interpretability and representation learning.
Publications
- M. T. Mukhtar, S. M. A. Kazmi, K. Naseem, M. A. Chattha, A. Dengel, S. Ahmed, M. N. Bajwa, M. I. Malik. “SLUM-i: Semi-Supervised Learning for Urban Mapping of Informal Settlements.” arXiv:2602.04525, 2026.arXivPDFCode
BibTeX
@misc{mukhtar2026slumi, title = {SLUM-i: Semi-Supervised Learning for Urban Mapping of Informal Settlements}, author = {Muhammad Taha Mukhtar and Syed Musa Ali Kazmi and Khola Naseem and Muhammad Ali Chattha and Andreas Dengel and Sheraz Ahmed and Muhammad Naseer Bajwa and Muhammad Imran Malik}, year = {2026}, eprint = {2602.04525}, archivePrefix = {arXiv}, primaryClass = {cs.CV}, url = {https://arxiv.org/abs/2602.04525} } - H. Aslam, M. A. Chattha, M. T. Mukhtar, M. I. Malik, A. Dengel, S. Ahmed. “E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability.” arXiv:2605.10261, 2026.arXivPDF
BibTeX
@misc{aslam2026etcav, title = {E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability}, author = {Hasib Aslam and Muhammad Ali Chattha and Muhammad Taha Mukhtar and Muhammad Imran Malik and Andreas Dengel and Sheraz Ahmed}, year = {2026}, eprint = {2605.10261}, archivePrefix = {arXiv}, primaryClass = {cs.AI}, url = {https://arxiv.org/abs/2605.10261} }
Research software
Talks
- Resilient Futures: GeoAI for Farms and SLUMs, NUST, IslamabadOct 2025
- Remote Sensing Workshop, NUST, IslamabadOct 2024
Experience
- DFKI, Visiting Researcher2024 to present
- NCAI, Research Associate2025 to 2026
- Google Summer of Code, CVAT2024
Education
BS Computer Science, NUST2025
Thesis on semi-supervised slum segmentation, carried out at DFKI.