Publications (38)
Hyperbolic Graph Diffusion Model
Lingfeng Wen, Xuan Tang, Mingjie Ouyang +5
Diffusion generative models (DMs) have achieved promising results in image and graph generation. However, real-world graphs, such as social networks, molecular graphs, and traffic…
We Need a More Robust Classifier: Dual Causal Learning Empowers Domain-Incremental Time Series Classification
Zhipeng Liu, Peibo Duan, Xuan Tang +6
The World Wide Web thrives on intelligent services that rely on accurate time series classification, which has recently witnessed significant progress driven by advances in deep le…
Multi-scale Geometry-aware Transformer for 3D Point Cloud Classification
Xian Wei, Muyu Wang, Shing-Ho Jonathan Lin +4
Self-attention modules have demonstrated remarkable capabilities in capturing long-range relationships and improving the performance of point cloud tasks. However, point cloud obje…
Investigation and optimization of the deconvolution method for PMT waveform reconstruction
Jingzhe Tang, Tianying Xiao, Xuan Tang +1
Photomultiplier tubes (PMTs) are extensively employed as photosensors in neutrino and dark matter detection. The precise charge and timing information extracted from the PMT wavefo…
Phase Dependent Hanbury-Brown and Twiss effect
Xuan Tang, Yunxiao Zhang, Xueshi Guo +3
Hanbury-Brown and Twiss (HBT) effect is the foundation for stellar intensity interferometry. However, it is a phase insensitive two-photon interference effect. In this paper, we ex…
ViR:the Vision Reservoir
Xian Wei, Bin Wang, Mingsong Chen +7
The most recent year has witnessed the success of applying the Vision Transformer (ViT) for image classification. However, there are still evidences indicating that ViT often suffe…
Dual-BEV Nav: Dual-layer BEV-based Heuristic Path Planning for Robotic Navigation in Unstructured Outdoor Environments
Jianfeng Zhang, Hanlin Dong, Jian Yang +6
Path planning with strong environmental adaptability plays a crucial role in robotic navigation in unstructured outdoor environments, especially in the case of low-quality location…
The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient
Jichu Li, Xuan Tang, Difan Zou
A variety of widely used optimization methods like SignSGD and Muon can be interpreted as instances of steepest descent under different norm-induced geometries. In this work, we st…
1D-Convolutional Capsule Network for Hyperspectral Image Classification
Haitao Zhang, Lingguo Meng, Xian Wei +5
Recently, convolutional neural networks (CNNs) have achieved excellent performances in many computer vision tasks. Specifically, for hyperspectral images (HSIs) classification, CNN…
Synonymous Codon Usage Bias Overrides Phylogeny to Reflect Convergent Frond Architecture in a Rapidly Radiating Fern Family Thelypteridaceae
Kerui Huang, Wenyan Zhao, Huan Li +14
Convergent evolution provides powerful evidence for natural selection, yet its molecular basis is typically sought in protein-coding amino acid substitutions. Whether adaptive pres…
Collabs: A Flexible and Performant CRDT Collaboration Framework
Matthew Weidner, Huairui Qi, Maxime Kjaer +7
A collaboration framework is a distributed system that serves as the data layer for a collaborative app. Conflict-free Replicated Data Types (CRDTs) are a promising theoretical tec…
Optical interference by amplitude measurement
Yunxiao Zhang, Xuan Tang, Xueshi Guo +3
Interference effects are usually observed by intensity measurement. Path indistinguishability by quantum complementarity principle requires projection of the interfering fields int…
AI Governance InternationaL Evaluation Index (AGILE Index) 2024
Yi Zeng, Enmeng Lu, Xin Guan +14
The rapid advancement of Artificial Intelligence (AI) technology is profoundly transforming human society and concurrently presenting a series of ethical, legal, and social issues.…
YASPS: A Symbolic Framework for Extensible, High-Performance IPC Simulation
Xuan Tang, Kemeng Huang, Gilbert Bernstein +2
Incremental Potential Contact (IPC) enables robust, contact-rich simulation by casting elasticity and contact as a single energy minimization problem, but high-performance IPC pipe…
Joint Learning of Discriminative Low-dimensional Image Representations Based on Dictionary Learning and Two-layer Orthogonal Projections
Xian Wei, Hao Shen, Yuanxiang Li +4
There are some inadequacies in the language description of this paper that require further improvement. This paper is based on a revision of a conference paper. It is now necessary…
Group Equivariant BEV for 3D Object Detection
Hongwei Liu, Jian Yang, Jianfeng Zhang +5
Recently, 3D object detection has attracted significant attention and achieved continuous improvement in real road scenarios. The environmental information is collected from a sing…
Generation of a CW anti-bunched photon field from a thin-film PPLN waveguide by two-photon interference with a weak coherent state
Yue Li, Haochuan Li, Yuhang Lei +7
An anti-bunched photon field is produced from a thin-film ppln waveguide by mixing the on-chip two-photon state with a weak but matched coherent state. This is achieved by taking o…
A Cross-Platform Benchmark for Interval Computation Libraries
Xuan Tang, Zachary Ferguson, Teseo Schneider +3
Interval computation is widely used to certify computations that use floating point operations to avoid pitfalls related to rounding error introduced by inaccurate operations. Desp…
HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenes
