Pei Li

The paper proposes a novel, locally deployable agentic workflow using large language models (LLMs) to accurately and privately detect various types of personally identifiable information (PII) within unstructured crash narratives.

This paper introduces a novel framework for differentially private sampling by using the Wasserstein distance as the utility measure, proposing the Wasserstein Projection Mechanism (WPM) to address limitations of density ratio-based methods.

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic tasks and embodiments.

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.