Xinke Kong 孔信轲

I am currently an undergraduate student at Tianjin University, majoring in Computer Science and Technology. I am conducting research in the field of deep learning. I will be receiving my Bachelor's degree in the summer of 2025 from the School of Computer Science and Technology at Tianjin University.

Afterward, I will pursue my Master's degree at Tianjin University, supervised by Prof. Changqing Zhang, starting in the fall of 2025. I am looking forward to further developing my knowledge and research in deep learning during my graduate studies.

Email  /  Google Scholar  /  Github

profile photo
News

[2025-01] One paper accepted by ICLR, thanks to all co-authors!


Publications(* equal contribution)
clean-usnob COME: Test-time Adaption by Conservatively Minimizing Entropy

Qingyang Zhang, Yatao Bian, Xinke Kong, Peilin Zhao and Changqing Zhang
ICLR, 2025
arXiv / code

COME naturally regularizes the TTA model to favor conservative confidence on unreliable samples.

Awards

National Scholarship (1%) 2022



Updated at Jan. 2025
Thanks Jon Barron for this amazing template.