Zhengfei Lu, Jian Yang, Muyu Wang +7
Continual learning in visual navigation remains challenging due to catastrophic forgetting and the difficulties associated with adapting to diverse and evolving environments. To ad…
Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
Xuan Tang, Han Zhang, Yuan Cao +1
Adam is a popular and widely used adaptive gradient method in deep learning, which has also received tremendous focus in theoretical research. However, most existing theoretical wo…
Learning Robust and Lightweight Model through Separable Structured Transformations
Xian Wei, Yanhui Huang, Yangyu Xu +5
With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are…
DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification
Zhipeng Liu, Peibo Duan, Binwu Wang +5
Real-world time series typically exhibit complex temporal variations, making the time series classification task notably challenging. Recent advancements have demonstrated the pote…
R2Det: Exploring Relaxed Rotation Equivariance in 2D object detection
Zhiqiang Wu, Yingjie Liu, Hanlin Dong +5
Group Equivariant Convolution (GConv) empowers models to explore underlying symmetry in data, improving performance. However, real-world scenarios often deviate from ideal symmetri…
Scaling Laws for Precision in High-Dimensional Linear Regression
Dechen Zhang, Xuan Tang, Yingyu Liang +1
Low-precision training is critical for optimizing the trade-off between model quality and training costs, necessitating the joint allocation of model size, dataset size, and numeri…
A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization
Xuan Tang, Jichu Li, Difan Zou
The rapid scaling of large language models (LLMs) has made low-precision training essential for reducing memory, improving efficiency, and enabling larger models and datasets. Exis…
Quantum entangled Sagnac interferometer
Wen Zhao, Xuan Tang, Xueshi Guo +2
SU(1,1) interferometer (SUI) is a novel type of interferometer that uses directly entangled quantum fields for sensing phase change. For rotational sensing, Sagnac geometry is usua…
Hyperbolic Contrastive Learning for Hierarchical 3D Point Cloud Embedding
Yingjie Liu, Pengyu Zhang, Ziyao He +3
Hyperbolic spaces allow for more efficient modeling of complex, hierarchical structures, which is particularly beneficial in tasks involving multi-modal data. Although hyperbolic g…
Autoencoders with Intrinsic Dimension Constraints for Learning Low Dimensional Image Representations
Jianzhang Zheng, Hao Shen, Jian Yang +5
Autoencoders have achieved great success in various computer vision applications. The autoencoder learns appropriate low dimensional image representations through the self-supervis…
TimeFormer: Transformer with Attention Modulation Empowered by Temporal Characteristics for Time Series Forecasting
Zhipeng Liu, Peibo Duan, Xuan Tang +6
Although Transformers excel in natural language processing, their extension to time series forecasting remains challenging due to insufficient consideration of the differences betw…
Curvature-Aware Captioning:Leveraging Geodesic Attention for 3D Scene Understanding
Ziyao He, Yingjie Liu, ZhangYangRui +3
Accurate 3D scene description is fundamental to robotic navigation and augmented reality, yet current dense captioning methods face significant limitations in processing sparse poi…
Continual Learning via Manifold Expansion Replay
Zihao Xu, Xuan Tang, Yufei Shi +4
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual le…
OMGSR: You Only Need One Mid-timestep Guidance for Real-World Image Super-Resolution
Zhiqiang Wu, Zhaomang Sun, Tong Zhou +7
Denoising Diffusion Probabilistic Models (DDPMs) show promising potential in one-step Real-World Image Super-Resolution (Real-ISR). Current one-step Real-ISR methods typically inje…
Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification
Jianzhang Zheng, Fan Yang, Hao Shen +4
Adversarial attacks are often considered as threats to the robustness of Deep Neural Networks (DNNs). Various defending techniques have been developed to mitigate the potential neg…
NeuroLoc: Encoding Navigation Cells for 6-DOF Camera Localization
Xun Li, Jian Yang, Fenli Jia +10
Recently, camera localization has been widely adopted in autonomous robotic navigation due to its efficiency and convenience. However, autonomous navigation in unknown environments…
PDDFormer: Pairwise Distance Distribution Graph Transformer for Crystal Material Property Prediction
Xiangxiang Shen, Zheng Wan, Lingfeng Wen +7
Crystal structures can be simplified as a periodic point set that repeats across three-dimensional space along an underlying lattice. Traditionally, crystal representation methods…
SmartPlay: A Benchmark for LLMs as Intelligent Agents
Yue Wu, Xuan Tang, Tom M. Mitchell +1
Recent large language models (LLMs) have demonstrated great potential toward intelligent agents and next-gen automation, but there currently lacks a systematic benchmark for evalua…
Sparsity-Specific Code Optimization using Expression Trees
Philipp Herholz, Xuan Tang, Teseo Schneider +3
We introduce a code generator that converts unoptimized C++ code operating on sparse data into vectorized and parallel CPU or GPU kernels. Our approach unrolls the computation into…
Relaxed Rotational Equivariance via -Biases in Vision
Zhiqiang Wu, Yingjie Liu, Licheng Sun +7
Group Equivariant Convolution (GConv) can capture rotational equivariance from original data. It assumes uniform and strict rotational equivariance across all features as the trans…