Alec Helbling

I am an ML PhD student at Georgia Tech's College of Computing, working with Polo Chau and supported by the National Science Foundation Graduate Research Fellowship.

My work centers on methods for guiding generative models, particularly ones for image generation. I am broadly interested also in the application of data visualization and HCI to understanding and guiding machine learning systems.

I previously worked with Chris Rozell at Georgia Tech on methods for guiding generative models based on human feedback. I have also interned at Adobe on the Firefly team under Oliver Brdiczka . Prior to that I interned at IBM Research with Achille Fokue where my work focused on applying graph neural networks at large scale language models to the task of document summarization. Prior to that I was a software engineering intern at Microsoft where I worked on scaling a data analytics service. I also was an intern in the Machine Learning and Instrument Autonomy Group at NASA Jet Propulsion Laboratory with Lukas Mandrake. At NASA my work focused on developing web-based visualization tools for interacting with machine learning models. I started my research career working with David Koes at the University of Pittsburgh. There I worked on machine learning applications to computational drug discovery, specifically trying to understand protein-ligand interactions. I also worked on a web-based molecular visualization library called 3Dmol.js.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo
Research

I am interested in machine learning and software engineering. I am specifically interested in generative modeling, multimodal modeling, and visualization.

Transformer Explainer: Interactive Learning of Text-Generative Models
Aeree Cho (*), Grace C Kim (*), Alexander Karpekov (*), Alec Helbling, Zijie J Wang, Seongmin Lee, Benjamin Hoover, Duen Horng Chau
IEEE VIS: Visualization & Visual Analytics, 2024
Github (Currently ⭐)
Arxiv

We developed an interactive tool for explaining the transformer architecture.

Non-Robust Features are Not Always Useful in One-Class Classification
Matthew Lau, Haoran Wang, Alec Helbling, Matthew Hull, ShengYun Peng, Martin Andreoni, Willian T. Lunardi, Wenke Lee
CVPR, Workshop on Visual Anomaly and Novelty Detection, 2024
Arxiv

Analysis of the adversarial robustness of one-class classifiers for anomoly detection.

ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing
Alec Helbling, Seongmin Lee, Polo Chau
CVPR, Workshop on AI for Content Creation, 2024
Arxiv

ClickDiffusion is an approach to image editing that aggregates a combination of mouse feedback and text instructions.

LLM Attributor: Interactive Visual Attribution for LLM Generation
Seongmin Lee, Zijie J Wang, Aishwarya Chakravarthy, Alec Helbling, ShengYun Peng, Mansi Phute, Duen Horng Chau, Minsuk Kahng
IEEE VIS: Visualization and Visual Analytics, 2024
Arxiv

We developed a visual interface for attributing LLM generations to their sources.

Mobile Fitting Room: On-device Virtual Try-on via Diffusion Models
Justin Blalock, David Munechika, Harsha Karanth, Alec Helbling , Pratham Mehta, Seongmin Lee, Duen Horng Chau
CVPR 2024, Workshop on Virtual Try-on, 2023
Invited Talk!
Arxiv

We developed an on-device approach to virtual try-on using diffusion models.

ObjectComposer: Consistent Generation of Multiple Objects Without Fine-tuning
Alec Helbling, Evan Montoya, Duen Horng (Polo) Chau
Arxiv

We developed a technique for generating image compositions containing multiple concepts that are faithful to reference images.

LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
Alec Helbling, Mansi Phute, Matthew Hull, Duen Horng (Polo) Chau
Arxiv

We showed that it is possible to defend against adversarial attacks on language models, which encourage LLMs to produce harmful content, by simply filtering out this content using another instance of an LLM.

ManimML: Communicating Machine Learning Architectures with Animation
Alec Helbling, Duen Horng (Polo) Chau
IEEE VIS: Visualization and Visual Analytics, 2023
🏆 Won Best Poster Award!
Arxiv
Github (Currently ⭐)

We developed ManimML, an open-source Python library for easily generating animations of ML algorithms directly from code. ManimML has a familiar syntax for specifying neural networks that mimics popular deep learning frameworks like Pytorch. A user can take a preexisting neural network architecture and easily write a specification for an animation in ManimML, which will then automatically compose animations for different components of the system into a final animation of the entire neural network.

Manifold Contrastive Learning with Variational Lie Group Operators
Kion Fallah, Alec Helbling, Kyle A. Johnsen, Christopher John Rozell
Preprint 2023
Arxiv

We developed a self-supervised learning approach derived from Lie algebra to apply automatic data augmentations to image data that stay on low-dimensional manifolds in high-dimensional latent representations.

PrefGen: Preference Guided Image Generation with Relative Attributes
Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy, Kion Fallah
Preprint 2023
Arxiv

We developed a method for controlling the features of images generating with a GAN by asking user's relative queries of of the form "do you prefer image a or image b?" From these queries we could infer what images a user prefers and use that understanding of user preferences to generate reccomendation images.

Oracle Guided Image Synthesis with Relative Queries
Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy, Kion Fallah
International Conference on Learning Representations
Workshop on Deep Generative Models for Highly Structured Data, 2022
OpenReview

We developed a method for guiding the generative process of VAEs by asking user's relative queries of of the form "do you prefer image a or image b?" From these queries we could infer what images a user prefers and use that understanding of user preferences to generate reccomendation images with our VAE.

Visualizing Convolutional Neural Network Protein-Ligand Scoring
Joshua Hochuli, Alec Helbling, Tamar Skaist, Matthew Ragoza, David Ryan Koes
Journal of Molecular Graphics and Modeling, 2018
arXiv

We applied convolutional neural networks to the problem of predicting whether or not a protein-ligan pair are likely to bind. We developed methods of visualizing and understanding the learned structure of these models.

Projects
3Dmol.js
Github (Currently ⭐)

I made significant contributions to 3Dmol.js while working with David Koes at the University of Pittsburgh Department of Computational and Systems Biology. 3Dmol.js is a JavaScript tool allowing biologists to easily visualize 3D molecular structures like proteins.


This website uses a template from https://jonbarron.info/