Aller au contenu principal
Profil bibliographique

Zequn Liu

Informations fournies par OpenAlex. Research Africa ne déduit ni nationalité, ni poste, ni coordonnées personnelles.

45Publications signalées
349Citations signalées
1Affiliations récentes

Les institutions déclarées

Les domaines associés

Topic ModelingNatural Language Processing TechniquesAI in cancer detectionImage Retrieval and Classification TechniquesEndometriosis Research and Treatment

Les publications récentes

2026 article OpenAlex

M2PL-GAN: Multi-View Multi-Level Pathology Semantic Perception Learning for H&E-to-IHC Virtual Staining

Zequn Liu, Liangkuan Zhu, Yining Xie, Xiaoqing Hu et autres

Immunohistochemistry (IHC) staining is crucial for determining tumor subtypes, obtaining protein expression information, and developing personalized treatment plans. But compared with hematoxylin and eosin (H&E) staining, IHC staining is more complex and expensive. With the advancement of deep learning, converting H&E stained …

cn (code pays fourni par la source)

0 citations IEEE Transactions on Medical Imaging
Accès ouvert 2025 preprint OpenAlex

Nature Language Model: Deciphering the Language of Nature for Scientific Discovery

Yingce Xia, Peiran Jin, Shufang Xie, Liang He et autres

Foundation models have revolutionized natural language processing and artificial intelligence, significantly enhancing how machines comprehend and generate human languages. Inspired by the success of these foundation models, researchers have developed foundation models for individual scientific domains, including small molecules, materials, proteins, DNA, …

1 citation arXiv (Cornell University)
Accès ouvert 2025 preprint OpenAlex

ExLM: Rethinking the Impact of [MASK] Tokens in Masked Language Models

Kangjie Zheng, Junwei Yang, Bin Feng, Zequn Liu et autres

Masked Language Models (MLMs) have achieved remarkable success in many self-supervised representation learning tasks. MLMs are trained by randomly masking portions of the input sequences with [MASK] tokens and learning to reconstruct the original content based on the remaining context. This paper …

0 citations arXiv (Cornell University)
Accès ouvert 2024 preprint OpenAlex

SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision

Kangjie Zheng, Junwei Yang, Bin Feng, Zequn Liu et autres

SMILES, a crucial textual representation of molecular structures, has garnered significant attention as a foundation for pre-trained language models (LMs). However, most existing pre-trained SMILES LMs focus solely on the single-token level supervision during pre-training, failing to fully leverage the substructural information …

1 citation arXiv (Cornell University)
2024 article OpenAlex

Nonlinear Model for Magnetostrictive Vibration Energy Harvester Considering Dynamic Forces

Zequn Liu, Wenmei Huang, Pingping Guo, Huiwen Yang et autres

Magnetostrictive vibration energy harvester (MVEH) has obvious advantages in output stability, strain capacity and electromechanical coupling. For MVEH, multiple bidirectional coupling of mechanica-magnetic-electric and nonlinear characteristics occur in the process of energy conversion. So, the models based on the linear piezomagnetic equation …

cn (code pays fourni par la source)

4 citations IEEE Sensors Journal
Accès ouvert 2023 article OpenAlex

ASXL3 gene mutations inhibit cell proliferation and promote cell apoptosis in mouse cardiomyocytes by upregulating lncRNA NONMMUT063967.2

Zequn Liu, Yanmin Jiang, Fang Fu, Ru Li et autres

Congenital heart disease (CHD) is a serious condition with unknown etiology. In a recent study, a compound heterozygous mutation (c.3526C > T [p.Arg1176Trp] and c.4643A > G [p.Asp1548Gly]) in the ASXL3 gene was identified, which is associated with CHD. This mutation was …

cn (code pays fourni par la source)

3 citations Biochemistry and Biophysics Reports

BNTIC News n’est pas le producteur de ces données. Les publications sont interrogées à la demande dans Crossref, OpenAIRE, DOAJ, Europe PMC, HAL, DataCite, AfricArXiv, ROR et la Banque mondiale, sans clé d’accès. OpenAlex reste optionnel. Aucun service payant n’est nécessaire et aucune donnée externe n’est enregistrée en base. Consulter les sources et leurs limites.