2 citations · 2 across the 8 of their papers we have counts for
10 papers
What Would Removing This Corruption Change? Failure Attribution for Vision-Language-Action Models
Carson Sobolewski, Anjali Parashar, Fei Chen +2
Vision-language-action (VLA) models are sensitive to visual corruptions, but knowing that a corruption is typically harmful does not establish whether removing it would benefit the…
Careful Judge: Safe and Efficient Human-AI Collaborative Decision Making
Chenyu Zhang, Rachel Luo, Boyi Li +3
In human-AI collaborative decision making, human review can prevent unsafe AI decisions, but each human judgment is costly. Treating human intervention after AI abstention as a one…
Coverage Aware Active Evaluation for Failure Discovery with Paired Systems
Anjali Parashar, Rachel Luo, Apoorva Sharma +6
Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets. Although cheaper proxies such as simulators…
Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records
Anjali Parashar, Chuchu Fan
To ensure safe on-road behavior, pre-deployment testing and failure discovery of Autonomous Driving Systems (ADS) is crucial. Present day simulation based testing methods focus lar…
SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing
Anjali Parashar, Yingke Li, Eric Yang Yu +4
As autonomous systems such as drones, become increasingly deployed in high-stakes, human-centric domains, it is critical to evaluate the ethical alignment since failure to do so im…
Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference
Yingke Li, Anjali Parashar, Enlu Zhou +1
Active inference (AIF) unifies exploration and exploitation by minimizing the Expected Free Energy (EFE), balancing epistemic value (information gain) and pragmatic value (task per…
Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference
Yingke Li, Anjali Parashar, Enlu Zhou +1
Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task performance and reduce uncertainty. Ba…
Failure Prediction from Limited Hardware Demonstrations
Anjali Parashar, Kunal Garg, Joseph Zhang +1
Prediction of failures in real-world robotic systems either requires accurate model information or extensive testing. Partial knowledge of the system model makes simulation-based f…
Fast and Modular Autonomy Software for Autonomous Racing Vehicles
Andrew Saba, Aderotimi Adetunji, Adam Johnson +27
Autonomous motorsports aim to replicate the human racecar driver with software and sensors. As in traditional motorsports, Autonomous Racing Vehicles (ARVs) are pushed to their han…
RADIUM: Predicting and Repairing End-to-End Robot Failures using Gradient-Accelerated Sampling
Charles Dawson, Anjali Parashar, Chuchu Fan
Before autonomous systems can be deployed in safety-critical applications, we must be able to understand and verify the safety of these systems. For cases where the risk or cost of…