10 papers
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…
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.…
Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement
Alec Helbling, Andrey Bryutkin, Mauro Martino +2
Discrete flow models have recently shown promising performance on few-step text generation; however, when naively applied to structured reasoning tasks such as Sudoku and Zebra puz…
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…