Jie Deng

The paper introduces ProductWebGen, a benchmark for evaluating multimodal models' ability to generate consistent, high-fidelity product webpages from images and instructions, finding that separate editing-based workflows outperform unified models in overall webpage instruction following.

This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (MultiTF). MBD-LMs improve inter-block parallelism and wall-clock acceleration.

This paper introduces IR275K, a curated benchmark for multi-frame super-resolution in infrared remote sensing, and evaluates CGMamba, a lightweight state-space model, achieving state-of-the-art performance.