Related papers: Understanding Structural Representation in Foundat…

Recent research on predicting the binding affinity between drug molecules and proteins use representations learned, through unsupervised learning techniques, from large databases of molecule SMILES and protein sequences. While these…

This work introduces a method for generating generalized structures of amorphous polymers using simulated polymerization and molecular dynamics equilibration, with a particular focus on amorphous polymers. The techniques and algorithms used…

Multimodal Large Language Models (MLLMs) excel in general domains but struggle with complex, real-world science. We posit that polymer science, an interdisciplinary field spanning chemistry, physics, biology, and engineering, is an ideal…

We introduce Group SELFIES, a molecular string representation that leverages group tokens to represent functional groups or entire substructures while maintaining chemical robustness guarantees. Molecular string representations, such as…

Understanding material failure is critical for designing stronger and lighter structures by identifying weaknesses that could be mitigated. Existing full-physics numerical simulation techniques involve trade-offs between speed, accuracy,…

Multimodal large language models (MLLMs) have advanced static visual--spatial reasoning, yet they often fail to preserve long-horizon spatial coherence in embodied settings where beliefs must be continuously revised from egocentric…

Polymers, macromolecules formed from covalently bonded monomers, underpin countless technologies and are indispensable to modern life. While deep learning is advancing polymer science, existing methods typically represent the whole polymer…

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with…

Accurate prediction of atomistic, thermodynamic, and kinetic properties from molecular structures underpins materials innovation. Existing computational and experimental approaches lack the scalability required to navigate chemical space…

In recent years, artificial intelligence has played an important role on accelerating the whole process of drug discovery. Various of molecular representation schemes of different modals (e.g. textual sequence or graph) are developed. By…

Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs are ineffective in this problem space because: (i) most models lack polymer-specific knowledge, and (ii) existing aligned…

The structure of membrane-active peptides and their interaction with lipid bilayers can be studied in oriented lipid membranes deposited on solid substrates. Such systems are desirable for a number of surface-sensitive techniques. Here we…

In science, we are interested not only in forecasting but also in understanding how predictions are made, specifically what the interpretable underlying model looks like. Data-driven machine learning technology can significantly streamline…

Accurate molecular property prediction is central to drug discovery, catalysis, and process design, yet real-world applications are often limited by small datasets. Molecular foundation models provide a promising direction by learning…

Identification of high affinity drug-target interactions is a major research question in drug discovery. Proteins are generally represented by their structures or sequences. However, structures are available only for a small subset of…

The discovery of polymers with targeted properties is challenged by the vast chemical design space and the limited availability of consistent, high-quality data across multiple properties. In this work, an integrated polymer informatics…

Large Language Models (LLMs) have achieved remarkable progress on advanced reasoning tasks such as mathematics and coding competitions. Meanwhile, physics, despite being both reasoning-intensive and essential to real-world understanding,…

Generalizable robotic mobile manipulation in open-world environments poses significant challenges due to long horizons, complex goals, and partial observability. A promising approach to address these challenges involves planning with a…

Experimental approaches have been applied to address questions in understanding three-dimensional chromatin organisation and function. As datasets increase in size and complexity, it becomes a challenge to reach a mechanistic interpretation…

Rapid and accurate simulations of fluid dynamics around complicated geometric bodies are critical in a variety of engineering and scientific applications, including aerodynamics and biomedical flows. However, while scientific machine…