8 papers
Brain-Inspired Hierarchical Modularity for General Continual Learning
Hongwei Yan, Kanglei Zhou, Qi Cheng +7
Continual learning, the ability to learn from sequential experience while retaining and adapting prior knowledge, is central to intelligent systems operating in changing environmen…
CEL: Continual Ego, Exo, and Ego-Exo Learning
Hongwei Yan, Kanglei Zhou, Yuchen Liu +3
Perception for embodied agents is video-based, often multi-view (ego, exo, or both), and inherently continual, with simultaneous task and viewpoint shifts. Yet continual learning (…
MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning
Guanglong Sun, Kanglei Zhou, Liyuan Wang +6
General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous data, making it a realistic y…
ComMem: Complementary Memory Systems for Test-Time Adaptation of Vision-Language Models
Guanglong Sun, Shuang Cui, Bo Lei +6
Test-time adaptation (TTA) of vision-language models (VLMs) is essential for their robust deployment in dynamic, real-world environments. However, existing TTA methods often adapt…
FlyPrompt: Brain-Inspired Random-Expanded Routing with Temporal-Ensemble Experts for General Continual Learning
Hongwei Yan, Guanglong Sun, Kanglei Zhou +3
General continual learning (GCL) challenges intelligent systems to learn from single-pass, non-stationary data streams without clear task boundaries. While recent advances in conti…
MePo: Meta Post-Refinement for Rehearsal-Free General Continual Learning
Guanglong Sun, Hongwei Yan, Liyuan Wang +5
To cope with uncertain changes of the external world, intelligent systems must continually learn from complex, evolving environments and respond in real time. This ability, collect…
Right Time to Learn:Promoting Generalization via Bio-inspired Spacing Effect in Knowledge Distillation
Guanglong Sun, Hongwei Yan, Liyuan Wang +3
Knowledge distillation (KD) is a powerful strategy for training deep neural networks (DNNs). Although it was originally proposed to train a more compact "student" model from a larg…
Orchestrate Latent Expertise: Advancing Online Continual Learning with Multi-Level Supervision and Reverse Self-Distillation
HongWei Yan, Liyuan Wang, Kaisheng Ma +1
To accommodate real-world dynamics, artificial intelligence systems need to cope with sequentially arriving content in an online manner. Beyond regular Continual Learning (CL) atte…