Xiaoyi Dong

HydroAgent achieves up to 84% correlation in flood predictions by embedding expert rules into LLM-driven workflows, transforming tacit knowledge into structured decision-making.

CapRL++ redefines caption quality through utility, enabling models to produce high-fidelity descriptions without the constraints of traditional supervised fine-tuning.

Ditch diffusion models: MeanFlow policies offer a faster, leaner path to high-performing reinforcement learning agents.

By mimicking how humans use visual anchors, ChartVSR lets models iteratively correct their own visual perception errors, leading to more accurate chart parsing.