Projects MLI

Generating Highly Designable Proteins with Geometric Algebra Flow Matching
Generating structurally diverse and physically realizable protein backbones remains one of the grand challenges in protein design. We propose a generative …
Read more
Diffusion models for protein design
Generative deep learning has transformed protein design, enabling the creation of new protein structures, interactions, and functions with high precision, by …
Read moreMaster and Bachelor thesis projects
Extending Graph Neural CDEs to Directed and Heterogeneous Graphs
In recent years, Neural Differential Equations (NDEs) [1, 2] have emerged as a powerful bridge between dynamical systems and deep learning, finding applications in…
Equivariant NNs and Geometric Priors in Temporal Non-linear ICA
Many real-world processes, such as human motion, molecular dynamics, and neural activity, exhibit inherent geometric structures that standard nonlinear ICA models ignore…
Enhancing Large Language Model Reasoning with Graph Neural Networks
Large Language Models (LLMs) have demonstrated exceptional performance in tasks such as text generation, question-answering, and summarization. However, they…
Equivariant Generative Models for Protein Structure
Machine learning has revolutionized the fields of protein structure prediction and protein design in the past few years, as recognized by the Nobel Prize in Chemistry in 2024…
Spectral Analysis of Graph Transformers via Dynamical Systems
Transformers have demonstrated remarkable success across various domains, including natural language processing, vision, and, more recently, graph-based tasks…
Search Strategies for Large Language Model Inference
Effective reasoning requires combining multiple cognitive abilities: logical inference, knowledge retrieval, and combinatorial search. While Large Language Models (LLMs) show strong reasoning potential, they often…
Graph Neural Networks for Molecular Force Fields
For the simulation of molecular systems, atomic forces need to be predicted in each timestep. While those forces can be derived from quantum mechanical calculations…