34 citations · 93 across the 29 of their papers we have counts for
29 papers
Miles: Metric Learning with Expandable Subspace for Pre-Trained Model-Based Class-Incremental Learning
Kai Jiang, Zisong Lin, Hongyuan Zhang +2
Class Incremental Learning (CIL) aims to learn new concepts consistently from a data stream without forgetting. Unlike typical CIL methods which need to learn a model from scratch,…
MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
Da Zhang, Bingyu Li, Zhiyuan Zhao +3
Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointl…
Safeguarding Text-to-Image Generative Models Against Unauthorized Knowledge Distillation
Yilan Gao, Sida Huang, Hongyuan Zhang +1
Closed-weight generative services are increasingly deployed through query-based APIs, where users can obtain generated outputs while model parameters remain inaccessible. However,…
AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors
Xiaozhen Qiao, Wenjia Wang, Zhiyuan Zhao +4
Reconstructing 3D humans from images captured at multiple perspectives typically requires pre-calibration, like using checkerboards or MVS algorithms, which limits scalability and…
ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models
Ruishu Zhu, Zhihao Huang, Jiacheng Sun +3
Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce V…
GRPO-RM: Fine-Tuning Representation Models via GRPO-Driven Reinforcement Learning
Yanchen Xu, Ziheng Jiao, Hongyuan Zhang +1
The Group Relative Policy Optimization (GRPO), a reinforcement learning method used to fine-tune large language models (LLMs), has proved its effectiveness in practical application…
Multimodal Continual Learning with MLLMs from Multi-scenario Perspectives
Kai Jiang, Siqi Huang, Xiangyu Chen +4
Multimodal large language models (MLLMs) deployed on devices must adapt to continuously changing visual scenarios such as variations in background and perspective, to effectively p…
Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Models
Xiaozhen Qiao, Jingkai Zhao, Yuqiu Jiang +4
Vision-Language Models (VLMs) demonstrate impressive zero-shot generalization through large-scale image-text pretraining, yet their performance can drop once the deployment distrib…
Object-AVEdit: An Object-level Audio-Visual Editing Model
Youquan Fu, Ruiyang Si, Hongfa Wang +6
There is a high demand for audio-visual editing in video post-production and the film making field. While numerous models have explored audio and video editing, they struggle with…
Mixture of Noise for Pre-Trained Model-Based Class-Incremental Learning
Kai Jiang, Zhengyan Shi, Dell Zhang +2
Class Incremental Learning (CIL) aims to continuously learn new categories while retaining the knowledge of old ones. Pre-trained models (PTMs) show promising capabilities in CIL.…
AI Flow: Perspectives, Scenarios, and Approaches
Hongjun An, Wenhan Hu, Sida Huang +11
Pioneered by the foundational information theory by Claude Shannon and the visionary framework of machine intelligence by Alan Turing, the convergent evolution of information and c…
Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning
Yuheng Lei, Sitong Mao, Shunbo Zhou +3
A generalist agent must continuously learn and adapt throughout its lifetime, achieving efficient forward transfer while minimizing catastrophic forgetting. Previous work within th…
Learn Beneficial Noise as Graph Augmentation
Siqi Huang, Yanchen Xu, Hongyuan Zhang +1
Although graph contrastive learning (GCL) has been widely investigated, it is still a challenge to generate effective and stable graph augmentations. Existing methods often apply h…
NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering
Zhihao Huang, Xi Qiu, Yukuo Ma +5
Autoregressive models have achieved significant success in image generation. However, unlike the inherent hierarchical structure of image information in the spectral domain, standa…
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?
Yanchen Xu, Siqi Huang, Hongyuan Zhang +1
Graph contrastive learning (GCL) has been widely used as an effective self-supervised learning method for graph representation learning. However, how to apply adequate and stable g…
Enhance Vision-Language Alignment with Noise
Sida Huang, Hongyuan Zhang, Xuelong Li
With the advancement of pre-trained vision-language (VL) models, enhancing the alignment between visual and linguistic modalities in downstream tasks has emerged as a critical chal…
G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation
Tianxing Chen, Yao Mu, Zhixuan Liang +8
Recent advances in imitation learning for 3D robotic manipulation have shown promising results with diffusion-based policies. However, achieving human-level dexterity requires seam…
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
Hongyuan Zhang, Yanchen Xu, Sida Huang +1
Inspired by the idea of Positive-incentive Noise (Pi-Noise or -Noise) that aims at learning the reliable noise beneficial to tasks, we scientifically investigate the connection…
CNN2GNN: How to Bridge CNN with GNN
Ziheng Jiao, Hongyuan Zhang, Xuelong Li
Although the convolutional neural network (CNN) has achieved excellent performance in vision tasks by extracting the intra-sample representation, it will take a higher training exp…
Discretize Relaxed Solution of Spectral Clustering via a Non-Heuristic Algorithm
Hongyuan Zhang, Xuelong Li
Spectral clustering and its extensions usually consist of two steps: (1) constructing a graph and computing the relaxed solution; (2) discretizing relaxed solutions. Although the f…
Variational Positive-incentive Noise: How Noise Benefits Models
Hongyuan Zhang, Sida Huang, Yubin Guo +1
A large number of works aim to alleviate the impact of noise due to an underlying conventional assumption of the negative role of noise. However, some existing works show that the…
Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One
Hongyuan Zhang, Yanan Zhu, Xuelong Li
Graph neural networks (GNN) suffer from severe inefficiency. It is mainly caused by the exponential growth of node dependency with the increase of layers. It extremely limits the a…
Deep Manifold Learning with Graph Mining
Xuelong Li, Ziheng Jiao, Hongyuan Zhang +1
Admittedly, Graph Convolution Network (GCN) has achieved excellent results on graph datasets such as social networks, citation networks, etc. However, softmax used as the decision…
Matrix Completion via Non-Convex Relaxation and Adaptive Correlation Learning
Xuelong Li, Hongyuan Zhang, Rui Zhang
The existing matrix completion methods focus on optimizing the relaxation of rank function such as nuclear norm, Schatten-p norm, etc. They usually need many iterations to converge…