33 citations · 66 across the 25 of their papers we have counts for
27 papers
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
Yiming Liu, Bin Lu, Meng Jin +6
Marine lead (Pb) and its isotopes are critical tracers for ocean circulation and anthropogenic pollution, yet in-situ observations remain costly and sparse. While vast historical r…
Improving LLM Reasoning with Homophily-aware Structural and Semantic Text-Attributed Graph Compression
Zijun Di, Bin Lu, Huquan Kang +5
Large language models (LLMs) have demonstrated promising capabilities in Text-Attributed Graph (TAG) understanding. Recent studies typically focus on verbalizing the graph structur…
Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing
Nanyang Ye, Qiao Sun, Yifei Wang +10
Analog computing using non-volatile memristors has emerged as a promising solution for energy-efficient deep learning. New materials, like perovskites-based memristors are recently…
Scientific and technological knowledge grows linearly over time
Huquan Kang, Luoyi Fu, Russell J. Funk +6
The past few centuries have witnessed a dramatic growth in scientific and technological knowledge. However, the nature of that growth - whether exponential or otherwise - remains c…
Good Idea or Not, Representation of LLM Could Tell
Yi Xu, Bo Xue, Shuqian Sheng +6
In the ever-expanding landscape of academic research, the proliferation of ideas presents a significant challenge for researchers: discerning valuable ideas from the less impactful…
AceParse: A Comprehensive Dataset with Diverse Structured Texts for Academic Literature Parsing
Huawei Ji, Cheng Deng, Bo Xue +6
With the development of data-centric AI, the focus has shifted from model-driven approaches to improving data quality. Academic literature, as one of the crucial types, is predomin…
MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation
Jianping Zhou, Junhao Li, Guanjie Zheng +2
Missing values are prevalent in multivariate time series, compromising the integrity of analyses and degrading the performance of downstream tasks. Consequently, research has focus…
FLAME: Empowering Frozen LLMs for Knowledge Graph Completion
Bo Xue, Yi Xu, Bolei Ma +4
Traditional knowledge graph completion (KGC) methods rely solely on structural information and struggle with sparsity, while Large Language Models (LLMs) address these limitations…
Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints
Shiqing Gao, Jiaxin Ding, Luoyi Fu +2
In Constrained Reinforcement Learning (CRL), agents explore the environment to learn the optimal policy while satisfying constraints. The penalty function method has recently been…
MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
Jianping Zhou, Bin Lu, Zhanyu Liu +6
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missin…
OXYGENERATOR: Reconstructing Global Ocean Deoxygenation Over a Century with Deep Learning
Bin Lu, Ze Zhao, Luyu Han +7
Accurately reconstructing the global ocean deoxygenation over a century is crucial for assessing and protecting marine ecosystem. Existing expert-dominated numerical simulations fa…
CRoFT: Robust Fine-Tuning with Concurrent Optimization for OOD Generalization and Open-Set OOD Detection
Lin Zhu, Yifeng Yang, Qinying Gu +3
Recent vision-language pre-trained models (VL-PTMs) have shown remarkable success in open-vocabulary tasks. However, downstream use cases often involve further fine-tuning of VL-PT…
GeoViz: A Multi-View Visualization Platform for Spatio-temporal Knowledge Graph
Jianping Zhou, Junhao Li, Guanjie Zheng +3
In this paper, we propose a multi-view visualization technology for spatio-temporal knowledge graph(STKG), which utilizes three distinct perspectives: knowledge tree, knowledge net…
AceMap: Knowledge Discovery through Academic Graph
Xinbing Wang, Luoyi Fu, Xiaoying Gan +23
The exponential growth of scientific literature requires effective management and extraction of valuable insights. While existing scientific search engines excel at delivering sear…
Characterizing the Influence of Topology on Graph Learning Tasks
Kailong Wu, Yule Xie, Jiaxin Ding +4
Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations. However, the…
Temporal Generalization Estimation in Evolving Graphs
Bin Lu, Tingyan Ma, Xiaoying Gan +4
Graph Neural Networks (GNNs) are widely deployed in vast fields, but they often struggle to maintain accurate representations as graphs evolve. We theoretically establish a lower b…
RepEval: Effective Text Evaluation with LLM Representation
Shuqian Sheng, Yi Xu, Tianhang Zhang +7
The era of Large Language Models (LLMs) raises new demands for automatic evaluation metrics, which should be adaptable to various application scenarios while maintaining low cost a…
Sm-Nd Isotope Data Compilation from Geoscientific Literature Using an Automated Tabular Extraction Method
Zhixin Guo, Tao Wang, Chaoyang Wang +4
The rare earth elements Sm and Nd significantly address fundamental questions about crustal growth, such as its spatiotemporal evolution and the interplay between orogenesis and cr…
Is Reference Necessary in the Evaluation of NLG Systems? When and Where?
Shuqian Sheng, Yi Xu, Luoyi Fu +4
The majority of automatic metrics for evaluating NLG systems are reference-based. However, the challenge of collecting human annotation results in a lack of reliable references in…
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
Hang Yin, Liyao Xiang, Dong Ding +4
We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), and this type…
Graph Parsing Networks
Yunchong Song, Siyuan Huang, Xinbing Wang +2
Graph pooling compresses graph information into a compact representation. State-of-the-art graph pooling methods follow a hierarchical approach, which reduces the graph size step-b…
G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection
Fan Wu, Jinling Gao, Lanqing Hong +3
In this paper, we focus on a realistic yet challenging task, Single Domain Generalization Object Detection (S-DGOD), where only one source domain's data can be used for training ob…
Crafter: Facial Feature Crafting against Inversion-based Identity Theft on Deep Models
Shiming Wang, Zhe Ji, Liyao Xiang +4
With the increased capabilities at the edge (e.g., mobile device) and more stringent privacy requirement, it becomes a recent trend for deep learning-enabled applications to pre-pr…
GeoGalactica: A Scientific Large Language Model in Geoscience
Zhouhan Lin, Cheng Deng, Le Zhou +18
Large language models (LLMs) have achieved huge success for their general knowledge and ability to solve a wide spectrum of tasks in natural language processing (NLP). Due to their…