Publications (60)
SVGen: Interpretable Vector Graphics Generation with Large Language Models
Feiyu Wang, Zhiyuan Zhao, Yuandong Liu +4
Scalable Vector Graphics (SVG) is widely used in front-end development and UI/UX design due to its scalability, editability, and rendering efficiency. However, turning creative ide…
Semantic-Aware Temporal Adaptation for UAV Anti-UAV Tracking
Xiaozhen Qiao, Da Zhang, Yubin Guo +3
The paper introduces SATATrack, a framework that uses semantic descriptions of the target and online feature distribution alignment to improve UAV-to-UAV tracking under rapid appea…
Correlated two-photon imaging with true thermal light
Da Zhang, Xi-Hao Chen, Yan-Hua Zhai +1
We report the first experimental demonstration of two-photon correlated imaging with true thermal light from a hollow cathode lamp. The coherence time of the source is much shorter…
StitchFusion: Weaving Any Visual Modalities to Enhance Multimodal Semantic Segmentation
Bingyu Li, Da Zhang, Zhiyuan Zhao +2
Multimodal semantic segmentation shows significant potential for enhancing segmentation accuracy in complex scenes. However, current methods often incorporate specialized feature f…
IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework
Feiyu Wang, Jiayuan Yang, Zhiyuan Zhao +4
Scalable Vector Graphics (SVG) are central to digital design due to their inherent scalability and editability. Despite significant advancements in content generation enabled by Vi…
When Box Meets Graph Neural Network in Tag-aware Recommendation
Fake Lin, Ziwei Zhao, Xi Zhu +6
Last year has witnessed the re-flourishment of tag-aware recommender systems supported by the LLM-enriched tags. Unfortunately, though large efforts have been made, current solutio…
An authenticated and secure accounting system for international emissions trading
Chenxing Li, Yang Yu, Andrew Chi-Chih Yao +2
Expanding multi-country emissions trading system is considered as crucial to fill the existing mitigation gap for the 2\degree C climate target. Trustworthy emissions accounting is…
MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
Da Zhang, Xiyang Dai, Xin Wang +2
This research strives for natural language moment retrieval in long, untrimmed video streams. The problem is not trivial especially when a video contains multiple moments of intere…
Temporal-order-driven asymmetric quantum interference and temporal coherence enhancement in spontaneous six-wave mixing
Da Zhang, Yu Zhang
Narrow-band multiphoton entanglement sources serve as a core enabling resource for advanced quantum information technologies. Recently, researchers have directly generated energy-t…
Unsupervised Detection of Topological Phase Transitions with a Quantum Reservoir
Li Xin, Da Zhang, Zhang-Qi Yin
In quantum many-body systems, characterizing topological phase transitions typically requires complex many-body topological invariants, which are costly to compute and measure. Ins…
UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting
Da Zhang, Bingyu Li, Zhuyuan Zhao +3
As multimodal data proliferates across diverse real-world applications, leveraging heterogeneous information such as texts and timestamps for accurate time series forecasting (TSF)…
Unveiling the link between fractional Schrödinger equation and light propagation in honeycomb lattice
Da Zhang, Yiqi Zhang, Zhaoyang Zhang +5
We establish a link between the fractional Schrödinger equation (FSE) and light propagation in the honeycomb lattice (HCL) - the Dirac-Weyl equation (DWE). The fractional Laplacia…
The Gene of Scientific Success
Xiangjie Kong, Jun Zhang, Da Zhang +3
This paper elaborates how to identify and evaluate causal factors to improve scientific impact. Currently, analyzing scientific impact can be beneficial to various academic activit…
Bitcoin's future carbon footprint
Shize Qin, Lena KlaaÃen, Ulrich Gallersdörfer +2
The carbon footprint of Bitcoin has drawn wide attention, but Bitcoin's long-term impact on the climate remains uncertain. Here we present a framework to overcome uncertainties in…
Hierarchy of Genuine Tripartite Non-Gaussian Entanglement
Da Zhang, David Barral, Yanpeng Zhang +2
Triple-photon states generated by three-mode spontaneous parametric down-conversion are the paradigm of unconditional non-Gaussian states, essential assets for quantum advantage. H…
