Xiao Li (李虓)
Xiao Li (李虓)
Ph.D. candidate at University of Michigan
在 umich.edu 的电子邮件经过验证 - 首页
A geometric analysis of neural collapse with unconstrained features
Z Zhu*, T Ding*, J Zhou, X Li, C You, J Sulam, Q Qu
Advances in Neural Information Processing Systems 34, 29820-29834, 2021
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
J Zhou*, X Li*, T Ding, C You, Q Qu, Z Zhu
arXiv preprint arXiv:2203.01238, 2022
Are all losses created equal: A neural collapse perspective
J Zhou, C You, X Li, K Liu, S Liu, Q Qu, Z Zhu
Advances in Neural Information Processing Systems 35, 31697-31710, 2022
Investigating the catastrophic forgetting in multimodal large language models
Y Zhai, S Tong, X Li, M Cai, Q Qu, YJ Lee, Y Ma
arXiv preprint arXiv:2309.10313, 2023
Convolutional normalization: Improving deep convolutional network robustness and training
S Liu*, X Li*, Y Zhai, C You, Z Zhu, C Fernandez-Granda, Q Qu
Advances in Neural Information Processing Systems 34, 28919-28928, 2021
Principled and Efficient Transfer Learning of Deep Models via Neural Collapse
X Li*, S Liu*, J Zhou, X Lu, C Fernandez-Granda, Z Zhu, Q Qu
arXiv preprint arXiv:2212.12206, 2022
Deep-SMOLM: deep learning resolves the 3D orientations and 2D positions of overlapping single molecules with optimal nanoscale resolution
T Wu, P Lu, MA Rahman, X Li, MD Lew
Optics Express 30 (20), 36761-36773, 2022
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
P Wang*, X Li*, C Yaras, Z Zhu, L Balzano, W Hu, Q Qu
arXiv preprint arXiv:2311.02960, 2023
Neural Collapse in Multi-label Learning with Pick-all-label Loss
P Li*, Y Wang*, X Li, Q Qu
arXiv preprint arXiv:2310.15903, 2023
Dynamic Low-rank Estimation for Transformer-based Language Models
T Hua*, X Li*, S Gao, YC Hsu, Y Shen, H Jin
Findings of the Association for Computational Linguistics: EMNLP 2023, 9275-9287, 2023
文章 1–10