23 citations · 60 across the 16 of their papers we have counts for
17 papers
Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting
Xiang Yuan, Kaiqing Lei, Zhenyu Jin +3
The performance of Large Language Models (LLMs) is fundamentally influenced by the distributional composition of multi-domain pre-training data. While manual heuristics were preval…
Flash EQ-Linear: Accelerating Equivariant Linear Layers via Group-wise Discrete Fourier Transform
Zhongchen Zhao, Jixin Wang, Qi Xie +4
Equivariant networks embed geometric symmetries as structural priors through weight sharing, achieving remarkable parameter efficiency across vision tasks. However, this parameter…
BaRA: Bayesian Adaptive Rank Allocation for Parameter-Efficient Fine-Tuning
Zhibin Duan, Yuhong Wang, Jiahong Fu +3
While Low-rank adaptation (LoRA) enables highly efficient fine-tuning by constraining task-specific updates to fixed low-rank subspaces, this rigid design limits representational f…
Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration
Feiyu Tan, Qi Xie, Zongben Xu +1
Image restoration is an inherently ill posed inverse problem. Equivariant networks that embed geometric symmetry priors can mitigate this ill posedness and improve performance. How…
Rotation Equivariant Mamba for Vision Tasks
Zhongchen Zhao, Qi Xie, Keyu Huang +3
Rotation equivariance constitutes one of the most general and crucial structural priors for visual data, yet it remains notably absent from current Mamba-based vision architectures…
A Limit Theory of Foundation Models: A Mathematical Approach to Understanding Emergent Intelligence and Scaling Laws
Jun Shu, Junxiong Jia, Deyu Meng +1
Emergent intelligence have played a major role in the modern AI development. While existing studies primarily rely on empirical observations to characterize this phenomenon, a rigo…
KoopGen: Koopman Generator Networks for Representing and Predicting Dynamical Systems with Continuous Spectra
Liangyu Su, Jun Shu, Rui Liu +2
Representing and predicting high-dimensional and spatiotemporally chaotic dynamical systems remains a fundamental challenge in dynamical systems and machine learning. Although data…
Vanilla Group Equivariant Vision Transformer: Simple and Effective
Jiahong Fu, Qi Xie, Deyu Meng +1
Incorporating symmetry priors as inductive biases to design equivariant Vision Transformers (ViTs) has emerged as a promising avenue for enhancing their performance. However, exist…
Feed Two Birds with One Scone: Exploiting Function-Space Regularization for Both OOD Robustness and ID Fine-Tuning Performance
Xiang Yuan, Jun Shu, Deyu meng +1
Robust fine-tuning aims to achieve competitive in-distribution (ID) performance while maintaining the out-of-distribution (OOD) robustness of a pre-trained model when transferring…
Rotation Equivariant Arbitrary-scale Image Super-Resolution
Qi Xie, Jiahong Fu, Zongben Xu +1
The arbitrary-scale image super-resolution (ASISR), a recent popular topic in computer vision, aims to achieve arbitrary-scale high-resolution recoveries from a low-resolution inpu…
Improving Memory Efficiency for Training KANs via Meta Learning
Zhangchi Zhao, Jun Shu, Deyu Meng +1
Inspired by the Kolmogorov-Arnold representation theorem, KANs offer a novel framework for function approximation by replacing traditional neural network weights with learnable uni…
TRG-Net: An Interpretable and Controllable Rain Generator
Zhiqiang Pang, Hong Wang, Qi Xie +2
Exploring and modeling rain generation mechanism is critical for augmenting paired data to ease training of rainy image processing models. Against this task, this study proposes a…
Rotation Equivariant Proximal Operator for Deep Unfolding Methods in Image Restoration
Jiahong Fu, Qi Xie, Deyu Meng +1
The deep unfolding approach has attracted significant attention in computer vision tasks, which well connects conventional image processing modeling manners with more recent deep l…
Nonparametric Prior Learning in Differential Equation Modeling
Junxiong Jia, Deyu Meng, Zongben Xu +1
This paper addresses Bayesian inference related to partial differential equations (PDEs), particularly nonparametric regression constrained by PDEs. To effectively encode prior inf…
Meta Transition Adaptation for Robust Deep Learning with Noisy Labels
Jun Shu, Qian Zhao, Zongben Xu +1
To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted la…
Variational Bayes' method for functions with applications to some inverse problems
Junxiong Jia, Qian Zhao, Zongben Xu +2
Bayesian approach, as a useful tool for quantifying uncertainties, has been widely used for solving inverse problems of partial differential equations (PDEs). One of the key diffic…
Divide-and-Conquer Method for L1 Norm Matrix Factorization in the Presence of Outliers and Missing Data
Deyu Meng, Zongben Xu
The low-rank matrix factorization as a L1 norm minimization problem has recently attracted much attention due to its intrinsic robustness to the presence of outliers and missing da…