Yang Xiang

The paper introduces MEntA, a highly query-efficient and surrogate-free membership inference attack that uses natural-language entailment to detect if a specific document was used by a RAG system, achieving high accuracy with only five queries.

The paper proposes ESRT, an edge-cloud framework that achieves state-of-the-art, bandwidth-efficient, and privacy-preserving many-to-many speech translation across 45 languages by splitting the model inference.

This paper investigates safety dynamics in the use of Role-play AI Companions through interviews and a 14-day assessment, identifying key factors shaping these dynamics and revealing short-term emotional relief masking longer-term deterioration.