collaborators

6 papers

cs.CV2026

Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery

Wei He, Xianghan Meng, Zhiyuan Huang +3

Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set reco…

cs.LG2026

Delving into Muon and Beyond: Deep Analysis and Extensions

Xianbiao Qi, Marco Chen, Jiaquan Ye +2

The Muon optimizer has recently attracted considerable attention for its strong empirical performance and use of orthogonalized updates on matrix-shaped parameters, yet its underly…

cs.LG2026

SimpleGPT: Improving GPT via A Simple Normalization Strategy

Marco Chen, Xianbiao Qi, Yelin He +2

In this work, we revisit Transformer optimization through the lens of second-order geometry and establish a direct connection between architectural design, activation scale, the He…

cs.LG2025

Taming Transformer Without Using Learning Rate Warmup

Xianbiao Qi, Yelin He, Jiaquan Ye +5

Scaling Transformer to a large scale without using some technical tricks such as learning rate warump and using an obviously lower learning rate is an extremely challenging task, a…

cs.CV2025

Exploring a Principled Framework for Deep Subspace Clustering

Xianghan Meng, Zhiyuan Huang, Wei He +3

Subspace clustering is a classical unsupervised learning task, built on a basic assumption that high-dimensional data can be approximated by a union of subspaces (UoS). Nevertheles…

cs.LG2025

Neural Normalized Cut: A Differential and Generalizable Approach for Spectral Clustering

Wei He, Shangzhi Zhang, Chun-Guang Li +3

Spectral clustering, as a popular tool for data clustering, requires an eigen-decomposition step on a given affinity to obtain the spectral embedding. Nevertheless, such a step suf…