Discrete flow matching

I Gat, T Remez, N Shaul, F Kreuk, RTQ Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Despite Flow Matching and diffusion models having emerged as powerful generative
paradigms for continuous variables such as images and videos, their application to high …

[HTML][HTML] Quo Vadis ChatGPT? From Large Language Models to Large Knowledge Models

V Venkatasubramanian, A Chakraborty - Computers & Chemical …, 2025 - Elsevier
The startling success of ChatGPT and other large language models (LLMs) using
transformer-based generative neural network architecture in applications such as natural …

Benchmarking large language models for molecule prediction tasks

Z Zhong, K Zhou, D Mottin - arXiv preprint arXiv:2403.05075, 2024 - arxiv.org
Large Language Models (LLMs) stand at the forefront of a number of Natural Language
Processing (NLP) tasks. Despite the widespread adoption of LLMs in NLP, much of their …

Towards building specialized generalist ai with system 1 and system 2 fusion

K Zhang, B Qi, B Zhou - arXiv preprint arXiv:2407.08642, 2024 - arxiv.org
In this perspective paper, we introduce the concept of Specialized Generalist Artificial
Intelligence (SGAI or simply SGI) as a crucial milestone toward Artificial General Intelligence …

A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery

Y Zhang, X Chen, B Jin, S Wang, S Ji, W Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
In many scientific fields, large language models (LLMs) have revolutionized the way with
which text and other modalities of data (eg, molecules and proteins) are dealt, achieving …

Geometry Informed Tokenization of Molecules for Language Model Generation

X Li, L Wang, Y Luo, C Edwards, S Gui, Y Lin… - arXiv preprint arXiv …, 2024 - arxiv.org
We consider molecule generation in 3D space using language models (LMs), which
requires discrete tokenization of 3D molecular geometries. Although tokenization of …

Crystalline material discovery in the era of artificial intelligence

Z Wang, H Hua, W Lin, M Yang, KC Tan - arXiv preprint arXiv:2408.08044, 2024 - arxiv.org
Crystalline materials, with their symmetrical and periodic structures, possess a diverse array
of properties and have been widely used in various fields, ranging from electronic devices to …

Empowering Cognitive Digital Twins with Generative Foundation Models: Developing a Low-Carbon Integrated Freight Transportation System

X Li, H Xu, J Tupayachi, O Omitaomu… - arXiv preprint arXiv …, 2024 - arxiv.org
Effective monitoring of freight transportation is essential for advancing sustainable, low-
carbon economies. Traditional methods relying on single-modal data and discrete …

[HTML][HTML] Advancing Life Cycle Assessment of Sustainable Green Hydrogen Production Using Domain-Specific Fine-Tuning by Large Language Models Augmentation

Y Chen, U Liebau, SM Guruprasad… - Machine Learning and …, 2024 - mdpi.com
Assessing the sustainable development of green hydrogen and assessing its potential
environmental impacts using the Life Cycle Assessment is crucial. Challenges in LCA, like …

Amyloid-β Deposition Prediction with Large Language Model Driven and Task Oriented Learning of Brain Functional Networks

Y Liu, M Liu, Y Zhang, Y Guan, Q Guo… - … on Medical Imaging, 2025 - ieeexplore.ieee.org
Amyloid-β positron emission tomography can reflect the Amyloid-β protein deposition in the
brain and thus serves as one of the golden standards for Alzheimer's disease (AD) …