Binjie Wang

figure.png

I’m Binjie Wang, currently a senior undergraduate student at Fudan University. I major in computer science and I work on advancing Large Language Models and Vision–Language Models, with my past and current research interests centered on factuality, knowledge editing, test-time compute, and reinforcement learning.

I was fortunate to be advised by Prof. Pengfei Liu at the GAIR Lab, Shanghai Jiao Tong University (SJTU). I also spent a wonderful semester at Harvard University as a Visiting Undergraduate Student (VUS), where I interned with the Harvard Visual Computing Group (VCG) under Prof. Hanspeter Pfister. I am now working closely with Prof. Kianté Brantley, focusing on test-time compute and reinforcement learning.

selected publications

You can see my full publication list at Google Scholar.

  1. dualedit.png
    DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models
    Zhiyi Shi*, Binjie Wang*, Chongjie Si, and 3 more authors
    In Second Conference on Language Modeling(COLM), 2025
  2. haluj.png
    Halu-J: Critique-Based Hallucination Judge
    Binjie Wang, Steffi Chern, Ethan Chern, and 1 more author
    In AAAI 2025 Workshop on Preventing and Detecting LLM Misinformation (PDLM), 2025

selected projects