Publications

* indicates co-first authors.

Wenjie Shu (2025). CoRe-GRPO: Consensus-driven and Region-focused RL for Human-Centric Generation in Lightweight Diffusion Models. Under review.
Wenjie Shu (2025). Temporal Regularization Makes Your Video Generator Stronger. Preprint.
Preprint PDF
Wenjie Shu (2025). LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization. Preprint.
Preprint PDF
Wenjie Shu (2024). VideoGen-of-Thought: Step-by-step Generating Multi-shot Video with Minimal Manual Intervention. NIPSW 2026 (Workshop).
Preprint PDF
Wenjie Shu, Hong-Xia Dou, Rui Wen, Xiao Wu, Liang-Jian Deng (2024). CMT: Cross Modulation Transformer with Hybrid Loss for Pansharpening. IEEE GRSL 2024.
Source Document
Haoyu Deng, Zijing Xu, Yule Duan, Xiao Wu, Wenjie Shu, Liang-Jian Deng (2024). Exploring the Low-Pass Filtering Behavior in Image Super-Resolution. ICML 2024.
Preprint PDF PDF Preprint
Wenjie Shu (2024). DDA: A Dual-Domain Attention Plug-and-Play Prior for Pansharpening. ICLR Tiny 2024.
PDF Source Document