Munich AI, Machine Learning and Computer Vision Meetup

Explainable AI (XAI) often falls short at runtime, particularly when extracting concepts from intermediate layers without predefined labels. While current open-source tools focus on model explainability post hoc, they lack efficient dataset-building mechanisms from these crucial layers. This talk introduces a new open-source repository designed to seamlessly compute, store, and train on raw tensor data from intermediate layers—scaling from minimal compute to terabytes of data. By enabling structured dataset generation and improving mechanistic interpretability, this initiative pushes the boundaries of XAI, making it more practical and accessible for real-world applications.

Predicting future human motion is a key challenge in generative AI and computer vision, as generated motions should be realistic and diverse at the same time. This talk presents a novel approach that leverages top-performing latent generative diffusion models with a novel paradigm. Nonisotropic Gaussian diffusion leads to better performance, fewer parameters, and faster training at no additional computational cost. We will also discuss how such benefits can be obtained in other application domains.

High-performing models start with high-quality data—but finding noisy, mislabeled, or edge-case samples across massive datasets remains a significant bottleneck. In this session, we’ll explore a scalable approach to curating and refining large-scale visual datasets using semantic search powered by transformer-based embeddings. By leveraging similarity search and multimodal representation learning, you’ll learn to surface hidden patterns, detect inconsistencies, and uncover edge cases. We’ll also discuss how these techniques can be integrated into data lakes and large-scale pipelines to streamline model debugging, dataset optimization, and the development of more robust foundation models in computer vision. Join us to discover how semantic search reshapes how we build and refine AI systems.