Spatiotemporal Arbitrage of Large-Scale Portable Energy Storage for Grid Congestion Relief
Guannan He, Da Zhang, Xidong Pi +3
Energy storage has great potential in grid congestion relief. By making large-scale energy storage portable through trucking, its capability to address grid congestion can be great…
MARIS: Marine Open-Vocabulary Instance Segmentation with Geometric Enhancement and Semantic Alignment
Bingyu Li, Feiyu Wang, Da Zhang +3
Most existing underwater instance segmentation approaches are constrained by close-vocabulary prediction, limiting their ability to recognize novel marine categories. To support ev…
Two-photon interference with true thermal light
Yan-Hua Zhai, Xi-Hao Chen, Da Zhang +1
Two-photon interference and "ghost" imaging with entangled light have attracted much attention since the last century because of the novel features such as non-locality and sub-wav…
Towards Realistic Open-Vocabulary Remote Sensing Segmentation: Benchmark and Baseline
Bingyu Li, Tao Huo, Haocheng Dong +4
Open-vocabulary remote sensing image segmentation (OVRSIS) remains underexplored due to fragmented datasets, limited training diversity, and the lack of evaluation benchmarks that…
Big Networks: A Survey
Hayat Dino Bedru, Shuo Yu, Xinru Xiao +4
A network is a typical expressive form of representing complex systems in terms of vertices and links, in which the pattern of interactions amongst components of the network is int…
U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation
Bingyu Li, Da Zhang, Zhiyuan Zhao +2
Multimodal semantic segmentation is a pivotal component of computer vision and typically surpasses unimodal methods by utilizing rich information set from various sources.Current m…
Hierarchy of Nonlinear Entanglement Dynamics for Continuous Variables
Da Zhang, David Barral, Yin Cai +3
The entanglement produced by a bilinear Hamiltonian in continuous variables has been thoroughly studied and widely used. In contrast, the physics of entanglement resulting from non…
Generation of energy-time entangled triphotons in a six-level cold atomic system
Ling Niu, Zhiyin Duan, Na Liu +5
Multiphoton entangled states are pivotal resources for implementing optical quantum information protocols. Recently, energy-time-entangled triphotons have been observed in hot atom…
Efficient quantum state tomography with auxiliary systems
Wenlong Zhao, Da Zhang, Huili Zhang +2
Quantum state tomography is a technique in quantum information science used to reconstruct the density matrix of an unknown quantum state, providing complete information about the…
S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks
Da Zhang, Xiyang Dai, Xin Wang +1
In this paper, we present a novel Single Shot multi-Span Detector for temporal activity detection in long, untrimmed videos using a simple end-to-end fully three-dimensional convol…
Deep Reinforcement Learning for Visual Object Tracking in Videos
Da Zhang, Hamid Maei, Xin Wang +1
In this paper we introduce a fully end-to-end approach for visual tracking in videos that learns to predict the bounding box locations of a target object at every frame. An importa…
The economics of utility-scale portable energy storage systems in a high-renewable grid
Guannan He, Jeremy Michalek, Soummya Kar +3
Battery storage is expected to play a crucial role in the low-carbon transformation of energy systems. The deployment of battery storage in the power gird, however, is currently se…
ProductNet: a Collection of High-Quality Datasets for Product Representation Learning
Chu Wang, Lei Tang, Yang Lu +5
ProductNet is a collection of high-quality product datasets for better product understanding. Motivated by ImageNet, ProductNet aims at supporting product representation learning b…
MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
Da Zhang, Bingyu Li, Zhiyuan Zhao +3
Medical time series are central to healthcare, enabling continuous monitoring and supporting timely clinical decisions. Despite recent progress, existing methods struggle to jointl…
Diverse Entanglement Mechanisms in Multimode Nonlinear Continuous Variables
Da Zhang, David Barral, Yanpeng Zhang +1
