Related papers: LightPFP: A Lightweight Route to Ab Initio Accurac…

Machine learning (ML) techniques and atomistic modeling have rapidly transformed materials design and discovery. Specifically, generative models can swiftly propose promising materials for targeted applications. However, the predicted…

Universal machine-learning interatomic potentials (uMLIPs) enable reactive molecular simulations with near-DFT accuracy, yet applying them efficiently to large, realistic condensed-phase systems remains computationally demanding. Here we…

Machine Learning Interatomic Potentials (MLIPs) are becoming a central tool in simulation-based chemistry. However, like most deep learning models, MLIPs struggle to make accurate predictions on out-of-distribution data or when trained in a…

Machine learning interatomic potentials (MLIPs) have revolutionized molecular and materials modeling, but existing benchmarks suffer from data leakage, limited transferability, and an over-reliance on error-based metrics tied to specific…

The foundation model (FM) paradigm is transforming Machine Learning Force Fields (MLFFs), leveraging general-purpose representations and scalable training to perform a variety of computational chemistry tasks. Although MLFF FMs have begun…

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…

Crystal Structure Prediction (CSP) of molecular crystals plays a central role in applications, such as pharmaceuticals and organic electronics. CSP is challenging and computationally expensive due to the need to explore a large search space…

Machine learning interatomic potentials (MLIPs) are inherently limited by the accuracy of the training data, usually consisting of energies and forces obtained from quantum mechanical calculations, such as density functional theory (DFT).…

Machine Learning Interatomic Potentials (MLIP) are a novel in silico approach for molecular property prediction, creating an alternative to disrupt the accuracy/speed trade-off of empirical force fields and density functional theory (DFT).…

Diffusion Models have emerged as a leading class of generative models, yet their iterative sampling process remains computationally expensive. Timestep distillation is a promising technique to accelerate generation, but it often requires…

GNN-to-MLP (G2M) methods have emerged as a promising approach to accelerate Graph Neural Networks (GNNs) by distilling their knowledge into simpler Multi-Layer Perceptrons (MLPs). These methods bridge the gap between the expressive power of…

Generative recommendation models employing Semantic IDs (SIDs) exhibit strong potential, yet their practical deployment is bottlenecked by the high inference latency of beam-expanded autoregressive decoding. In this work, we identify that…

One of the ultimate goals of computational modeling in condensed matter is to be able to accurately compute materials properties with minimal empirical information. First-principles approaches such as the density functional theory (DFT)…

Free energy profiles serve as a fundamental bridge between microscopic atomic fluctuations and macroscopic thermodynamic observables. Estimating the free energy profile along a reaction coordinate, referred to as the potential of mean force…

Accurate evaluation of the thermal conductivity of a material can be a challenging task from both experimental and theoretical points of view. In particular for the nanostructured materials, the experimental measurement of thermal…

Accurate prediction of surface energies and stabilities is essential for materials design, yet first-principles calculations remain computationally expensive and most existing interatomic potentials are trained only on bulk systems. Here,…

Recent advances in machine learning, combined with the generation of extensive density functional theory (DFT) datasets, have enabled the development of universal machine learning interatomic potentials (uMLIPs). These models offer broad…

Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for…

Large Language models (LLMs) are achieving state-of-the-art performance in many different downstream tasks. However, the increasing urgency of data privacy puts pressure on practitioners to train LLMs with Differential Privacy (DP) on…

We present a novel approach to knowledge transfer in model-based reinforcement learning, addressing the critical challenge of deploying large world models in resource-constrained environments. Our method efficiently distills a high-capacity…