Minghao Li

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 introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that current state-of-the-art models fail on complex, domain-specific structures.

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.