Publications

* indicates co-first authors.

Wenjie Shu^*, Xianghong Fang^*, Dehan Kong, Tim G. J. Rudner (2026). Latent Prior GANs: Efficient Decoder Refinement via Inherited Generative Structure. Under Review.

Wenjie Shu^*, Yexin Liu^*, Harold Haodong Chen, Xuerui Qiu, Zehan Wang, Yidi Zhang, Yizhan Chen, Zunwei Wang, Minghao Liu, Qi Chen, Harry Yang, Xiaogang Xu (2026). SolveEdit: Benchmarking Visual Problem Solving in Generative Models. Under Review.

Harold Haodong Chen^*, Rongjin Guo^*, Disen Lan^*, Wenjie Shu^*, Hongfei Zhang^*, and 18 other authors (2026). The Past Frames the Future: Memory for Autoregressive Video Generation. Under Review.

Xianghong Fang^*, Wenjie Shu^*, Tongda Xu, Wenlong Mou, Dehan Kong, Tim G. J. Rudner (2026). A Latent Distribution Perspective on Evaluating and Improving Latent Generative Models. Under Review.

Harold Haodong Chen^*, Wenjie Shu^*, Disen Lan^*, Qingyang Liu, Zihan Wang, and 12 other authors (2026). ThinkVid: Benchmarking Visual Reasoning in Video Generative Models. CVPR 2026.

Harold Haodong Chen^*, Xinxiang Yin^*, Wenjie Shu, Hongfei Zhang, Zixin Zhang, Chenfei Liao, Litao Guo, Qifeng Chen, Ying-Cong Chen (2026). Show, Don't Tell: Morphing Latent Reasoning into Image Generation. ICML 2026.

Harold Haodong Chen^*, Xianfeng Wu^*, Wenjie Shu, Rongjin Guo, Disen Lan, Harry Yang, Ying-Cong Chen (2026). ScalingAR: Scaling Confidence for Autoregressive Image Generation. ICML 2026.

Wenjie Shu, Xuerui Qiu, Rui-Jie Zhu, Harold Haodong Chen, Yexin Liu, Harry Yang (2026). LoopViT: Scaling Visual ARC with Looped Transformers. EMNLP 2026 Findings.

Yexin Liu, Wenjie Shu, Zile Huang, Haoze Zheng, Yueze Wang, Jingjin Zhu, Manyuan Zhang, Ser-Nam Lim, Harry Yang (2026). AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation. ICML 2026.

Wenjie Shu (2025). Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward. Under review.