Selected Publications

V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation;
Cong Wang*, Kuan Tian*, Jun Zhang^✉, Yonghang Guan, Feng Luo, Fei Shen, Zhiwei Jiang^✉, Qing Gu, Xiao Han, Wei Yang;
arXiv:2406.02511.
[code] [project page] [arXiv] [models]

TL;DR: We propopse V-Express for talking-head generation, which adpots conditional dropout to balance the control strengths of mutimodal conditions.

Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization;
Cong Wang*, Zexuan Deng*, Zhiwei Jiang^✉, Yafeng Yin^✉, Fei Shen, Zifeng Cheng, Shiping Ge, Shiwei Gan, Qing Gu;
Annual Conference on Neural Information Processing Systems (NeurIPS), 2025.
[paper] [code] [model] [poster] [arXiv]

TL;DR: We propose SignViP for sign language video generation, which adopts discrete tokenization to integrate and represent multiple fine-grained conditions.

Ensembling Diffusion Models via Adaptive Feature Aggregation;
Cong Wang*, Kuan Tian*, Yonghang Guan, Fei Shen, Zhiwei Jiang^✉, Qing Gu, Jun Zhang^✉;
International Conference on Learning Representations (ICLR), 2025.
[paper] [code] [poster] [arXiv]

TL;DR: We propose AFA to ensemble multiple diffusion models based on different states like prompts, noises, timesteps, and spatial locations.

Aggregating Multiple Heuristic Signals as Supervision for Unsupervised Automated Essay Scoring;
Cong Wang, Zhiwei Jiang^✉, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu;
Annual Meeting of the Association for Computational Linguistics (ACL), 2023.
[paper] [code] [poster] [slides] [video]

TL;DR: We propose ULRA for unsupervised automated essay scoring, which aggregates multiple heuristic quality signals to construct robust training object.

Controlling Class Layout for Deep Ordinal Classification via Constrained Proxies Learning;
Cong Wang, Zhiwei Jiang^✉, Yafeng Yin, Zifeng Cheng, Shiping Ge, Qing Gu;
AAAI Conference on Artificial Intelligence (AAAI), 2023.
[paper] [code] [poster] [slides] [arXiv]

TL;DR: We propose CPL for ordinal classification, which learns proxies for ordinal classes and adjusts their layout to capture ordinal relationships.