Zeroth-order optimization (ZO) has demonstrated remarkable promise in efficient fine-tuning tasks for Large Language Models (LLMs). In particular, recent advances incorporate the low-rankness of gradients, introducing low-rank ZO estimators to further reduce GPU memory consumption. However, most existing works focus so...
Y. Sun, Qi-Xin Zhang, Liang Ding et al.· IEEE Transactions on Pattern...· 11 citations· ⚡1
RegimeFormer is presented, a large protein perturbation model coupled to RegimeAtlas, which is constructed by harmonizing, representing and indexing 202,556,313 non-redundant protein sequences across the tree of life to establish a large-model framework for mapping, predicting and querying protein perturbation landscap...
Simkins Ma, Yinxiang Chai, Yi Wu et al.· bioRxiv· 0 citations
CSN is proposed, which enables efficient Communication with Skill Neurons in decentralized MARL by exchanging the essential components of learned knowledge at neuron level by communicating only a sparse subset of model parameters and doing so intermittently.
Jiahua Lan, Li Shen, Ruijun Liu et al.· IEEE Transactions on Pattern...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.