Praktikum, Abschlussarbeit bei Wenxuan Ye in Online
Eingestellt am 17.07.2025
Are you excited by the rapid evolution of Large Language Models (LLMs) and curious about the architectural innovations that drive their remarkable capabilities? Are you interested in pushing beyond current paradigms and exploring how modules within LLMs might organize and coordinate themselves? This project investigates a promising research direction by exploring novel LLM architectures that brings unprecedented computational efficiency and flexibility, and holds potential to revolutionize the traditional boundaries of AI systems. We are seeking outstanding students to collaborate on this research area. Our lab is led by Prof. Volker Tresp from LMU, one of PIs of European Laboratory for Learning and Intelligent Systems (ELLIS) fellowship program, the first distinguished research scientist at Siemens Corporate Technology, and PI of Munich Center of Machine Learning (MCML). We have established strong track record with high-quality publications at premier venues (NeurIPS, ICLR, ACL, EMNLP, NAACL, AAAI, UAI, CIKM, etc.).
This research project offers opportunities to work alongside brilliant PhD researchers and excellent publication potential. You will develop in-depth understanding of cutting-edge methodologies for advancing LLM research, and gain precious hands-on engineering experience in large-scale deployment, pretraining and evaluation of LLMs.
Topic Description: Concrete LLM-related topics including novel architectural designs, large-scale pretraining and deployment, parameter efficiency, dynamic neural network, etc.
Requirements:
● Study (Bachelor/Master) in computer
science, electrical engineering, physics,
mathematics, or related field;
● Strong understanding in machine learning
and deep learning;
● Experience with transformer and LLMs /
distributed systems preferred;
● Strong programming skills in Python and
deep learning framework (PyTorch preferred);
● Strong motivation and independent working
Additional Information:
Start: immediate availability preferred
Duration: 6-9 months
Keine Angabe
Keine Angabe
Online (Deutschland)
Englisch
Informatik, Informatik - Informatik
Wenxuan Ye
Boltzmannstraße 3
85748 Munich, Deutschland
Yilun Liu
yilun.liu@tum.de
Bewerbungen an diese E-Mail Adresse
Alumni & Career übernimmt keine Gewähr für die Inhalte dieser Stellenanzeige. Sehen Sie ein Problem mit dieser Stellenanzeige? Melden Sie es uns!
TUM Alumni & Career
The goal of this webinar is to supply you with best practises to be successful in an application process with AI.