Non-Gaussian entangled states play a crucial role in harnessing quantum advantage in continuous-variable quantum information. However, how to fully characterize N-partite (N > 3) n…
Enhancing Quantum Machine Learning with Anyons
Da Zhang, Wen-Qiang Liu, Zhaohui Wei +1
The power of quantum computing and quantum machine learning relies on harnessing uniquely quantum phenomena as computational resources. While superposition, coherence and entanglem…
Exploring the Underwater World Segmentation without Extra Training
Bingyu Li, Tao Huo, Da Zhang +3
Accurate segmentation of marine organisms is vital for biodiversity monitoring and ecological assessment, yet existing datasets and models remain largely limited to terrestrial sce…
Multimodal Transfer: A Hierarchical Deep Convolutional Neural Network for Fast Artistic Style Transfer
Xin Wang, Geoffrey Oxholm, Da Zhang +1
Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced on-line iterative…
An Open-Source Benchmark and Baseline for Multi-temporal Referring Segmentation
Bingyu Li, Da Zhang, Tao Huo +3
Large Vision-Language Models (LVLMs) have shown strong visual understanding and language-guided grounding abilities, yet their capacity for multi-temporal visual reasoning remains…
Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing
Bingyu Li, Haocheng Dong, Da Zhang +3
Open-Vocabulary Remote Sensing Image Segmentation (OVRSIS), an emerging task that adapts Open-Vocabulary Segmentation (OVS) to the remote sensing (RS) domain, remains underexplored…
INT: Towards Infinite-frames 3D Detection with An Efficient Framework
Jianyun Xu, Zhenwei Miao, Da Zhang +7
It is natural to construct a multi-frame instead of a single-frame 3D detector for a continuous-time stream. Although increasing the number of frames might improve performance, pre…
FAIM: Frequency-Aware Interactive Mamba for Time Series Classification
Da Zhang, Bingyu Li, Zhiyuan Zhao +4
Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition. TSC tasks require mod…
Transport properties in the photonic super-honeycomb lattice - a hybrid fermionic and bosonic system
Hua Zhong, Yiqi Zhang, Yi Zhu +6
We report on transport properties of the super-honeycomb lattice, the band structure of which possesses a flat band and Dirac cones, according to the tight-binding approximation. T…
CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking
Ruilong Ren, Songsheng Cheng, Yunpeng Zhou +9
The paper introduces CosFly-VLA, a vision-language-action model for UAVs that jointly grounds target location, predicts visibility, and generates flight actions, using spatial pret…
UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding
Da Zhang, Chenggang Rong, Bingyu Li +4
Large vision-language models (VLMs) have achieved remarkable success in natural scene understanding, yet their application to underwater environments remains largely unexplored. Un…
Greatly enhanced intensity-difference squeezing for narrow-band quantum metrology applications
Da Zhang, Changbiao Li, Zhaoyang Zhang +4
Narrow-band intensity-difference squeezing beams have important applications in quantum metrology and gravitational wave detection. The best way to generate narrow-band intensity-d…
FusAD: Time-Frequency Fusion with Adaptive Denoising for General Time Series Analysis
Da Zhang, Bingyu Li, Zhiyuan Zhao +3
Time series analysis plays a vital role in fields such as finance, healthcare, industry, and meteorology, underpinning key tasks including classification, forecasting, and anomaly…
Dynamic Proxy Domain Generalizes the Crowd Localization by Better Binary Segmentation
Junyu Gao, Da Zhang, Qiyu Wang +2
Crowd localization targets on predicting each instance precise location within an image. Current advanced methods propose the pixel-wise binary classification to tackle the congest…
Prototype-Based Low Altitude UAV Semantic Segmentation
Da Zhang, Gao Junyu, Zhao Zhiyuan
Semantic segmentation of low-altitude UAV imagery presents unique challenges due to extreme scale variations, complex object boundaries, and limited computational resources on edge…
Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting
Da Zhang, Bingyu Li, Feiyu Wang +2
Zero-shot object counting (ZSOC) aims to enumerate objects of arbitrary categories specified by text descriptions without requiring visual exemplars. However, existing methods ofte…
