2 papers
cs.LG2026
STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations
Rishit Dagli, Abir Harrasse, Luke Zhang +4
Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observing how a model chan…
cs.RO2026
Adversarial Stress Testing of SPARK Humanoid Safety Filters
Saurav Ghosh, Abdou Sow, Luke Zhang
Humanoid robots are difficult to deploy safely because they have high-dimensional bodies, many collision constraints, and must operate near people and obstacles. Safety filters hel…