Zhihan Zhang

OpenRTAG reveals that traditional GNNs struggle significantly more than LLM-GNNs under realistic data quality degradation, highlighting critical vulnerabilities in graph learning models.

LLMs can autonomously optimize AI models for embedded devices, achieving 250x compression with minimal accuracy loss—something human experts struggle to match.

Training a foundation model on a trillion minutes of wearable sensor data unlocks surprisingly accurate predictions across a wide range of health conditions, even with limited labeled data.

Training on semantically equivalent chart renderings in Python, R, and LaTeX unlocks surprisingly effective multi-lingual chart-to-code generation from a single model.