48 citations · 82 across the 26 of their papers we have counts for
28 papers
Learning PDE Dynamics between Submanifolds Using Green's Observation Operators
Jan Tauberschmidt, Jephte Abijuru, Samuel Okon +5
Many physical systems are driven and observed only on lower-dimensional submanifolds of a larger spatial domain, while their dynamics are governed by the ambient medium occupying t…
Skipping the Zeros in Diffusion Models for Sparse Data Generation
Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy +6
Diffusion models (DMs) excel on dense continuous data, but are not designed for sparse continuous data. They do not model exact zeros that represent the deliberate absence of a sig…
Optimization Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise
Puyu Wang, Jan Schuchardt, Nikita Kalinin +5
The theoretical understanding of differentially private stochastic gradient descent (DP-SGD) with temporally correlated noise remains limited, particularly for non-convex neural ne…
Formally Exploring Time-Series Anomaly Detection Evaluation Metrics
Dennis Wagner, Arjun Nair, Billy Joe Franks +24
Undetected anomalies in time series can trigger catastrophic failures in safety-critical systems, such as chemical plant explosions or power grid outages. Although many detection m…
DiffStyleTS: Diffusion Model for Style Transfer in Time Series
Mayank Nagda, Phil Ostheimer, Justus Arweiler +13
Style transfer combines the content of one signal with the style of another. It supports applications such as data augmentation and scenario simulation, helping machine learning mo…
PIANO: Physics Informed Autoregressive Network
Mayank Nagda, Jephte Abijuru, Phil Ostheimer +2
Solving time-dependent partial differential equations (PDEs) is fundamental to modeling critical phenomena across science and engineering. Physics-Informed Neural Networks (PINNs)…
Continual Neural Topic Model
Charu Karakkaparambil James, Waleed Mustafa, Marius Kloft +1
In continual learning, our aim is to learn a new task without forgetting what was learned previously. In topic models, this translates to learning new topic models without forgetti…
Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
Jan Tauberschmidt, Sophie Fellenz, Sebastian J. Vollmer +1
We present a framework for fine-tuning flow-matching generative models to enforce physical constraints and solve inverse problems in scientific systems. Starting from a model train…
Superstudent intelligence in thermodynamics
Rebecca Loubet, Pascal Zittlau, Marco Hoffmann +6
In this short note, we report and analyze a striking event: OpenAI's large language model o3 has outwitted all students in a university exam on thermodynamics. The thermodynamics e…
Multi-level Supervised Contrastive Learning
Naghmeh Ghanooni, Barbod Pajoum, Harshit Rawal +3
Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances an…
Sparse Data Diffusion for Scientific Simulations in Biology and Physics
Phil Ostheimer, Mayank Nagda, Andriy Balinskyy +5
Sparse data is fundamental to scientific simulations in biology and physics, from single-cell gene expression to particle calorimetry, where exact zeros encode physical absence rat…
Using Large Language Models for Solving Thermodynamic Problems
Rebecca Loubet, Pascal Zittlau, Luisa Vollmer +5
Large Language Models (LLMs) have made significant progress in reasoning, demonstrating their capability to generate human-like responses. This study analyzes the problem-solving c…
BBPOS: BERT-based Part-of-Speech Tagging for Uzbek
Latofat Bobojonova, Arofat Akhundjanova, Phil Ostheimer +1
This paper advances NLP research for the low-resource Uzbek language by evaluating two previously untested monolingual Uzbek BERT models on the part-of-speech (POS) tagging task an…
Challenging Assumptions in Learning Generic Text Style Embeddings
Phil Ostheimer, Marius Kloft, Sophie Fellenz
Recent advancements in language representation learning primarily emphasize language modeling for deriving meaningful representations, often neglecting style-specific consideration…
Towards Graph Foundation Models: A Study on the Generalization of Positional and Structural Encodings
Billy Joe Franks, Moshe Eliasof, Semih Cantürk +4
Recent advances in integrating positional and structural encodings (PSEs) into graph neural networks (GNNs) have significantly enhanced their performance across various graph learn…
Tethering Broken Themes: Aligning Neural Topic Models with Labels and Authors
Mayank Nagda, Phil Ostheimer, Sophie Fellenz
Topic models are a popular approach for extracting semantic information from large document collections. However, recent studies suggest that the topics generated by these models o…
SetPINNs: Set-based Physics-informed Neural Networks
Mayank Nagda, Phil Ostheimer, Thomas Specht +5
Physics-Informed Neural Networks (PINNs) solve partial differential equations using deep learning. However, conventional PINNs perform pointwise predictions that neglect dependenci…
Comgra: A Tool for Analyzing and Debugging Neural Networks
Florian Dietz, Sophie Fellenz, Dietrich Klakow +1
Neural Networks are notoriously difficult to inspect. We introduce comgra, an open source python library for use with PyTorch. Comgra extracts data about the internal activations o…
HANNA: Hard-constraint Neural Network for Consistent Activity Coefficient Prediction
Thomas Specht, Mayank Nagda, Sophie Fellenz +3
We present the first hard-constraint neural network for predicting activity coefficients (HANNA), a thermodynamic mixture property that is the basis for many applications in scienc…
KnowTD-An Actionable Knowledge Representation System for Thermodynamics
Luisa Vollmer, Sophie Fellenz, Fabian Jirasek +2
We demonstrate that thermodynamic knowledge acquired by humans can be transferred to computers so that the machine can use it to solve thermodynamic problems and produce explainabl…
On the Challenges and Opportunities in Generative AI
Laura Manduchi, Clara Meister, Kushagra Pandey +23
The field of deep generative modeling has grown rapidly in the last few years. With the availability of massive amounts of training data coupled with advances in scalable unsupervi…
Reimagining Anomalies: What If Anomalies Were Normal?
Philipp Liznerski, Saurabh Varshneya, Ece Calikus +5
Deep learning-based methods have achieved a breakthrough in image anomaly detection, but their complexity introduces a considerable challenge to understanding why an instance is pr…
Text Style Transfer Evaluation Using Large Language Models
Phil Ostheimer, Mayank Nagda, Marius Kloft +1
Evaluating Text Style Transfer (TST) is a complex task due to its multifaceted nature. The quality of the generated text is measured based on challenging factors, such as style tra…
Evaluating Dynamic Topic Models
Charu James, Mayank Nagda, Nooshin Haji Ghassemi +2
There is a lack of quantitative measures to evaluate the progression of topics through time in dynamic topic models (DTMs). Filling this gap, we propose a novel evaluation measure…