Guolin Ke
YOU?
Author Swipe
View article: MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining
MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining Open
Large language models (LLMs) possess broad world knowledge and strong general-purpose reasoning ability, yet they struggle to learn from many in-context examples on standard machine learning (ML) tasks, that is, to leverage many-shot demon…
View article: CD93: A Promising NETs-Related Biomarker for Diagnosis and Therapy in Actinic Keratosis
CD93: A Promising NETs-Related Biomarker for Diagnosis and Therapy in Actinic Keratosis Open
Our study establishes CD93 as a key NETs-related biomarker in AK, mechanistically linking neutrophil-driven inflammation to angiogenesis. The CD93-Gö6976 interaction provides a translational basis for developing novel targeted therapies ag…
View article: Closed-Loop AI Enables Organic Continuous-Wave Laser
Closed-Loop AI Enables Organic Continuous-Wave Laser Open
The realization of continuous-wave (CW) organic lasers critically depends on the rational design of high-performance gain media to mitigate thermal effects and optical losses under sustained excitation. However, such design remains challen…
View article: Deep learning for sub-ångström-resolution imaging in uncorrected scanning transmission electron microscopy
Deep learning for sub-ångström-resolution imaging in uncorrected scanning transmission electron microscopy Open
Achieving sub-ångström resolution has long been restricted to sophisticated aberration-corrected scanning transmission electron microscopy (AC-STEM). Recent advances in computational super-resolution techniques, such as deconvolution and e…
View article: DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials
DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials Open
In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications…
View article: End‐to‐End Crystal Structure Prediction from Powder X‐Ray Diffraction
End‐to‐End Crystal Structure Prediction from Powder X‐Ray Diffraction Open
Powder X‐ray diffraction (PXRD) is a prevalent technique in materials characterization. While the analysis of PXRD often requires extensive human manual intervention, and most automated method only achieved at coarse‐grained level. The mor…
View article: SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis
SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis Open
View article: DPA-2: a large atomic model as a multi-task learner
DPA-2: a large atomic model as a multi-task learner Open
The rapid advancements in artificial intelligence (AI) are catalyzing transformative changes in atomic modeling, simulation, and design. AI-driven potential energy models have demonstrated the capability to conduct large-scale, long-durati…
View article: Intelligent System for Automated Molecular Patent Infringement Assessment
Intelligent System for Automated Molecular Patent Infringement Assessment Open
Automated drug discovery offers significant potential for accelerating the development of novel therapeutics by substituting labor-intensive human workflows with machine-driven processes. However, molecules generated by artificial intellig…
View article: MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild
MolParser: End-to-end Visual Recognition of Molecule Structures in the Wild Open
In recent decades, chemistry publications and patents have increased rapidly. A significant portion of key information is embedded in molecular structure figures, complicating large-scale literature searches and limiting the application of…
View article: Author Correction: Data-driven quantum chemical property prediction leveraging 3D conformations with Uni-Mol+
Author Correction: Data-driven quantum chemical property prediction leveraging 3D conformations with Uni-Mol+ Open
View article: A high-accuracy multi-model mixing retrosynthetic method
A high-accuracy multi-model mixing retrosynthetic method Open
The field of computer-aided synthesis planning (CASP) has seen rapid advancements in recent years, achieving significant progress across various algorithmic benchmarks. However, chemists often encounter numerous infeasible reactions when u…
View article: SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding
SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding Open
Scientific literature understanding is crucial for extracting targeted information and garnering insights, thereby significantly advancing scientific discovery. Despite the remarkable success of Large Language Models (LLMs), they face chal…
View article: S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search Open
Virtual Screening is an essential technique in the early phases of drug discovery, aimed at identifying promising drug candidates from vast molecular libraries. Recently, ligand-based virtual screening has garnered significant attention du…
View article: Enhancing Challenging Target Screening via Multimodal Protein-Ligand Contrastive Learning
Enhancing Challenging Target Screening via Multimodal Protein-Ligand Contrastive Learning Open
Recent advancements in genomics and proteomics have identified numerous clinically significant protein targets, with notably 85% categorized as undruggable. These targets present widespread challenges due to their complex structures and dy…
View article: Data-driven quantum chemical property prediction leveraging 3D conformations with Uni-Mol+
