3.7k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Peking UniversityCN33 papers
- Princeton UniversityUS25 papers
- Renmin University of ChinaCN21 papers
- Chinese Academy of SciencesCN12 papers
- Tsinghua UniversityCN12 papers
- University of Chinese Academy of SciencesCN10 papers
- Institute of Applied Physics and Computational MathematicsCN9 papers
- Aerospace Information Research InstituteCN4 papers
- CAEP Software Center for High Performance Numerical SimulationCN4 papers
- International Research Center of Big Data for Sustainable Development GoalsCN4 papers
- Central South UniversityCN3 papers
- ETH ZurichCH3 papers
108 papers
Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection
Zhiyuan Wang, Yanxiang Chen, Pengcheng Zhao +2
Detecting AI-generated images across unseen architectures remains challenging, as existing models often overfit to generator-specific fingerprints and semantic content rather than…
Involution game with migration and spatial heterogeneity of social resources
Bo Li, Qiwen Ge, Yong Shi
Involution -- a phenomenon of excessive competition with diminishing returns -- has become a pressing socio-economic concern in contemporary China, prompting both academic inquiry…
Innovative Tooth Segmentation Using Hierarchical Features and Bidirectional Sequence Modeling
Xinxin Zhao, Jian Jiang, Yan Tian +5
Tooth image segmentation is a cornerstone of dental digitization. However, traditional image encoders relying on fixed-resolution feature maps often lead to discontinuous segmentat…
Inductive Learning for Possibilistic Logic Programs Under Stable Models
Hongbo Hu, Yisong Wang, Yi Huang +1
Possibilistic logic programs (poss-programs) under stable models are a major variant of answer set programming (ASP). While its semantics (possibilistic stable models) and properti…
Interpreting Language Models Through Concept Descriptions: A Survey
Nils Feldhus, Laura Kopf
Understanding the decision-making processes of neural networks is a central goal of mechanistic interpretability. In the context of Large Language Models (LLMs), this involves unco…
Rediscovering the Milky Way with an orbit superposition approach and APOGEE data V. The disc growth and history of star formation
Bridget Ratcliffe, Sergey Khoperskov, Nathan Lee +8
The Milky Way's (MW's) star formation history (SFH) offers insight into the chronology of its assembly and the mechanisms driving its structural development. In this study, we pres…
Infherno: End-to-end Agent-based FHIR Resource Synthesis from Free-form Clinical Notes
Johann Frei, Nils Feldhus, Lisa Raithel +3
For clinical data integration and healthcare services, the HL7 FHIR standard has established itself as a desirable format for interoperability between complex health data. Previous…
APCoTTA: Continual Test-Time Adaptation for Semantic Segmentation of Airborne LiDAR Point Clouds
Yuan Gao, Shaobo Xia, Sheng Nie +3
Airborne laser scanning (ALS) point cloud semantic segmentation is a fundamental task for large-scale 3D scene understanding. Fixed models deployed in real-world scenarios often su…
LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectives
Yuan Gao, Shaobo Xia, Pu Wang +3
Light detection and ranging (LiDAR) remote sensing encompasses two major directions: data interpretation and parameter inversion. However, both directions rely heavily on costly an…
ARSGaussian: 3D Gaussian Splatting with LiDAR for Aerial Remote Sensing Novel View Synthesis
Yiling Yao, Bing Zhang, Wenjuan Zhang +5
Novel View Synthesis (NVS) can reconstruct scenes from multi-view images and synthesize novel images from new viewpoints, which provides technical support for tasks such as target…
Towards Sharper Risk Bounds for Minimax Problems
Bowei Zhu, Shaojie Li, Yong Liu
Minimax problems have achieved success in machine learning such as adversarial training, robust optimization, reinforcement learning. For theoretical analysis, current optimal exce…
A novel directly energy-preserving method for charged particle dynamics
Yexin Li, Ping Jiang, Haochen Li
In this paper, we apply the coordinate increment discrete gradient (CIDG) method to solve the Lorentz force system which can be written as a non-canonical Hamiltonian system. Then…
Post-inflationary Leptogenesis and Dark Matter production: Metric versus Palatini formalism
Anish Ghoshal, Zygmunt Lalak, Supratik Pal +1
We investigate production of non-thermal dark matter particles and heavy sterile neutrinos from inflaton during the reheating era, which is preceded by a slow-roll inflationary epo…
Federated learning-outcome prediction with multi-layer privacy protection
Yupei Zhang, Yuxin Li, Yifei Wang +3
Learning-outcome prediction (LOP) is a long-standing and critical problem in educational routes. Many studies have contributed to developing effective models while often suffering…
Natural Model Reduction for Kinetic Equations
Zeyu Jin, Ruo Li
A promising approach to investigating high-dimensional problems is to identify their intrinsically low-dimensional features, which can be achieved through recently developed techni…
Direct and Indirect Treatment Effects in the Presence of Semi-Competing Risks
Yuhao Deng, Yi Wang, Xiao-Hua Zhou
Semi-competing risks refer to the phenomenon that the terminal event (such as death) can censor the non-terminal event (such as disease progression) but not vice versa. The treatme…
Reconstructing Three-decade Global Fine-Grained Nighttime Light Observations by a New Super-Resolution Framework
Jinyu Guo, Feng Zhang, Hang Zhao +2
Satellite-collected nighttime light provides a unique perspective on human activities, including urbanization, population growth, and epidemics. Yet, long-term and fine-grained nig…
Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
Jiaqi Han, Wenbing Huang, Yu Rong +3
It has been discovered that Graph Convolutional Networks (GCNs) encounter a remarkable drop in performance when multiple layers are piled up. The main factor that accounts for why…
Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models
Xiaolei Wang, Xinyu Tang, Wayne Xin Zhao +2
The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs), which rely on natural language conv…
Evolutionary Augmentation Policy Optimization for Self-supervised Learning
Noah Barrett, Zahra Sadeghi, Stan Matwin
Self-supervised Learning (SSL) is a machine learning algorithm for pretraining Deep Neural Networks (DNNs) without requiring manually labeled data. The central idea of this learnin…
Text2Poster: Laying out Stylized Texts on Retrieved Images
Chuhao Jin, Hongteng Xu, Ruihua Song +1
Poster generation is a significant task for a wide range of applications, which is often time-consuming and requires lots of manual editing and artistic experience. In this paper,…
Biomarker-guided heterogeneity analysis of genetic regulations via multivariate sparse fusion
Sanguo Zhang, Xiaonan Hu, Ziye Luo +3
Heterogeneity is a hallmark of many complex diseases. There are multiple ways of defining heterogeneity, among which the heterogeneity in genetic regulations, for example GEs (gene…
Enhancing User Behavior Sequence Modeling by Generative Tasks for Session Search
Haonan Chen, Zhicheng Dou, Yutao Zhu +3
Users' search tasks have become increasingly complicated, requiring multiple queries and interactions with the results. Recent studies have demonstrated that modeling the historica…
Multi-view Feature Augmentation with Adaptive Class Activation Mapping
Xiang Gao, Yingjie Tian, Zhiquan Qi
We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Diffe…