13 citations · 18 across the 17 of their papers we have counts for
6 papers · 1 filter
Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning
Jia Tang, Xinrui Wang, Songcan Chen
Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to constr…
Context-Aware Multi-Turn Visual-Textual Reasoning in LVLMs via Dynamic Memory and Adaptive Visual Guidance
Weijie Shen, Xinrui Wang, Yuanqi Nie +1
Current Large Language Models (LLMs) and Vision-Language Large Models (LVLMs) excel in single-turn tasks but face significant challenges in multi-turn interactions requiring deep c…
Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning
Xinrui Wang, Shao-yuan Li, Jiaqiang Zhang +1
Multi-Label Online Continual Learning (MOCL) requires models to learn continuously from endless multi-label data streams, facing complex challenges including persistent catastrophi…
LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
Chuanxing Geng, Qifei Li, Xinrui Wang +3
Using unlabeled wild data containing both in-distribution (ID) and out-of-distribution (OOD) data to improve the safety and reliability of models has recently received increasing a…
Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulation
Xinrui Wang, Yan Jin
Reinforcement learning (RL) has demonstrated remarkable potential in robotic manipulation but faces challenges in sample inefficiency and lack of interpretability, limiting its app…
Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning
Xinrui Wang, Chuanxing Geng, Wenhai Wan +2
Recent studies have verified that semi-supervised learning (SSL) is vulnerable to data poisoning backdoor attacks. Even a tiny fraction of contaminated training data is sufficient…