activity
20242026
collaborators

19 papers

cs.CV2026

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,…

cs.CV2026

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…

cs.LG2026

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…

cs.LG2026

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…

cs.CR2026

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,…

cs.LG2026

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…