Lokesh Veeramacheneni

I am a PhD student advised by Prof. Dr. Juergen Gall at University of Bonn. Currently, I am supported by HPC/A-Lab at University. My broader area of reserach is deep learning for computer vision. Particularly, I enjoy working with Diffusion models and efficient training of deep neural networks. I collaborate with distinguished researchers such as Prof. Dr. Hilde Kuehne and Dr. Moritz Wolter.

Prior to my PhD, I worked as a Junior software developer at RE: GmbH with focus in Ruby on Rails and I got my M.Sc degree in Autonomous Systems at Hochschule Bonn-Rhein-Sieg.

Email / Scholar / Github

Research

	Canonical Rank Adaptation: An Efficient Fine-Tuning Strategy for Vision Transformers Lokesh Veeramacheneni, Moritz Wolter, Hilde Kuehne, Juergen Gall arXiv, 2025 (Coming Soon)
	Position: More Rigorous Software Engineering Would Improve Reproducibility in Machine Learning Research Moritz Wolter, Lokesh Veeramacheneni arXiv, 2025 Paper / Code
	Fréchet Wavelet Distance: A Domain-Agnostic Metric for Image Generation Lokesh Veeramacheneni, Moritz Wolter, Hilde Kuehne, Juergen Gall Thirteenth International Conference on Learning Representations, 2025 Project Page / Paper / Code / Pip
	On the Stability of Neural Segmentation in Radiology Moritz Wolter, Lokesh Veeramacheneni, Bettina Baeßler, Ulrike I Attenberger, Barbara D Wichtmann European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2024 Paper / Code
	Canonical convolutional neural networks Lokesh Veeramacheneni, Moritz Wolter, Reinhard Klein, Jochen Garcke International Joint Conference on Neural Networks, 2022 Paper / Code

Workshops

	Enhancing Explainability with Multimodal Context Representations for Smarter Robots Anargh Viswanath, Lokesh Veeramacheneni, Hendrik Buschmeier 3rd Workshop on Explainability in HRC, 2025 Paper * denotes equal contribution
	A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation Lokesh Veeramacheneni, Matias Valdenegro Toro NeurIPS Workshop on Robot Learning: Trustworthy Robotics, 2022 Paper

Teaching

University of Bonn	Part of tutoring team for - Foundations of Machine Learning SoSe23, WiSe23, WiSe24 - Foundations of Machine Learning for Principal Investigators WiSe23, SoSe25 - Advanced Machine Learning SoSe24
Hochschule Bonn-Rhein-Sieg	C++ section in Foundation course WiSe19, SoSe20, WiSe20, SoSe21

Website design adopted from Jon Barron.