Publications (27)
Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction
Zekun Ni, Jonathan Weyn, Hang Zhang +7
Over the past few years, machine learning-based data-driven weather prediction has been transforming operational weather forecasting by providing more accurate forecasts while usin…
WeatherReal: A Benchmark Based on In-Situ Observations for Evaluating Weather Models
Weixin Jin, Jonathan Weyn, Pengcheng Zhao +7
In recent years, AI-based weather forecasting models have matched or even outperformed numerical weather prediction systems. However, most of these models have been trained and eva…
Phase Neural Operator for Multi-Station Picking of Seismic Arrivals
Hongyu Sun, Zachary E. Ross, Weiqiang Zhu +1
Seismic wave arrival time measurements form the basis for numerous downstream applications. State-of-the-art approaches for phase picking use deep neural networks to annotate seism…
A Survey on Automated Program Repair Techniques
Kai Huang, Zhengzi Xu, Su Yang +4
With the rapid development and large-scale popularity of program software, modern society increasingly relies on software systems. However, the problems exposed by software have al…
Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysis
Hongyu Sun, Qiuhong Ke, Yongcai Wang +4
This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point clo…
Deep learning for low frequency extrapolation of multicomponent data in elastic full waveform inversion
Hongyu Sun, Laurent Demanet
Full waveform inversion (FWI) strongly depends on an accurate starting model to succeed. This is particularly true in the elastic regime: The cycle-skipping phenomenon is more seve…
Parameter-efficient Prompt Learning for 3D Point Cloud Understanding
Hongyu Sun, Yongcai Wang, Wang Chen +2
This paper presents a parameter-efficient prompt tuning method, named PPT, to adapt a large multi-modal model for 3D point cloud understanding. Existing strategies are quite expens…
AirBirds: A Large-scale Challenging Dataset for Bird Strike Prevention in Real-world Airports
Hongyu Sun, Yongcai Wang, Xudong Cai +5
One fundamental limitation to the research of bird strike prevention is the lack of a large-scale dataset taken directly from real-world airports. Existing relevant datasets are ei…
KSHSeek: Data-Driven Approaches to Mitigating and Detecting Knowledge-Shortcut Hallucinations in Generative Models
Zhongxin Liu, Zhiwei Wang, Jun Niu +6
The emergence of large language models (LLMs) has significantly advanced the development of natural language processing (NLP), especially in text generation tasks like question ans…
Learning Hierarchical Interaction for Accurate Molecular Property Prediction
Huiyang Hong, Xinkai Wu, Hongyu Sun +3
Discovering molecules with desirable molecular properties, including ADMET profiles, is of great importance in drug discovery. Existing approaches typically employ deep learning mo…
VSFormer: Mining Correlations in Flexible View Set for Multi-view 3D Shape Understanding
Hongyu Sun, Yongcai Wang, Peng Wang +3
View-based methods have demonstrated promising performance in 3D shape understanding. However, they tend to make strong assumptions about the relations between views or learn the m…
Study on the Impacts of Hazardous Behaviors on Autonomous Vehicle Collision Rates Based on Humanoid Scenario Generation in CARLA
Longfei Mo, Min Hua, Hongyu Sun +3
Testing of function safety and Safety Of The Intended Functionality (SOTIF) is important for autonomous vehicles (AVs). It is hard to test the AV's hazard response in the real worl…
ViewFormer: View Set Attention for Multi-view 3D Shape Understanding
Hongyu Sun, Yongcai Wang, Peng Wang +2
This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating m…
Skillful high-resolution weather forecasting independent of physical models
Pengcheng Zhao, Siqi Xiang, Weixin Jin +10
Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producin…
Beyond Film Subtitles: Is YouTube the Best Approximation of Spoken Vocabulary?
Adam Nohejl, Frederikus Hudi, Eunike Andriani Kardinata +5
Word frequency is a key variable in psycholinguistics, useful for modeling human familiarity with words even in the era of large language models (LLMs). Frequency in film subtitles…
SolarSeer: Ultrafast and accurate 24-hour solar irradiance forecasts outperforming numerical weather prediction across the USA
Mingliang Bai, Zuliang Fang, Shengyu Tao +14
Accurate 24-hour solar irradiance forecasting is essential for the safe and economic operation of solar photovoltaic systems. Traditional numerical weather prediction (NWP) models…
Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis
Hongyu Sun, Qiuhong Ke, Ming Cheng +4
This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training dat…
FDLLM: A Dedicated Detector for Black-Box LLMs Fingerprinting
Zhiyuan Fu, Junfan Chen, Lan Zhang +9
Large Language Models (LLMs) are rapidly transforming the landscape of digital content creation. However, the prevalent black-box Application Programming Interface (API) access to…
OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations
Pengcheng Zhao, Jiang Bian, Zekun Ni +9
In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP…
Local Crystal Misorientation Influences Non-Radiative Recombination
Sarthak Jariwala, Hongyu Sun, Gede W. P. Adhyaksa +5
We use ultrasensitive electron backscatter diffraction (EBSD) to map the local crystal orientations, grains, and grain boundaries in CH3NH3PbI3 (MAPI) perovskite thin films. Althou…
ViPFormer: Efficient Vision-and-Pointcloud Transformer for Unsupervised Pointcloud Understanding
Hongyu Sun, Yongcai Wang, Xudong Cai +2
Recently, a growing number of work design unsupervised paradigms for point cloud processing to alleviate the limitation of expensive manual annotation and poor transferability of s…
Accelerating Time-Reversal Imaging with Neural Operators for Real-time Earthquake Locations
Hongyu Sun, Yan Yang, Kamyar Azizzadenesheli +2
Earthquake hypocenters form the basis for a wide array of seismological analyses. Pick-based earthquake location workflows rely on the accuracy of phase pickers and may be biased w…
SeqPE: Transformer with Sequential Position Encoding
Huayang Li, Yahui Liu, Hongyu Sun +5
Since self-attention layers in Transformers are permutation invariant by design, positional encodings must be explicitly incorporated to enable spatial understanding. However, fixe…
An ACO-MPC Framework for Energy-Efficient and Collision-Free Path Planning in Autonomous Maritime Navigation
Yaoze Liu, Zhen Tian, Qifan Zhou +2
Automated driving on ramps presents significant challenges due to the need to balance both safety and efficiency during lane changes. This paper proposes an integrated planner for…
ADAF: An Artificial Intelligence Data Assimilation Framework for Weather Forecasting
Yanfei Xiang, Weixin Jin, Haiyu Dong +7
The forecasting skill of numerical weather prediction (NWP) models critically depends on the accurate initial conditions, also known as analysis, provided by data assimilation (DA)…
Cargo Ecosystem Dependency-Vulnerability Knowledge Graph Construction and Vulnerability Propagation Study
Peiyang Jia, Chengwei Liu, Hongyu Sun +4
Currently, little is known about the structure of the Cargo ecosystem and the potential for vulnerability propagation. Many empirical studies generalize third-party dependency gove…
Extrapolated full waveform inversion with deep learning
Hongyu Sun, Laurent Demanet
The lack of low frequency information and a good initial model can seriously affect the success of full waveform inversion (FWI), due to the inherent cycle skipping problem. Comput…