Intern / Master Thesis (All Genders) - Gen-ai for Joint Source and Channel Coding of Short Multimedia Packets

The Fraunhofer-Gesellschaft currently operates 76 institutes and research institutions throughout Germany and is the world’s leading applied research organization. Around 32 000 employees work with an annual research budget of 3.4 billion euros. The Fraunhofer Institute for Integrated Circuits IIS, located in Erlangen, is the largest institute of the Fraunhofer-Gesellschaft with more than 1 200 employees. Conventional digital communication systems rely on Shannon’s separation theorem, which states that optimal performance can be achieved by independently designing source and channel coding components. However, this principle holds only asymptotically for infinitely long packets. In modern low-latency and short-packet communication scenarios, such as real-time multimedia transmission, this separation results in performance loss due to several factors: - The optimality of the separation theorem breaks down for short block lengths. - Real-world source coding does not yield ideally independent and identically distributed bitstreams. To overcome these limitations, recent research explores generative AI-based transmission schemes. For instance, demonstrates the effectiveness of generative AI in communication tasks1, while proposes a variational autoencoder (VAE) architecture that jointly encodes and modulates images, outperforming state-of-the-art separate digital solutions2. **You are passionate about innovation and eager to tackle fundamental challenges in future communication systems? Then have a look at our offer** **Here’s how you will make a difference** The position is offered under the **»Broadband and Broadcasting«** department. In the project that this thesis will be part of, we design machine learning based signal processing for physical layer communication. This thesis provides an exciting opportunity to contribute to cutting-edge research at the intersection of machine learning and communication engineering. The work will be conducted in close collaboration with our R&D team and may lead to publication in a reputable venue. - **Explore the foundations**: You conduct a comprehensive literature review on generative models applied to physical layer communication. - **Shape innovative solutions**: You design and implement generative AI-based transmission schemes (e.g., using VAE, GAN, or diffusion models). - **Evaluate progress**: You evaluate the performance of these schemes against conventional digital baselines in terms of distortion, reliability, and efficiency. **What you bring to the table** - You **study**in the field of **communication theory**, **signal processing**, and **machine learning**. - You have a **solid understanding** of **physical layer concepts**, including modulation and channel coding. - You have a **hands-on experience** with **Python**and **machine learning frameworks** such as PyTorch or TensorFlow, NumPy, SciPy. **What you can expect** - **Organize your schedule**: Benefit from flexible working hours that are perfectly compatible with your studies. - **Become part of a creative team**: Experience an open and friendly working atmosphere in which your ideas are valued. - **Variety that inspires**: Look forward to diverse tasks that inspire and challenge you. - **Innovation that inspires**: Exciting and pioneering projects that make a real difference. We will agree your start date and weekly working hours with you individually (for an internship at least three months). You can reduce your hours before exams and increase them during semester breaks. You can set your working days flexibly. After your studies, there are attractive opportunities to join the institute on a full-time or part-time basis. You can flexibly determine the working days of your fixed-term employment contract. **Interested? Join our team and work with us on the technology of tomorrow** Fraunhofer-Institute for Integrated Circuits IIS [1] N. Van Huynh et al., "Generative AI for Physical Layer Communications: A Survey," in IEEE Transactions on Cognitive Communications and Networking, vol. 10, no. 3, pp. 706-728, June 2024 [2] Y. Bo, Y. Duan, S. Shao and M. Tao, "Joint Coding-Modulation for Digital Semantic Communications via Variational Autoencoder," in IEEE Transactions on Communications, vol. 72, no. 9, pp. 5626-5640, Sept. 2024