← Search

Chenkai Xu

2 accepted papers

2026

Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

ICLR 2026poster

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a single iteration. However, none of the existing open-source dLLMs have achieved superior inference speed over AR LLMs of…

Cited by 0SourcecodeScholar
2026

Domain-Informed Graph Neural Networks for Climate Factor Forecasting to Support Sustainable Crop Management

IJCAI 2026

Forecasting climate factors is critical for anticipating agro-climatic risks and enabling sustainable crop management. However, accurate prediction remains challenging due to complex spatiotemporal variability, heterogeneous seasonal patterns, and intricate interdependencies among climate variables.

Cited by 0Scholar