Zhunxuan Wang

maths, video games, motion pictures and sounds.

exp

BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token Aggregation. Yingxiang Yang, Weihang Xiao, Zhunxuan Wang, and Niresh Agarwal. ER@COLM'26. [openreview]
Enabling User Agency in Scalable Content Recommendations with Large Language Models. Yucheng Li, Gerrit J.J. van den Burg, Wei Liu, Zhunxuan Wang, Abhishek Tripathi, and Murat Sensoy. AAMAS'26. [ifaamas]
Gradual Fine-Tuning with Graph Routing for Multi-Source Unsupervised Domain Adaptation. Yao Ma^†, Samuel Louvan^†, and Zhunxuan Wang^†. CoLLAs'24. [pmlr] [video] [poster]
Nonparametric Learning of Two-Layer ReLU Residual Units. Zhunxuan Wang, Linyun He, Chunchuan Lyu, and Shay B. Cohen. TMLR'22. [openreview] [code]
Image Deconvolution with Deep Image and Kernel Priors. Zhunxuan Wang, Zipei Wang, Qiqi Li, and Hakan Bilen. RLQ@ICCV'19. [cvf] [poster]

^† denotes equal contribution.