Alex Bäuerle

Supervised by Timo Ropinski, funded by the Carl-Zeiss-Scholarship

Grade: 1.1, supervised by Timo Ropinski

Grade: 1.2, supervised by Marc Schickler and Manfred Reichert

What is the right interface between humans and AI?

Building an awesome product for Humans + AI + Biology to solve drug toxicity.

Research and development of tools in the areas of AI evaluation and prompt engineering.

Bringing data and analysts closer together with the help of visualization and AI.

Designed and developed a framework for component-based ML interfaces which can be composed in different environments such as computational notebooks and web dashboards.

Designed and implemented a visualization approach for a novel bias detection algorithm. This visualization is designed to support large label spaces and multilabel classification problems.

Invented and experimented with a technique similar to Feature Visualization, but for language models.

Cell Painting for cytotoxicity and mode-of-action analysis in primary human hepatocytes

Jessica D Ewald,  Katherine L Titterton,  Alex Bäuerle,  Alex Beatson,  Daniil A Boiko,  Ángel A Cabrera,  Jaime Cheah,  Beth A Cimini,  Bram L Gorissen,  Joshua Harrill,  Thouis R Jones,  Konrad J Karczewski,  Christine E Crute,  David Rouquie,  Srijit Seal,  Erin Weisbart,  Brandon White,  Anne E Carpenter, and  Shantanu Singh

Your other Left! Vision-Language Models Fail to Identify Relative Positions in Medical Images

Daniel Wolf,  Heiko Hillenhagen,  Billurvan Taskin,  Alex Bäuerle,  Meinrad Beer,  Michael Götz, and  Timo Ropinski

A Survey on Quality Metrics for Text-to-Image Generation

Sebastian Hartwig,  Dominik Engel,  Leon Sick,  Hannah Kniesel,  Tristan Payer,  Poonam Poonam,  Michael Glöckner,  Alex Bäuerle, and  Timo Ropinski

Humboldt: Metadata-Driven Extensible Data Discovery

Alex Bäuerle,  Çağatay Demiralp, and  Michael Stonebraker

mint: Integrating scientific visualizations into virtual reality

Sergej Geringer,  Florian Geiselhart,  Alex Bäuerle,  Dominik Dec,  Olivia Odenthal,  Guido Reina,  Timo Ropinski, and  Daniel Weiskopf

An In-depth Look at Gemini’s Language Abilities

Syeda Nahida Akter,  Zichun Yu,  Aashiq Muhamed,  Tianyue Ou,  Alex Bäuerle,  Ángel Alexander Cabrera,  Krish Dholakia,  Chenyan Xiong, and  Graham Neubig

VegaProf: Profiling Vega Visualizations

Junran Yang,  Alex Bäuerle,  Dominik Moritz, and  Çağatay Demiralp

Semantic Hierarchical Exploration of Large Image Datasets

Alex Bäuerle,  Christian van Onzenoodt,  Daniel Jönsson, and  Timo Ropinski

Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts

Alex Bäuerle,  Daniel Jönsson, and  Timo Ropinski

Symphony: Composing Interactive Interfaces for Machine Learning

Alex Bäuerle,  Ángel Alexander Cabrera,  Fred Hohman,  Megan Maher,  David Koski,  Xavier Suau,  Titus Barik, and  Dominik Moritz

Where did my Lines go? Visualizing Missing Data in Parallel Coordinates

Alex Bäuerle,  Christian van Onzenoodt,  Simon der Kinderen,  Jimmy Johansson Westberg,  Daniel Jönsson, and  Timo Ropinski

exploRNN: Understanding Recurrent Neural Networks through Visual Exploration

Alex Bäuerle,  Patrick Albus,  Raphael Störk,  Tina Seufert, and  Timo Ropinski

Visual Identification of Problematic Bias in Large Label Spaces

Alex Bäuerle,  Aybuke Gul Turker,  Ken Burke,  Osman Aka,  Timo Ropinski,  Christina Greer, and  Mani Varadarajan

Net2Vis - A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations

Alex Bäuerle,  Christian van Onzenoodt, and  Timo Ropinski

Measuring Model Biases in the Absence of Ground Truth

Osman Aka,  Ken Burke,  Alex Bäuerle,  Christina Greer, and  Margaret Mitchell

What does BERT dream of?

Alex Bäuerle, and  James Wexler

Classifier-Guided Visual Correction of Noisy Labels for Image Classification Tasks

Alex Bäuerle,  Heiko Neumann, and  Timo Ropinski

Automatic identification of crossovers in cryo‐EM images of murine amyloid protein A fibrils with machine learning

Mattthias Weber,  Alex Bäuerle,  Matthias Schmidt,  Matthias Neumann,  Marcus Fähndrich,  Timo Ropinski, and  Volker Schmidt

Convolutional neural network (CNN) applied to respiratory motion detection in fluoroscopic frames

Christoph Baldauf,  Alex Bäuerle,  Timo Ropinski,  Volker Rasche, and  Ina Vernikouskaya

Created and regularly held one chapter on visualization for AI at Ulm University. Talk about different explainability techniques and visualization concepts that help investigate and communicate about AI systems.

Supervise undergrad and grad students in regular projects. We go through the process of ideation, implementation, and writing about these projects.

Held regular seminars for both undergrad and grad students.

Research Intern, Sigma Computing

VegaProf: Profiling Vega Visualizations

Bachelor Thesis, Ulm University

Creating an Interactive UI for Human/AI Collaboration in Poster Design Processes

Master Thesis, Ulm University

Visualizing Missing Data in Parallel Coordinates

Bachelor Thesis, Ulm University

Generating Synthesizer Presets from Audio with a Neural Network

Bachelor Thesis, Ulm University

Visualizing Deep Reinforcement Learning

Bachelor Thesis, Ulm University

leaRNN: Eine Interaktive Visualisieurng rekurrenter neuronaler Netze

Master Thesis, Ulm University

Convolutional Neural Networks (CNN) Applied to Respiratory Motion Detection in Fluoroscopic Frames

Carl-Zeiss Scholarship for PhD Students

German Stipend for Excellent Students