Representation Learning All Years 2026 All Pub. Types Preprint All Venues arXiv All Tags Continual LearningPretrained ModelsRepresentation Learning All Co-Authors Guanglong SunHang SuHongwei YanJun ZhuLiyuan WangQi ChengShuang CuiYi Zhong Clear Statistics Export 2026 MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated … Guanglong Sun, Kanglei Zhou, Liyuan Wang, Qi Cheng, Hongwei Yan, Shuang Cui, Hang Su, Jun Zhu, Yi Zhong Posted Sep 4, 2026 Preprint / Working Paper arXiv Cite PDF arXiv GitHub
'/>
<rect width='100%' height='100%' rx='14' ry='14' fill='none' stroke='%23ffffff' stroke-opacity='0.25' stroke-width='1.5'/>
<text x='50%' y='50%' dominant-baseline='middle' text-anchor='middle'
font-family='Inter, Segoe UI, Arial, sans-serif' font-size='38' font-weight='500'
fill='black' filter='url(%23shadow)'>
Coming Soon
</text>
</svg>)