Publications (142)
VectorPainter: Advanced Stylized Vector Graphics Synthesis Using Stroke-Style Priors
Juncheng Hu, Ximing Xing, Jing Zhang +1
We introduce VectorPainter, a novel framework designed for reference-guided text-to-vector-graphics synthesis. Based on our observation that the style of strokes can be an importan…
Rethinking Cross-Subject Data Splitting for Brain-to-Text Decoding
Congchi Yin, Qian Yu, Zhiwei Fang +2
Recent major milestones have successfully reconstructed natural language from non-invasive brain signals (e.g. functional Magnetic Resonance Imaging (fMRI) and Electroencephalogram…
Molecular Identifier Visual Prompt and Verifiable Reinforcement Learning for Chemical Reaction Diagram Parsing
Jiahe Song, Chuang Wang, Yinfan Wang +11
Reaction diagram parsing (RxnDP) is critical for extracting chemical synthesis information from literature. Although recent Vision-Language Models (VLMs) have emerged as a promisin…
Feasibility study of quantum computing using trapped electrons
Qian Yu, Alberto M. Alonso, Jackie Caminiti +7
We investigate the feasibility of using electrons in a linear Paul trap as qubits in a future quantum computer. We discuss the necessary experimental steps to realize such a device…
DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models
Ximing Xing, Chuang Wang, Haitao Zhou +3
We demonstrate that pre-trained text-to-image diffusion models, despite being trained on raster images, possess a remarkable capacity to guide vector sketch synthesis. In this pape…
RxnCaption: Reformulating Reaction Diagram Parsing as Visual Prompt Guided Captioning
Jiahe Song, Chuang Wang, Bowen Jiang +13
Large-scale chemical reaction datasets are crucial for AI research in chemistry. However, existing chemical reaction data often exist as images within papers, making them not machi…
Action based Network for Conversation Question Reformulation
Zheyu Ye, Jiangning Liu, Qian Yu +1
Conversation question answering requires the ability to interpret a question correctly. Current models, however, are still unsatisfactory due to the difficulty of understanding the…
Feature Cross Search via Submodular Optimization
Lin Chen, Hossein Esfandiari, Gang Fu +2
In this paper, we study feature cross search as a fundamental primitive in feature engineering. The importance of feature cross search especially for the linear model has been know…
On the exponential integrability of the derivative of intersection and self-intersection local time for fractional Brownian motion and a limit theorem related to the self-intersection local time for fractional Brownian motion
Kaustav Das, Gregory Markowsky, Binghao Wu +1
We give the correct condition for existence of the -th derivative of the intersection local time for fractional Brownian motion, which was originally discussed in [Guo, J., Hu,…
Graph Neural Network Framework for Sentiment Analysis Using Syntactic Feature
Linxiao Wu, Yuanshuai Luo, Binrong Zhu +3
Amidst the swift evolution of social media platforms and e-commerce ecosystems, the domain of opinion mining has surged as a pivotal area of exploration within natural language pro…
Large Scale Business Discovery from Street Level Imagery
Qian Yu, Christian Szegedy, Martin C. Stumpe +4
Search with local intent is becoming increasingly useful due to the popularity of the mobile device. The creation and maintenance of accurate listings of local businesses worldwide…
Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions
Qian Yu, Lei Qi, Luping Zhou +5
Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these…
CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
Yandong Guan, Xilin Wang, Ximing Xing +3
In this work, we introduce CAD-Coder, a novel framework that reformulates text-to-CAD as the generation of CadQuery scripts - a Python-based, parametric CAD language. This represen…
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
Zhiwei Zhang, Zhizhong Zhang, Qian Yu +3
3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation. In this task, we notice that images could provide rich…
SketchyScene: Richly-Annotated Scene Sketches
Changqing Zou, Qian Yu, Ruofei Du +6
We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level. The dat…
Sketch-a-Net that Beats Humans
Qian Yu, Yongxin Yang, Yi-Zhe Song +2
We propose a multi-scale multi-channel deep neural network framework that, for the first time, yields sketch recognition performance surpassing that of humans. Our superior perform…
TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environments
Yuheng Lu, Qian Yu, Hongru Wang +7
Graphical User Interface (GUI) agents, which autonomously operate on digital interfaces through natural language instructions, hold transformative potential for accessibility, auto…
