Thesis

For Master / Bachelor thesis we currently offer the following open topics. If you are interested in one of the topics, don't hesitate to contact us. We would be happy to discuss the topic with you in a physical meeting.

Opening Thesis

  • 3D Model Segmentation Leveraging 2D Cues and Representations

    2025/09/08

    Master thesis

    Supervisors: Prof. Dr.-Ing. Grace Li Zhang, Mengnan Jiang, M.Sc.

    Announcement as PDF

  • Dynamic Rank Allocation for Efficient LLM Inference on GPUs

    2025/07/11

    Master thesis

    Supervisors: Prof. Dr.-Ing. Grace Li Zhang, Jingcun Wang, M.Sc.

    Announcement as PDF

  • Explainable AI for Efficient Inference on Hardware

    2025/07/11

    Master thesis

    Supervisor: Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

  • LUT-based Neural Networks

    2025/07/11

    Master thesis

    Supervisor: Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

  • When Variations Meet Early-Exit

    2025/07/11

    Master thesis

    Supervisor: Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

  • Conversion of Convolutional Neural Networks (CNNs) into Logic Flows for Efficient Execution on RISC-V CPUs

    2025/04/14

    Master thesis

    When CNNs are deployed on edge devices, often a huge number of dedicated hardware multiply-accumulate (MAC) units are not available to process massive MAC operations in CNNs. Instead, CPUs exist in nearly all these devices. CPUs themselves are not good at executing such mathematical operations on a large scale, since they opt more to execute control flow logic. To execute CNNs on CPUs eGiciently, it is critical to convert their MAC operations into logic flows. In this master thesis, the execution of a convolutional neural network (CNN) will be converted to logic flows, so that it can be executed with low latency and low energy on CPUs.

    Announcement as PDF

  • Exploring Robust Optical Accelerators for Neural Networks

    2025/03/17

    Master thesis

    Supervisor: Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

  • Efficient LLM Inference with Weight Selection

    2025/03/17

    Master thesis

    Supervisors: Jingcun Wang, M.Sc., Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

  • Dynamic power allocation for hierarchical neural networks on FPGAs

    2025/03/17

    Master thesis

    Supervisor: Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

Thesis Template

All Students are required to use the following LaTex template for their thesis : Thesis Template

Ongoing Master Theses

  • Enhancing Multi-View Editable Vector Graphics with Generative AI

    2025/05/08

    Supervisors: Mengnan Jiang, M.Sc., Prof. Dr.-Ing. Grace Li Zhang

    Announcement as PDF

Finished Master Theses

  • AI for Science: Reinfocrement Learning for high entropy alloy design. Weijia He(07.01.2025- 15.07.2025)
  • Enhancing RISC-V through AI Accelerator Integration for Efficient Machine Learning at the Edge. Balasubramanian Asha Hareesh(20.01.2025 – 28.07.2025)
  • Explaining Neural Networks with Early-Exit. Yibo Yuan(04.11.2024 – 05.05.2025)
  • Security Vulnerability Detection in Source Code. Srividya Chamarajanagar Ravikumar(02.12.2024 – 03.06.2025)
  • Pruning Neural Networks with Classification Activation Paths (opens in new tab) Mengnan Jiang (21.02.2023 – 21.08.2023)
  • Quantization for Neural Networks based on Classification Difficulty Wanqi Yang (01.03.2023 – 15.09.2023)
  • Neural Network Accelerator Design with Logic Minimization Carlos José Llorente Cortijo (06.04.2023 – 26.09.2023)
  • Layer-wise Selection of Weights and Activations for Power-Efficient Neural Network Acceleration (opens in new tab) Fiona Ball (29.02.2024 – 19.09.2024)
  • Efficient Circuits of Convolutional Neural Networks. Chen Zhang (04.04.2024 – 02.10.2024)
  • Circuit optimization for neural networks in high-throughput applications. Jingang Zhang(10.05.2024 – 07.11.2024)