Robust and Efficient Quantum Reservoir Computing with Discrete Time Crystal
Da Zhang, Xin Li, Yibin Guo +3
The rapid development of machine learning and quantum computing has placed quantum machine learning at the forefront of research. However, existing quantum machine learning algorit…
Localization Technologies for Indoor Human Tracking
Da Zhang, Feng Xia, Zhuo Yang +2
The proliferation of wireless localization technologies provides a promising future for serving human beings in indoor scenarios. Their applications include real-time tracking, act…
A Criterion to identify maximally entangled nine-qubit state
Xinwei Zha, Irfan Ahmed, Da Zhang +1
We present a generalized criterion for maximally entangled nine-qubit states, whose minimum averaged subsystem purity should be equal to 1/14. In this note, we prove that absolutel…
Reference Product Search
Chu Wang, Lei Tang, Shujun Bian +3
For a product of interest, we propose a search method to surface a set of reference products. The reference products can be used as candidates to support downstream modeling tasks…
Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
Yu-Huan Wu, Da Zhang, Le Zhang +4
Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introdu…
Nonclassicality of fully degenerate triple-photon states and its application in generating non-Gaussian entanglement
Da Zhang, Yu Zhang, Juan Gao
We theoretically demonstrate via numerical modeling that fully degenerate triple-photon states generated by three-mode spontaneous parametric down-conversion can be categorized int…
FGAseg: Fine-Grained Pixel-Text Alignment for Open-Vocabulary Semantic Segmentation
Bingyu Li, Da Zhang, Zhiyuan Zhao +2
Open-vocabulary segmentation aims to identify and segment specific regions and objects based on text-based descriptions. A common solution is to leverage powerful vision-language m…
Simulation of complex DNA damage enhancement and biological effect validation for Proton-CAT
Lang Dong, Dechao An, Junxiang Wu +10
Proton therapy has been rapidly advancing due to its excellent conformal index, but its relatively low relative biological effect (RBE) has somewhat limited its therapeutic efficac…
Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning
Xin Wang, Jiawei Wu, Da Zhang +2
Although promising results have been achieved in video captioning, existing models are limited to the fixed inventory of activities in the training corpus, and do not generalize to…
Dynamic Temporal Pyramid Network: A Closer Look at Multi-Scale Modeling for Activity Detection
Da Zhang, Xiyang Dai, Yuan-Fang Wang
Recognizing instances at different scales simultaneously is a fundamental challenge in visual detection problems. While spatial multi-scale modeling has been well studied in object…
One-way network nonlocality of continuous variable entangled networks
Jun-Li Jiang, Xin-Zhu Liu, Xue Yang +3
Nonlocality is a key feature of quantum networks and is being studied for its potential applications in quantum communication and computing. Understanding and harnessing nonlocalit…
Performance Characterizations and Usage Guidelines of Samsung CXL Memory Module Hybrid Prototype
Jianping Zeng, Shuyi Pei, Da Zhang +10
The growing prevalence of data-intensive workloads, such as artificial intelligence (AI), machine learning (ML), high-performance computing (HPC), in-memory databases, and real-tim…
Quantum-inspired Interpretable Deep Learning Architecture for Text Sentiment Analysis
Bingyu Li, Da Zhang, Zhiyuan Zhao +2
Text has become the predominant form of communication on social media, embedding a wealth of emotional nuances. Consequently, the extraction of emotional information from text is o…
Certification of non-Gaussian Einstein-Podolsky-Rosen Steering
Mingsheng Tian, Zihang Zou, Da Zhang +5
Non-Gaussian quantum states are a known necessary resource for reaching a quantum advantage and for violating Bell inequalities in continuous variable systems. As one kind of manif…
Estimating air quality co-benefits of energy transition using machine learning
Da Zhang, Qingyi Wang, Shaojie Song +6
Estimating health benefits of reducing fossil fuel use from improved air quality provides important rationales for carbon emissions abatement. Simulating pollution concentration is…