Simgrace: A simple framework for graph contrastive learning without data augmentation
Graph contrastive learning (GCL) has emerged as a dominant technique for graph
representation learning which maximizes the mutual information between paired graph …
representation learning which maximizes the mutual information between paired graph …
Biomaterials and bioelectronics for self-powered neurostimulation
Self-powered neurostimulation via biomaterials and bioelectronics innovation has emerged
as a compelling approach to explore, repair, and modulate neural systems. This review …
as a compelling approach to explore, repair, and modulate neural systems. This review …
Temporal attention unit: Towards efficient spatiotemporal predictive learning
Spatiotemporal predictive learning aims to generate future frames by learning from historical
frames. In this paper, we investigate existing methods and present a general framework of …
frames. In this paper, we investigate existing methods and present a general framework of …
Cvt-slr: Contrastive visual-textual transformation for sign language recognition with variational alignment
Sign language recognition (SLR) is a weakly supervised task that annotates sign videos as
textual glosses. Recent studies show that insufficient training caused by the lack of large …
textual glosses. Recent studies show that insufficient training caused by the lack of large …
Mole-bert: Rethinking pre-training graph neural networks for molecules
Recent years have witnessed the prosperity of pre-training graph neural networks (GNNs)
for molecules. Typically, atom types as node attributes are randomly masked and GNNs are …
for molecules. Typically, atom types as node attributes are randomly masked and GNNs are …
A systematic survey of chemical pre-trained models
Deep learning has achieved remarkable success in learning representations for molecules,
which is crucial for various biochemical applications, ranging from property prediction to …
which is crucial for various biochemical applications, ranging from property prediction to …
A fistful of vectors: a tool for intrinsic evaluation of word embeddings
The utilization of word embeddings—powerful models computed through Neural Network
architectures that encode words as vectors—has witnessed rapid growth across various …
architectures that encode words as vectors—has witnessed rapid growth across various …
A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias
Y Xu, L Hu, J Zhao, Z Qiu, Y Ye, H Gu - arXiv preprint arXiv:2404.00929, 2024 - arxiv.org
Based on the foundation of Large Language Models (LLMs), Multilingual Large Language
Models (MLLMs) have been developed to address the challenges of multilingual natural …
Models (MLLMs) have been developed to address the challenges of multilingual natural …
Why Deep Models Often Cannot Beat Non-deep Counterparts on Molecular Property Prediction?
Molecular property prediction (MPP) is a crucial task in the drug discovery pipeline, which
has recently gained considerable attention thanks to advances in deep neural networks …
has recently gained considerable attention thanks to advances in deep neural networks …
Lightweight contrastive protein structure-sequence transformation
Pretrained protein structure models without labels are crucial foundations for the majority of
protein downstream applications. The conventional structure pretraining methods follow the …
protein downstream applications. The conventional structure pretraining methods follow the …