no code implementations • 11 Jan 2024 • Bo Chen, Xingyi Cheng, Pan Li, Yangli-ao Geng, Jing Gong, Shen Li, Zhilei Bei, Xu Tan, Boyan Wang, Xin Zeng, Chiming Liu, Aohan Zeng, Yuxiao Dong, Jie Tang, Le Song
We propose a unified protein language model, xTrimoPGLM, to address these two types of tasks simultaneously through an innovative pre-training framework.
no code implementations • 28 Oct 2023 • Wenju Sun, Qingyong Li, Wen Wang, Yangli-ao Geng
The knowledge from the plastic learner is transferred to the stable learner via cumulative parameter averaging.
1 code implementation • CVPR 2023 • Wenju Sun, Qingyong Li, Jing Zhang, Wen Wang, Yangli-ao Geng
BMKP decouples the functions of learning and knowledge remembering via a bilevel-memory design: a working memory responsible for adaptively model learning, to ensure plasticity; a long-term memory in charge of enduringly storing the knowledge incorporated within the learned model, to guarantee stability.
1 code implementation • 5 Jan 2022 • Wenju Sun, Qingyong Li, Jing Zhang, Danyu Wang, Wen Wang, Yangli-ao Geng
DisCOIL follows the basic principle of POC, but it adopts variational auto-encoders (VAE) instead of other well-established one-class classifiers (e. g. deep SVDD), because a trained VAE can not only identify the probability of an input sample belonging to a class but also generate pseudo samples of the class to assist in learning new tasks.
no code implementations • 10 May 2021 • Haomin Yu, Yangli-ao Geng, Yingjun Zhang, Qingyong Li, Jiayu Zhou
Despite the popularity of this single-task schema, it may neglect interactions among calibration tasks of different sensors, which encompass underlying information to promote calibration performance.
no code implementations • 2 Nov 2016 • Yangli-ao Geng, Qingyong Li, Rong Zheng, Fuzhen Zhuangz, Ruisi He
Furthermore, we discover that the number of clusters computed by RECOME is a step function of the $\alpha$ parameter with jump discontinuity on a small collection of values.
Databases