Related papers: Beyond the Training Domain: Robust Generative Tran…
Retrosynthesis prediction is a fundamental problem in organic synthesis, where the task is to identify precursor molecules that can be used to synthesize a target molecule. A key consideration in building neural models for this task is…
Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the…
Classical transition state theory (TST) is the cornerstone of reaction rate theory. It postulates a partition of phase space into reactant and product regions, which are separated by a dividing surface that reactive trajectories must cross.…
Recent generative adversarial networks (GANs) are able to generate impressive photo-realistic images. However, controllable generation with GANs remains a challenging research problem. Achieving controllable generation requires semantically…
Artificial intelligence and machine learning have shown great promise in their ability to accelerate novel materials discovery. As researchers and domain scientists seek to unify and consolidate chemical knowledge, the case for models with…
Recent advances in large language models (LLMs) have enabled molecular reasoning for property prediction. However, toxicity arises from complex biological mechanisms beyond chemical structure, necessitating mechanistic reasoning for…
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…
Accurately modeling chemical reactions at the atomistic level requires high-level electronic structure theory due to the presence of unpaired electrons and the need to properly describe bond breaking and making energetics. Commonly used…
Drawing inspiration from the achievements of natural language processing, we adopt self-supervised learning and utilize an equivariant graph neural network to develop a unified platform designed for training generative models capable of…
Set prediction is about learning to predict a collection of unordered variables with unknown interrelations. Training such models with set losses imposes the structure of a metric space over sets. We focus on stochastic and underdefined…
Generative pretraining (the "GPT" in ChatGPT) enables language models to learn from vast amounts of internet text without human supervision. This approach has driven breakthroughs across AI by allowing deep neural networks to learn from…
Machine-learned interatomic potentials (MLPs) provide near density functional theory (DFT) accuracy at reduced computational cost, but their reliability depends on representative training data and often deteriorates in transition-state…
Machine-learning driven models have proven to be powerful tools for the identification of phases of matter. In particular, unsupervised methods hold the promise to help discover new phases of matter without the need for any prior…
Predicting the effects of chemical and genetic perturbations on quantitative cell states is a central challenge in computational biology, molecular medicine and drug discovery. Recent work has leveraged large-scale single-cell data and…
Existing dynamics prediction frameworks for transient stability analysis (TSA) fail to achieve multi-scenario "universality": the inherent ability of a single, pre-trained architecture to generalize across diverse operating conditions,…
Reaction prediction, a critical task in synthetic chemistry, is to predict the outcome of a reaction based on given reactants. Generative models like Transformer have typically been employed to predict the reaction product. However, these…
Mapping reaction pathways and transition states (TS) is fundamental to chemistry but computationally expensive at scale. The minimum energy pathway (MEP) dictates reaction rates and mechanisms, yet recovering it via electronic-structure…
Transition State Theory is a central cornerstone in reaction dynamics. Its key step is the identification of a dividing surface that is crossed only once by all reactive trajectories. This assumption is often badly violated, especially when…
Tandem Mass Spectrometry is a cornerstone technique for identifying unknown small molecules in fields such as metabolomics, natural product discovery and environmental analysis. However, certain aspects, such as the probabilistic…
Deep learning models for anticipating the products of organic reactions have found many use cases, including validating retrosynthetic pathways and constraining synthesis-based molecular design tools. Despite compelling performance on…