Straggler Mitigation in Distributed Matrix Multiplication: Fundamental Limits and Optimal Coding
Qian Yu, Mohammad Ali Maddah-Ali, A. Salman Avestimehr
We consider the problem of massive matrix multiplication, which underlies many data analytic applications, in a large-scale distributed system comprising a group of worker nodes. W…
Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation
Qian Yu, Yinghuan Shi, Yefeng Zheng +3
Robust segmentation for non-elongated tissues in medical images is hard to realize due to the large variation of the shape, size, and appearance of these tissues in different patie…
The net-regular strongly regular signed graphs with degree 5
Qian Yu, Yaoping Hou
In this paper, we determine all connected net-regular strongly regular signed graphs with degree 5. There are five and two strongly regular signed graphs with net-degree 3 and 1, r…
Limit theorems for functionals of two independent Gaussian processes
Jian Song, Fangjun Xu, Qian Yu
Under certain mild conditions, some limit theorems for functionals of two independent Gaussian processes are obtained. The results apply to general Gaussian processes including fra…
Attention-based Extraction of Structured Information from Street View Imagery
Zbigniew Wojna, Alex Gorban, Dar-Shyang Lee +4
We present a neural network model - based on CNNs, RNNs and a novel attention mechanism - which achieves 84.2% accuracy on the challenging French Street Name Signs (FSNS) dataset,…
Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms
Qian Yu, Yining Wang, Baihe Huang +2
In stochastic zeroth-order optimization, a problem of practical relevance is understanding how to fully exploit the local geometry of the underlying objective function. We consider…
Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework
Xiaoxiao Xu, Chen Yang, Qian Yu +7
We propose a general Variational Embedding Learning Framework (VELF) for alleviating the severe cold-start problem in CTR prediction. VELF addresses the cold start problem via alle…
EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation
Rui Nie, Chuang Wang, Haitao Zhou +4
Controllable local editing of 3D assets requires precise target localization and appropriate visual guidance. However, existing methods lack a simple yet accurate way to obtain 3D…
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
Qian Yu, Yining Wang, Baihe Huang +2
Optimization of convex functions under stochastic zeroth-order feedback has been a major and challenging question in online learning. In this work, we consider the problem of optim…
Balancing Multi-Target Semi-Supervised Medical Image Segmentation with Collaborative Generalist and Specialists
You Wang, Zekun Li, Lei Qi +3
Despite the promising performance achieved by current semi-supervised models in segmenting individual medical targets, many of these models suffer a notable decrease in performance…
Metal oxide resistive switching: evolution of the density of states across the metal-insulator transition
Alireza Mottaghizadeh, Qian Yu, Pei Lin Lang +2
We report the study of metal-STO-metal memristors where the doping concentration in STO can be fine-tuned through electric field migration of oxygen vacancies. In this tunnel junct…
SVGDreamer: Text Guided SVG Generation with Diffusion Model
Ximing Xing, Haitao Zhou, Chuang Wang +3
Text-guided scalable vector graphics (SVG) synthesis has broad applications in icon and sketch generation. However, existing text-to-SVG methods often suffer from limited editabili…
An estimation of Fisher information bound for distribution-dependent SDEs driven by fractional Brownian motion with small noise
Tongxuan Liu, Qian Yu
In this paper, we consider the distribution-dependent SDE driven by fractional Brownian motion with small noise and study the rate of Fisher information convergence in the central…
Limit Theorems for Tempered Linear Processes with Innovations in the Domain of Attraction of a Stable Law
Qian Yu
We study the partial-sum behavior of tempered linear processes \[ X_{N,n}=\sum_{j=1}^{\infty}e^{-λ_Nj}\frac{\ell(j)}{j}\varepsilon_{n-j}, \qquad λ_N\downarrow0, \] where i…
Building Information Modeling and Classification by Visual Learning At A City Scale
Qian Yu, Chaofeng Wang, Barbaros Cetiner +4
In this paper, we provide two case studies to demonstrate how artificial intelligence can empower civil engineering. In the first case, a machine learning-assisted framework, BRAIL…
Prune4Web: DOM Tree Pruning Programming for Web Agent
Jiayuan Zhang, Kaiquan Chen, Zhihao Lu +3
