2 papers
cs.CV2026
EgoSafetyBench: A Diagnostic Egocentric Video Benchmark for Evaluating Embodied VLMs as Runtime Safety Guards
Siddhant Panpatil, Arth Singh, Mijin Koo +3
Vision-language models (VLMs) are now proposed as runtime safety guards for embodied agents in homes and factories. A deployable guard must catch genuinely unsafe situations while…
cs.CL2025
Eliciting and Analyzing Emergent Misalignment in State-of-the-Art Large Language Models
Siddhant Panpatil, Hiskias Dingeto, Haon Park
Despite significant advances in alignment techniques, we demonstrate that state-of-the-art language models remain vulnerable to carefully crafted conversational scenarios that can…