15 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…
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP's kNN Graph
Duen Horng Chau, Donghao Ren, Fred Hohman +1
While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) gra…
UNIPO: Unified Interactive Visual Explanation for RL Fine-Tuning Policy Optimization
Aeree Cho, Alexander D. Greenhalgh, Jonathan Bodea +2
Reinforcement learning has emerged as a dominant technique for fine-tuning the behavior of large language models, with policy optimization (PO) algorithms such as GRPO, DAPO, and D…
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.…
QueryWeaver: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation
Aishwarya Chakravarthy, Vidhi Kulkarni, Duen Horng Chau
Many real-world queries over personal data span multiple applications and require structured planning, as individual tools expose only partial information. While LLMs show strong r…
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…