Related papers: MMPolymer: A Multimodal Multitask Pretraining Fram…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

Establishing the relationship between 3D structures and the energy states of molecular systems has proven to be a promising approach for learning 3D molecular representations. However, existing methods are limited to modeling the molecular…

We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations…

3D-aware visual pretraining has proven effective in improving the performance of downstream robotic manipulation tasks. However, existing methods are constrained to Euclidean embedding spaces, whose flat geometry limits their ability to…

Machine-Learning Interatomic Potentials (MLIPs) have surged in popularity due to their promise of expanding the spatiotemporal scales possible for simulating molecules with high fidelity. The accuracy of any MLIP is dependent on the data…

Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism…

Multimodal representation learning is a challenging task in which previous work mostly focus on either uni-modality pre-training or cross-modality fusion. In fact, we regard modeling multimodal representation as building a skyscraper, where…

Artificial intelligence-based methods are becoming increasingly effective at screening libraries of polymers down to a selection that is manageable for experimental inquiry. The vast majority of presently adopted approaches for polymer…

We report a deep learning (DL) framework viz. deep autoencoder that autonomously discovers an appropriate order parameter from molecular dynamics (MD) simulation data to characterize the coil to globule phase transition of a polymer. The…

Foundation models have been transformational in machine learning fields such as natural language processing and computer vision. Similar success in atomic property prediction has been limited due to the challenges of training effective…

Two-dimensional (2D) materials have been a central focus of recent research because they host a variety of properties, making them attractive both for fundamental science and for applications. It is thus crucial to be able to identify…

We present a three-dimensional foundation model for polycrystalline materials based on a masked autoencoder trained via large-scale self-supervised learning. The model is pretrained on $100{,}000$ voxelized synthetic face-centered cubic…

Molecular property prediction is an increasingly critical task within drug discovery and development. Typically, neural networks can learn molecular properties using graph-based, language-based or feature-based methods. Recent advances in…

Polymer discovery is central to fields ranging from energy storage to biomedicine, but it is hindered by an astronomically large chemical design space and fragmented representations of structure, properties, and prior knowledge. This…

Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the…

Predicting stroke risk is a complex challenge that can be enhanced by integrating diverse clinically available data modalities. This study introduces a self-supervised multimodal framework that combines 3D brain imaging, clinical data, and…

Multimodal protein language models (PLMs) integrate sequence and token-based structural information, serving as a powerful foundation for protein modeling, generation, and design. However, the reliance on tokenizing 3D structures into…

Polymers are widely-studied materials with diverse properties and applications determined by different molecular structures. It is essential to represent these structures clearly and explore the full space of achievable chemical designs.…

Time series analysis is widely used in extensive areas. Recently, to reduce labeling expenses and benefit various tasks, self-supervised pre-training has attracted immense interest. One mainstream paradigm is masked modeling, which…

In this study, we present a sophisticated hybrid machine-learning framework that significantly improves the accuracy of predicting hydrogen storage capacities in metal hydrides. This is a critical challenge due to the scarcity of…