324 citations · 1.4k across the 135 of their papers we have counts for
21 papers · 1 filter
DRAW2ACT: Turning Depth-Encoded Trajectories into Robotic Demonstration Videos
Yang Bai, Liudi Yang, George Eskandar +4
Video diffusion models provide powerful real-world simulators for embodied AI but remain limited in controllability for robotic manipulation. Recent works on trajectory-conditioned…
Explainable Learning Based Regularization of Inverse Problems
Martin Burger, Samira Kabri, Gitta Kutyniok +2
Machine learning techniques for the solution of inverse problems have become an attractive approach in the last decade, while their theoretical foundations are still in their infan…
CHEM: Estimating and Understanding Hallucinations in Deep Learning for Image Processing
Jianfei Li, Ines Rosellon-Inclan, Gitta Kutyniok +1
Deep learning-based methods have recently achieved significant success in image reconstruction problems. However, challenges have emerged, as these methods may generate unrealistic…
Random Spiking Neural Networks are Stable and Spectrally Simple
Ernesto Araya, Massimiliano Datres, Gitta Kutyniok
Spiking neural networks (SNNs) are a promising paradigm for energy-efficient computation, yet their theoretical foundations-especially regarding stability and robustness-remain lim…
When is a System Discoverable from Data? Discovery Requires Chaos
Zakhar Shumaylov, Peter Zaika, Philipp Scholl +3
The deep learning revolution has enabled major AI advances in physical sciences, particularly in discovering dynamical systems from observational data. Yet the reliability of learn…
Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping
Liudi Yang, Yang Bai, Yuhao Wang +4
Robotic grasping under uncertainty remains a fundamental challenge due to its uncertain and contact-rich nature. Traditional rigid robotic hands, with limited degrees of freedom an…
Improved probabilistic regression using diffusion models
Carlo Kneissl, Christopher Bülte, Philipp Scholl +1
Probabilistic regression models the entire predictive distribution of a response variable, offering richer insights than classical point estimates and directly allowing for uncerta…
Uncertainty Quantification for Regression: A Unified Framework based on kernel scores
Christopher Bülte, Yusuf Sale, Gitta Kutyniok +1
Regression tasks, notably in safety-critical domains, require reliable uncertainty quantification, yet the literature remains largely classification-focused. To address this, we in…
A Variational Framework for the Complexity of PDE Solutions
Juan Esteban Suarez Cardona, Holger Boche, Gitta Kutyniok
Partial Differential Equations (PDEs) are fundamental mathematical models for describing physical phenomena, yet most PDEs of practical interest require numerical approximations. T…
RoboEnvision: A Long-Horizon Video Generation Model for Multi-Task Robot Manipulation
Liudi Yang, Yang Bai, George Eskandar +7
We address the problem of generating long-horizon videos for robotic manipulation tasks. Text-to-video diffusion models have made significant progress in photorealism, language und…
Time to Spike? Understanding the Representational Power of Spiking Neural Networks in Discrete Time
Duc Anh Nguyen, Ernesto Araya, Adalbert Fono +1
Recent years have seen significant progress in developing spiking neural networks (SNNs) as a potential solution to the energy challenges posed by conventional artificial neural ne…
RoboSwap: A GAN-driven Video Diffusion Framework For Unsupervised Robot Arm Swapping
Yang Bai, Liudi Yang, George Eskandar +5
Recent advancements in generative models have revolutionized video synthesis and editing. However, the scarcity of diverse, high-quality datasets continues to hinder video-conditio…
Revisiting Glorot Initialization for Long-Range Linear Recurrences
Noga Bar, Mariia Seleznova, Yotam Alexander +2
Proper initialization is critical for Recurrent Neural Networks (RNNs), particularly in long-range reasoning tasks, where repeated application of the same weight matrix can cause v…
Interpretable Robotic Friction Learning via Symbolic Regression
Philipp Scholl, Alexander Dietrich, Sebastian Wolf +4
Accurately modeling the friction torque in robotic joints has long been challenging due to the request for a robust mathematical description. Traditional model-based approaches are…
Conflicting Biases at the Edge of Stability: Norm versus Sharpness Regularization
Maria Matveev, Vit Fojtik, Hung-Hsu Chou +2
The remarkable generalization properties of overparameterized networks are often attributed to implicit biases, such as norm minimization at small learning rates and low sharpness…
GradPCA: Leveraging NTK Alignment for Reliable Out-of-Distribution Detection
Mariia Seleznova, Hung-Hsu Chou, Claudio Mayrink Verdun +1
We introduce GradPCA, an Out-of-Distribution (OOD) detection method that exploits the low-rank structure of neural network gradients induced by Neural Tangent Kernel (NTK) alignmen…
Graph Representational Learning: When Does More Expressivity Hurt Generalization?
Sohir Maskey, Raffaele Paolino, Fabian Jogl +2
Graph Neural Networks (GNNs) are powerful tools for learning on structured data, yet the relationship between their expressivity and predictive performance remains unclear. We intr…
Graph Neural Networks for Enhancing Ensemble Forecasts of Extreme Rainfall
Christopher Bülte, Sohir Maskey, Philipp Scholl +2
Climate change is increasing the occurrence of extreme precipitation events, threatening infrastructure, agriculture, and public safety. Ensemble prediction systems provide probabi…
An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regression
Christopher Bülte, Yusuf Sale, Timo Löhr +3
Uncertainty quantification is crucial in machine learning, yet most (axiomatic) studies of uncertainty measures focus on classification, leaving a gap in regression settings with l…
Probabilistic neural operators for functional uncertainty quantification
Christopher Bülte, Philipp Scholl, Gitta Kutyniok
Neural operators aim to approximate the solution operator of a system of differential equations purely from data. They have shown immense success in modeling complex dynamical syst…
Sustainable AI: Mathematical Foundations of Spiking Neural Networks
Adalbert Fono, Manjot Singh, Ernesto Araya +3
Deep learning's success comes with growing energy demands, raising concerns about the long-term sustainability of the field. Spiking neural networks, inspired by biological neurons…