Author

Yangli-ao Geng

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Open access Sep 2026

MOBO: A Merging-Oriented Bi-Level Optimization Framework for Class Incremental Learning

MOBO is proposed, a Merging-Oriented Bi-Level Optimization framework that synergizes the optimization of the current task model with the performance of the final merged model, and effectively mitigates the performance loss caused by incompatible adapter integration.

Si-Yu Zhang, Wen Wang, Wen-Ju Sun et al. · Proceedings of the Thirty-Fi... · 0 citations

Aug 2026

Co$^{2}$ In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and Integration.

Experimental results show that Co $^{2}$ In achieves state-of-the-art performance with efficient memory consumption and empower Co $^{2}$ In to accumulate knowledge with high plasticity and stability.

Wen-Ju Sun, Qing-Yong Li, Bo-Yang Li et al. · IEEE Transactions on Pattern... · 0 citations