Xinpeng Wang

Xinpeng Wang

A third-year Ph.D. student at Tongji University.

Xinpeng Wang 王新鹏

I am now a third-year Ph.D. student in the Intelligent Information Processing Lab, Department of Computer Science and Technology, Tongji University, Shanghai, China.

My research interests include Natural Language Generation and Multimodal Generation.

I have interned at Microsoft Research Asia, advised by Dr. Xiaoyuan Yi.

Main Publications

* indicates equal contribution

  1. Xuan Gong, Tianshi Ming, Xinpeng Wang, Zhihua Wei. DAMRO: Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination. EMNLP 2024 Main Conference (Oral). [pdf]
  2. Xinpeng Wang*, Shitong Duan*, Xiaoyuan Yi, Jing Yao, Shanlin Zhou, Zhihua Wei, Peng Zhang, Dongkuan Xu, Maosong Sun, Xing Xie. On the Essence and Prospect: An Investigation of Alignment Approaches for Big Models. IJCAI 2024. [pdf]
  3. Xinpeng Wang, Xiaoyuan Yi, Han Jiang, Shanlin Zhou, Zhihua Wei, Xing Xie. ToViLaG: Your Visual-Language Generative Model is Also An Evildoer. EMNLP 2023 Main Conference (Oral). [pdf], [code]
  4. Xinpeng Wang, Han Jiang, Zhihua Wei, Shanlin Zhou. CHAE: Fine-Grained Controllable Story Generation with Characters, Actions and Emotions. COLING 2022. [pdf], [code]
  5. Feifei Xu*, Shanlin Zhou*, Xinpeng Wang*, Yunpu Ma, Wenkai Zhang, Zhisong Li. Open-domain Dialogue Generation Grounded with Dynamic Multi-form Knowledge Fusion. DASFAA 2022 (Best Paper). [pdf], [code]
  6. Feifei Xu, Xinpeng Wang, Yunpu Ma, Volker Tresp, Yuyi Wang, Shanlin Zhou, Haizhou Du. Controllable Multi-Character Psychology-Oriented Story Generation. CIKM 2020 (Supervisor No.1, Student No.2). [pdf], [code]