Data-driven quantum chemical property prediction leveraging 3D conformations with Uni-Mol+ Open
View article: Bridging Machine Learning and Thermodynamics for Accurate p <i>K</i> <sub>a</sub> Prediction
Bridging Machine Learning and Thermodynamics for Accurate p <i>K</i> <sub>a</sub> Prediction Open
Integrating scientific principles into machine learning models to enhance their predictive performance and generalizability is a central challenge in the development of AI for Science. Herein, we introduce Uni-pK a, a nov…
View article: Uni-Mol2: Exploring Molecular Pretraining Model at Scale
Uni-Mol2: Exploring Molecular Pretraining Model at Scale Open
In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences. The significant advancements in NLP and CV are predominantly driven by the …
View article: Accurate Conformation Sampling via Protein Structural Diffusion
Accurate Conformation Sampling via Protein Structural Diffusion Open
Accurately sampling of protein conformations is pivotal for advances in biology and medicine. Although there have been tremendous progress in protein structure prediction in recent years due to deep learning, models that can predict the di…
View article: Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction
Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction Open
In recent years, machine learning (ML) methods have emerged as promising alternatives for molecular docking, offering the potential for high accuracy without incurring prohibitive computational costs. However, recent studies have indicated…
View article: DPA-2: Towards a universal large atomic model for molecular and materials simulation
DPA-2: Towards a universal large atomic model for molecular and materials simulation Open
The rapid development of artificial intelligence (AI) is driving significant changes in the field of atomic modeling, simulation, and design. AI-based potential energy models have been successfully used to perform large-scale and long-time…
View article: Uni-SMART: Universal Science Multimodal Analysis and Research Transformer
Uni-SMART: Universal Science Multimodal Analysis and Research Transformer Open
In scientific research and its application, scientific literature analysis is crucial as it allows researchers to build on the work of others. However, the fast growth of scientific knowledge has led to a massive increase in scholarly arti…
View article: SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis
SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysis Open
Recent breakthroughs in Large Language Models (LLMs) have revolutionized scientific literature analysis. However, existing benchmarks fail to adequately evaluate the proficiency of LLMs in this domain, particularly in scenarios requiring h…
View article: A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metal-organic frameworks
A comprehensive transformer-based approach for high-accuracy gas adsorption predictions in metal-organic frameworks Open
View article: Node-Aligned Graph-to-Graph: Elevating Template-free Deep Learning Approaches in Single-Step Retrosynthesis
Node-Aligned Graph-to-Graph: Elevating Template-free Deep Learning Approaches in Single-Step Retrosynthesis Open
Single-step retrosynthesis in organic chemistry increasingly benefits from deep learning (DL) techniques in computer-aided synthesis design. While template-free DL models are flexible and promising for retrosynthesis prediction, they often…
View article: DPA-2: Towards a universal large atomic model for molecular and material simulation
DPA-2: Towards a universal large atomic model for molecular and material simulation Open
<h2><strong>Data:</strong></h2>\n<div>\n<ul>\n<li>The complete collection of datasets employed in this research is encapsulated within the archive file <em>data-v1.3.tgz. </em>This…
View article: DPA-2: A Large Atomic Model As a Multi-task Learner
DPA-2: A Large Atomic Model As a Multi-task Learner Open
Data: The complete collection of datasets employed in this research is encapsulated within the archive file data-v1.3.tgz. This encompasses both the upstream datasets for pre-training and downstream datasets for fine-tuning, all in DeePMD …
View article: End-to-End Crystal Structure Prediction from Powder X-Ray Diffraction
End-to-End Crystal Structure Prediction from Powder X-Ray Diffraction Open
Powder X-ray diffraction (PXRD) is a prevalent technique in materials characterization. While the analysis of PXRD often requires extensive human manual intervention, and most automated method only achieved at coarse-grained level. The mor…
View article: DPA-2: Towards a universal large atomic model for molecular and material simulation
DPA-2: Towards a universal large atomic model for molecular and material simulation Open
<h2><strong>Data:</strong></h2>\n<div>\n<ul>\n<li>The complete collection of datasets employed in this research is encapsulated within the archive file <em>data-v1.3.tgz. </em>This…
View article: DPA-2: Towards a universal large atomic model for molecular and material simulation
DPA-2: Towards a universal large atomic model for molecular and material simulation Open
Data: The complete collection of datasets employed in this research is encapsulated within the archive file data-v1.3.tgz. This encompasses both the upstream datasets for pre-training and downstream datasets for…