Tie‐Yan Liu
YOU?
Author Swipe
View article: AI-Enhanced Subseasonal Forecasting of Extreme Temperature Risks
AI-Enhanced Subseasonal Forecasting of Extreme Temperature Risks Open
Sub-seasonal weather prediction remains a significant scientific challenge due to the chaotic nature of the atmosphere, with current numerical and AI-driven models exhibiting limited skill, particularly at the fine spatial scales for human…
View article: Probing the Limit of Heat Transfer in Inorganic Crystals with Deep Learning
Probing the Limit of Heat Transfer in Inorganic Crystals with Deep Learning Open
The record includes the MatterK dataset and the DFT verification results in https://arxiv.org/abs/2503.11568.
View article: A Physically Constrained Deep-Learning Fusion Method for Estimating Surface NO<sub>2</sub> Concentration from Satellite and Ground Monitors
A Physically Constrained Deep-Learning Fusion Method for Estimating Surface NO<sub>2</sub> Concentration from Satellite and Ground Monitors Open
Accurate estimation of atmospheric chemical concentrations from multiple observations is crucial for assessing the health effects of air pollution. However, existing methods are limited by imbalanced samples from observations. Here, we int…
View article: Bridging Geometric States via Geometric Diffusion Bridge
Bridging Geometric States via Geometric Diffusion Bridge Open
The accurate prediction of geometric state evolution in complex systems is critical for advancing scientific domains such as quantum chemistry and material modeling. Traditional experimental and computational methods face challenges in ter…
View article: SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation
SFM-Protein: Integrative Co-evolutionary Pre-training for Advanced Protein Sequence Representation Open
Proteins, essential to biological systems, perform functions intricately linked to their three-dimensional structures. Understanding the relationship between protein structures and their amino acid sequences remains a core challenge in pro…
View article: Pattern based learning and optimisation through pricing for bin packing problem
Pattern based learning and optimisation through pricing for bin packing problem Open
As a popular form of knowledge and experience, patterns and their identification have been critical tasks in most data mining applications. However, as far as we are aware, no study has systematically examined the dynamics of pattern value…
View article: Provable Adaptivity of Adam under Non-uniform Smoothness
Provable Adaptivity of Adam under Non-uniform Smoothness Open
Adam is widely adopted in practical applications due to its fast convergence. However, its theoretical analysis is still far from satisfactory. Existing convergence analyses for Adam rely on the bounded smoothness assumption, referred to a…
View article: Predicting equilibrium distributions for molecular systems with deep learning
Predicting equilibrium distributions for molecular systems with deep learning Open
Advances in deep learning have greatly improved structure prediction of molecules. However, many macroscopic observations that are important for real-world applications are not functions of a single molecular structure but rather determine…
View article: Regeneration Learning: A Learning Paradigm for Data Generation
Regeneration Learning: A Learning Paradigm for Data Generation Open
Machine learning methods for conditional data generation usually build a mapping from source conditional data X to target data Y. The target Y (e.g., text, speech, music, image, video) is usually high-dimensional and complex, and contains …
View article: Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction
Self-Consistency Training for Density-Functional-Theory Hamiltonian Prediction Open
Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science problems. Yet, its applicability is limited by insufficient labeled data for …
View article: Does Lorentz-symmetric design boost network performance in jet physics?
Does Lorentz-symmetric design boost network performance in jet physics? Open
In the deep learning era, improving the neural network performance in jet physics is a rewarding task, as it directly contributes to more accurate physics measurements at the LHC. Recent research has proposed various network designs in con…
View article: Target-aware Molecule Generation for Drug Design Using a Chemical Language Model<sup>*</sup>
Target-aware Molecule Generation for Drug Design Using a Chemical Language Model<sup>*</sup> Open
Generative drug design facilitates the creation of compounds effective against pathogenic target proteins. This opens up the potential to discover novel compounds within the vast chemical space and fosters the development of innovative the…
View article: Enhancing geometric representations for molecules with equivariant vector-scalar interactive message passing
Enhancing geometric representations for molecules with equivariant vector-scalar interactive message passing Open
Geometric deep learning has been revolutionizing the molecular modeling field. Despite the state-of-the-art neural network models are approaching ab initio accuracy for molecular property prediction, their applications, such as drug discov…
View article: Accelerating protein engineering with fitness landscape modeling and reinforcement learning
Accelerating protein engineering with fitness landscape modeling and reinforcement learning Open
Protein engineering holds significant promise for designing proteins with customized functions, yet the vast landscape of potential mutations versus limited lab capacity constrains the discovery of optimal sequences. To address this, we pr…
View article: FABind: Fast and Accurate Protein-Ligand Binding
FABind: Fast and Accurate Protein-Ligand Binding Open
The preprocessed PDBbind2020 dataset for paper "FABind: Fast and Accurate Protein-Ligand Binding" with associated code at https://github.com/QizhiPei/FABind. The dataset files are saved as .pt and lmdb file for the convenience of use. We f…
View article: AIMD-Chig: Exploring the conformational space of a 166-atom protein Chignolin with ab initio molecular dynamics
AIMD-Chig: Exploring the conformational space of a 166-atom protein Chignolin with ab initio molecular dynamics Open
Molecular dynamics (MD) simulations have revolutionized the modeling of biomolecular conformations and provided unprecedented insight into molecular interactions. Due to the prohibitive computational overheads of ab initio simulation for l…
View article: Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance
Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance Open
Order execution is a fundamental task in quantitative finance, aiming at finishing acquisition or liquidation for a number of trading orders of the specific assets. Recent advance in model-free reinforcement learning (RL) provides a data-d…
View article: AI<sup>2</sup>BMD: efficient characterization of protein dynamics with<i>ab initio</i>accuracy
AI<sup>2</sup>BMD: efficient characterization of protein dynamics with<i>ab initio</i>accuracy Open
SUMMARY Biomolecular dynamics simulation is a fundamental technology for life sciences research, and its usefulness depends on its accuracy and efficiency. Classical molecular dynamics simulation is fast but lacks chemical accuracy. Quantu…
View article: SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition
SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognition Open
Error correction in automatic speech recognition (ASR) aims to correct those incorrect words in sentences generated by ASR models. Since recent ASR models usually have low word error rate (WER), to avoid affecting originally correct tokens…
View article: Deep Latent Regularity Network for Modeling Stochastic Partial Differential Equations
Deep Latent Regularity Network for Modeling Stochastic Partial Differential Equations Open
Stochastic partial differential equations (SPDEs) are crucial for modelling dynamics with randomness in many areas including economics, physics, and atmospheric sciences. Recently, using deep learning approaches to learn the PDE solution f…
View article: AMOM: Adaptive Masking over Masking for Conditional Masked Language Model
AMOM: Adaptive Masking over Masking for Conditional Masked Language Model Open
Transformer-based autoregressive (AR) methods have achieved appealing performance for varied sequence-to-sequence generation tasks, e.g., neural machine translation, summarization, and code generation, but suffer from low inference efficie…
View article: Extract and Attend: Improving Entity Translation in Neural Machine Translation
Extract and Attend: Improving Entity Translation in Neural Machine Translation Open
While Neural Machine Translation(NMT) has achieved great progress in recent years, it still suffers from inaccurate translation of entities (e.g., person/organization name, location), due to the lack of entity training instances. When we h…