* Equal contribution. † Project lead. ‡ Corresponding author.
2025
Conference
-
MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization
Siyuan Li*, Luyuan Zhang*, Zedong Wang, Juanxi Tian, Tan Cheng, Zicheng Liu, Chang Yu, Qingsong Xie, Haonan Lu, Haoqian Wang, Zhen Lei‡
CVPR , 2025
Project Page
|
Paper
|
Code
-
Taming LLMs by Scaling Learning Rates with Gradient Grouping
Siyuan Li*, Juanxi Tian*, Zedong Wang, Xin Jin, Zicheng Liu, Wentao Zhang, Dan Xu‡
ACL Main, 2025
Paper
|
Project
-
WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes
Ling Yang*, Juanxi Tian*, Kaixin Zhu*, Bohan Zeng*, Mingbao Lin, Hongjuan Pei, Wentao Zhang, Shuicheng Yan‡
Paper
|
Dataset
|
Code
2024
Conference
-
Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning
Siyuan Li*, Juanxi Tian*, Zedong Wang*, Luyuan Zhang, Zicheng Liu, Weiyang Jin, Yang Liu, Baigui Sun, Stan Z Li‡
Tech Report, 2024
Paper
|
Blog
-
OpenMixup: Open mixup toolbox and benchmark for visual representation learning
Siyuan Li*, Zedong Wang, Zicheng Liu, Juanxi Tian, Di Wu, Cheng Tan, Weiyang Jin, Stan Z Li‡
Tech Report, 2024
Project Page
|
Paper
|
Code
-
Switch EMA: A Free Lunch for Better Flatness and Sharpness
Siyuan Li*, Juanxi Tian*, Zicheng Liu*, Ge Wang, Zedong Wang, Weiyang Jin, Di Wu, Cheng Tan, Tao Lin, Yang Liu, Baigui Sun, Stan Z. Li‡
Paper
|
Code
-
Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis
Bohan Zeng*, Ling Yang*, Siyu Li, Jiaming Liu, Zixiang Zhang, Juanxi Tian, Kaixin Zhu, Yongzhen Guo, Fu-Yun Wang, Minkai Xu, Stefano Ermon, Wentao Zhang‡
Paper
|
Code
-
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Peng Xia*, Ze Chen, Juanxi Tian, Yangrui Gong, Ruibo Hou, Yue Xu, Zhenbang Wu, Zhiyuan Fan, Yiyang Zhou, Kangyu Zhu, Wenhao Zheng, Xiao Wang, Xuchao Zhang, Chentan Bansal, Marc Niethammer, Junzhou Huang, Hongtu Zhu, Yun Li, Jimeng Sun, Zongyuan Ge, Gang Li, James Zou, Huaxiu Yao‡
NeurIPS DB Track, 2024
Paper
|
Project
|
Code
Journal
-
A Survey on Mixup Augmentations and Beyond
Xin Jin*, Hongyu Zhu*, Siyuan Li*, Zedong Wang, Zicheng Liu, Juanxi Tian, Chang Yu, Huafeng Qin, Stan Z Li‡
Paper
|
Code
