Yan Huang

The paper introduces Metric-Normalized Posterior Leakage (mPL), an attacker-aligned measure that provides a practical, certifiable privacy guarantee for machine learning systems consumed under joint observation, addressing shortcomings of traditional differential privacy.

The paper proposes Context-aware Metric Differential Privacy (C-mDP), a framework that improves vehicle location privacy by modeling temporal dependencies, achieving higher data utility than standard methods.

The paper introduces MTAVG-Bench 2.0, a new benchmark designed to diagnose high-level failure modes of cinematic expressiveness in multi-talker audio-video generation, showing that even advanced models struggle with complex scene-level failures.

The paper establishes conditions for QUBO formulations of combinatorial optimization problems that guarantee valid binary and feasible local minimizers using gradient-based methods.

This paper proposes RAPS-DA, a framework that addresses conflicts in retrieval-augmented generation using a regime-aware peer specialization system and a dual-layer selector.

This paper proposes Joint Speech-Text Interleaved Pretraining (JSTIP) for speech recognition, which constructs interleaved speech-text sequences and achieves consistent entity accuracy improvement.