4 papers
Matched-Input Estimates Differ in Sign Across Architectures: Auditing EEG Foundation Models on Motor Imagery
Kevin Zhou, Sparsh Roy
Pretrained EEG foundation models are increasingly proposed as general-purpose encoders for brain-computer interfaces, yet recent benchmarks disagree about when their representation…
Belief-Space Perception Routing under Coupled Sensor Faults and Compute Contention
Sparsh Roy, Vihan Aggarwal, Davin Yin
A robot that has to see and react on a fixed clock runs into two problems at once. Its cameras degrade in rain, mud, fog, and darkness. And the single onboard processor it runs on…
KAISEN: Reproducible Subgroup Fairness Auditing for Clinical Risk Models
Sparsh Roy, Samuel Girmachew, Nishita Chavan
Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups. Audit pipelines have been proposed to…
When Do Learned Diffusion Proposals Help Constraint Solving? A Controlled Study on Continuous Algebraic Systems
Quang Bui, Sparsh Roy, Akash Gundimeda +1
Solving a continuous algebraic constraint system requires two decisions: which values satisfy the constraints, and which structural augmentation renders an unsolvable system solvab…