Yang Gao

The paper proposes Look One Step Ahead (LOSA), a novel framework that enables efficient, privacy-preserving, and robust service provisioning in dynamic air-ground integrated networks by decoupling planning into a look-ahead phase and a real-time execution phase.

The paper challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits this region.

The paper introduces MIRA, a bilingual benchmark that reveals that LLMs tend to dilute or omit critical medical information when responding to prompts from users with low health literacy, a pattern termed Differential Information Dilution (DID).

MyoSem introduces an EMG-action semantic alignment framework that transforms low-level muscle signals into a shared semantic space, enabling bidirectional retrieval between EMG data and natural language action descriptions.

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

The paper proposes Progressive Loading-Aware Hierarchical Contrastive Learning (PL-HCL), a framework to detect misalignment between a skill's description and its true behavior in large language model agents, improving Macro-F1 from 0.45 to 0.87-0.89.