Conveners
Hybrid Machine Learning Session: Research Area Meeting
- Ramsés Sanchéz
Description
This session consists of one discussion and 7 short talks by Hybrid-ML researchers
-
Dr Ramsés Sanchéz (Lamarr institute, University of Bonn)19/02/2025, 10:00
Researchers at Hybrid-ML tackle a wide range of applied and theoretical problems, characterized by different data modalities, such as time series, graphs, natural language, images, and their combinations. Solving these problems requires drawing from an equally broad spectrum of background knowledge, from abstract algebra and statistical physics to cognitive psychology. Yet, despite this...
Go to contribution page -
Lio Schmitz19/02/2025, 10:20
Sketch-based Modeling and Animation are challenging problems due to the inherent ambiguity, style differences and lack of datasets. We explore how existing methods can be improved by integrating Diffusion Models for Video and 3D content generation. For this, Score-based Distillation Sampling, Optical Flow and alternative sketch representations are considered.
Go to contribution page -
Hongyu Zhou19/02/2025, 10:40
With a growing interest in 3D Gaussian splatting, there comes a need for geometry processing applications directly on this new representation. In this work, we propose a formulation to compute the Laplace-Beltrami operator, a commonly used tool in geometry processing, directly on Gaussian splatting leveraging the Mahalanobis distance, and show its improvement in accuracy compared to point...
Go to contribution page -
Tim Katzke19/02/2025, 11:00
Currently established graph anomaly detection methods predominantly operate in an unsupervised or self-supervised manner, assuming minimal anomaly contamination and relying solely on data-driven signals to infer notions of (a)normality. While these methods can, in theory, capture the relevant complex structural and attribute-based patterns, they typically do not allow for the meaningful...
Go to contribution page -
Simon Klüttermann19/02/2025, 11:40
My research focuses on ensemble methods for unsupervised learning tasks. Recently, I discovered a surprisingly effective approach for anomaly detection, which I named as a Polyra swarm. Upon further investigation, I found that Polyra exhibits a property analogous to the universal function approximation capability of neural networks. This insight has led me to explore an alternative paradigm...
Go to contribution page -
Zeyu Ding19/02/2025, 12:00
In this talk I introduce MCBench, a benchmark suite designed to assess the quality of Monte Carlo (MC) samples. The benchmark suite enables quantitative comparisons of samples by applying different metrics, including basic statistical metrics as well as more complex measures, in particular the sliced Wasserstein distance and the maximum mean discrepancy. We apply these metrics to point clouds...
Go to contribution page -
Florian Mai19/02/2025, 12:20
Large language models are strong heuristic reasoners, but their planning abilities remain poor. We introduce a method for language models to learn to plan from unlabeled data by using a planner model to predict many steps ahead and conditioning the language model on the predicted plans. A crucial parameter in this framework is the level of abstraction of the generated plans: While some tasks...
Go to contribution page -
Armin Berger, Helen Schneider19/02/2025, 12:40