100 citations · 135 across the 24 of their papers we have counts for
25 papers
RoleQ: Role-Aligned Scales for Converting Language Models to Ternary
Johannes Knittel, Alec Helbling, Hanspeter Pfister
Weight quantization below four bits shrinks memory and bandwidth at a perplexity that looks acceptable, but often at the cost of factual knowledge and task accuracy. Ternary weight…
ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity
Haoran Wang, Matthew Lau, Alec Helbling +7
Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches that cause them to miss objects…
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Mansi Phute, Alexander Greenhalgh, Matthew Hull +8
Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and…
Flow Reasoning Models: Turning Flows Into Efficient Recurrent Reasoners
Alec Helbling, Andrey Bryutkin, Mauro Martino +3
Structured reasoning requires making and revising interdependent decisions to reach a globally consistent solution. Existing architectures struggle with this: autoregressive models…
What Time Is It? How Data Geometry Makes Time Conditioning Optional for Flow Matching
Alec Helbling, Sebastian Gutierrez Hernandez, Benjamin Hoover +2
Recent work has shown that models flow matching models can be trained without explicit time conditioning, challenging the standard view that the interpolation time is needed to dis…
Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI
Lama Moukheiber, Caleb M. Yeung, Haotian Xue +3
Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial e…
LORE: Jointly Learning the Intrinsic Dimensionality and Relative Similarity Structure From Ordinal Data
Vivek Anand, Alec Helbling, Mark A. Davenport +3
Learning the intrinsic dimensionality of subjective perceptual spaces such as taste, smell, or aesthetics from ordinal data is a challenging problem. We introduce LORE (Low Rank Or…
SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation
Alec Helbling, Shruti Palaskar, Kundan Krishna +3
What exactly makes a particular image unsafe? Systematically differentiating between benign and problematic images is a challenging problem, as subtle changes to an image, such as…
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Mansi Phute, Matthew Hull, Haoran Wang +6
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions.…
Diffusion Explorer: Interactive Exploration of Diffusion Models
Alec Helbling, Duen Horng Chau
Diffusion models have been central to the development of recent image, video, and even text generation systems. They posses striking geometric properties that can be faithfully por…
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
Alec Helbling, Tuna Han Salih Meral, Ben Hoover +2
Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel metho…
RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering
Matthew Hull, Haoran Wang, Matthew Lau +8
Differentiable rendering techniques like Gaussian Splatting and Neural Radiance Fields have become powerful tools for generating high-fidelity models of 3D objects and scenes. Thei…
Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation
Aeree Cho, Grace C. Kim, Alexander Karpekov +6
The Transformer architecture underpins modern large language models powering state-of-the-art text generation and AI applications. However, its complexity makes it difficult for no…
Non-Robust Features are Not Always Useful in One-Class Classification
Matthew Lau, Haoran Wang, Alec Helbling +5
The robustness of machine learning models has been questioned by the existence of adversarial examples. We examine the threat of adversarial examples in practical applications that…
ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing
Alec Helbling, Seongmin Lee, Polo Chau
Recently, researchers have proposed powerful systems for generating and manipulating images using natural language instructions. However, it is difficult to precisely specify many…
LLM Attributor: Interactive Visual Attribution for LLM Generation
Seongmin Lee, Zijie J. Wang, Aishwarya Chakravarthy +5
While large language models (LLMs) have shown remarkable capability to generate convincing text across diverse domains, concerns around its potential risks have highlighted the imp…
Point and Instruct: Enabling Precise Image Editing by Unifying Direct Manipulation and Text Instructions
Alec Helbling, Seongmin Lee, Polo Chau
Machine learning has enabled the development of powerful systems capable of editing images from natural language instructions. However, in many common scenarios it is difficult for…
Mobile Fitting Room: On-device Virtual Try-on via Diffusion Models
Justin Blalock, David Munechika, Harsha Karanth +4
The growing digital landscape of fashion e-commerce calls for interactive and user-friendly interfaces for virtually trying on clothes. Traditional try-on methods grapple with chal…
ObjectComposer: Consistent Generation of Multiple Objects Without Fine-tuning
Alec Helbling, Evan Montoya, Duen Horng Chau
Recent text-to-image generative models can generate high-fidelity images from text prompts. However, these models struggle to consistently generate the same objects in different co…
LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked
Mansi Phute, Alec Helbling, Matthew Hull +4
Large language models (LLMs) are popular for high-quality text generation but can produce harmful content, even when aligned with human values through reinforcement learning. Adver…
Manifold Contrastive Learning with Variational Lie Group Operators
Kion Fallah, Alec Helbling, Kyle A. Johnsen +1
Self-supervised learning of deep neural networks has become a prevalent paradigm for learning representations that transfer to a variety of downstream tasks. Similar to proposed mo…
ManimML: Communicating Machine Learning Architectures with Animation
Alec Helbling, Duen Horng Chau
There has been an explosion in interest in machine learning (ML) in recent years due to its applications to science and engineering. However, as ML techniques have advanced, tools…
PrefGen: Preference Guided Image Generation with Relative Attributes
Alec Helbling, Christopher J. Rozell, Matthew O'Shaughnessy +1
Deep generative models have the capacity to render high fidelity images of content like human faces. Recently, there has been substantial progress in conditionally generating image…
Oracle Guided Image Synthesis with Relative Queries
Alec Helbling, Christopher John Rozell, Matthew O'Shaughnessy +1
Isolating and controlling specific features in the outputs of generative models in a user-friendly way is a difficult and open-ended problem. We develop techniques that allow an or…