3 papers
cs.CL2026
GRASP: Reinforcing Language Model Anonymizers with Group Relative Policy Optimization
Sajjad Ghiasvand, Nader Sehatbakhsh
Large language models can infer sensitive personal attributes, such as age, location, and occupation, from ordinary text, turning everyday writing into a privacy risk. Adversarial…
cs.RO2026
Your Model Already Knows: Attention-Guided Safety Filter for Vision-Language-Action Models
Seongbin Park, Fan Zhang, Baharan Mirzasoleiman +2
Vision-Language-Action (VLA) models have demonstrated impressive end-to-end performance across a variety of robotic manipulation tasks. However, these policies offer no guarantees…
cs.RO2026
ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models
Fan Zhang, Seongbin Park, Baharan Mirzasoleiman +2
Vision-Language-Action (VLA) models demonstrate strong perfor-1 mance on language-conditioned robotic manipulation within their training dis-2 tribution, yet their generalization c…