Web automation employs intelligent agents to execute high-level tasks by mimicking human interactions with web interfaces. Despite the capabilities of recent Large Language Model (…
AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
Juncheng Hu, Ziteng Xue, Guotao Liang +5
We introduce AmodalSVG, a new framework for amodal image vectorization that produces semantically organized and geometrically complete SVG representations from natural images. Exis…
Reason-SVG: Enhancing Structured Reasoning for Vector Graphics Generation with Reinforcement Learning
Ximing Xing, Ziteng Xue, Yandong Guan +3
Generating high-quality Scalable Vector Graphics (SVGs) is challenging for Large Language Models (LLMs), as it requires advanced reasoning for structural validity, semantic accurac…
SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation
Ximing Xing, Qian Yu, Chuang Wang +3
Recently, text-guided scalable vector graphics (SVG) synthesis has demonstrated significant potential in domains such as iconography and sketching. However, SVGs generated from exi…
AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
Lei Xiong, Kun Luo, Ziyi Xia +15
Autonomous scientific research is significantly advanced thanks to the development of AI agents. One key step in this process is finding the right scientific literature, whether to…
Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation
Xiawei Li, Qingyuan Xu, Jing Zhang +4
3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expe…
Trapping of electrons and ions in a dual-frequency Paul trap
Vladimir Mikhailovskii, Natalija Sheth, Guofeng Qu +12
We demonstrate the operation of a dual-frequency Paul trap and characterize its performance by storing either electrons or calcium ions while applying two quadrupole fields simulta…
The Devil is in the Middle: Exploiting Mid-level Representations for Cross-Domain Instance Matching
Qian Yu, Xiaobin Chang, Yi-Zhe Song +2
Many vision problems require matching images of object instances across different domains. These include fine-grained sketch-based image retrieval (FG-SBIR) and Person Re-identific…
Asymptotic Properties of the Derivative of Self-Intersection Local Time of Multidimensional Fractional Brownian Motion
Jiazhen Gu, Jinchi Jiang, Qian Yu
Let \{B_t^H,t\geq0\} be a d-dimensional fractional Brownian motion. We prove that the approximation of the first-order derivative of self-intersection local time, defined as α_{\v…
Feature Decomposition for Reducing Negative Transfer: A Novel Multi-task Learning Method for Recommender System
Jie Zhou, Qian Yu, Chuan Luo +1
In recent years, thanks to the rapid development of deep learning (DL), DL-based multi-task learning (MTL) has made significant progress, and it has been successfully applied to re…
Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation
Zhan Fa, Shumeng Li, Jian Zhang +3
Semi-supervised learning (SSL) techniques address the high labeling costs in 3D medical image segmentation, with the teacher-student model being a common approach. However, using a…
From 2D CAD Drawings to 3D Parametric Models: A Vision-Language Approach
Xilin Wang, Jia Zheng, Yuanchao Hu +3
In this paper, we present CAD2Program, a new method for reconstructing 3D parametric models from 2D CAD drawings. Our proposed method is inspired by recent successes in vision-lang…
A Fundamental Tradeoff between Computation and Communication in Distributed Computing
Songze Li, Mohammad Ali Maddah-Ali, Qian Yu +1
How can we optimally trade extra computing power to reduce the communication load in distributed computing? We answer this question by characterizing a fundamental tradeoff between…
Ising Model on Locally Tree-like Graphs: Uniqueness of Solutions to Cavity Equations
Qian Yu, Yury Polyanskiy
In the study of Ising models on large locally tree-like graphs, in both rigorous and non-rigorous methods one is often led to understanding the so-called belief propagation distrib…
ViewCraft3D: High-Fidelity and View-Consistent 3D Vector Graphics Synthesis
Chuang Wang, Haitao Zhou, Ling Luo +1
3D vector graphics play a crucial role in various applications including 3D shape retrieval, conceptual design, and virtual reality interactions due to their ability to capture ess…
Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation
Shumeng Li, Lei Qi, Qian Yu +3
Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce th…
Data-Free Generalized Zero-Shot Learning
Bowen Tang, Long Yan, Jing Zhang +3
Deep learning models have the ability to extract rich knowledge from large-scale datasets. However, the sharing of data has become increasingly challenging due to concerns regardin…
Derivative of self-intersection local time for multidimensional fractional Brownian motion
Qian Yu, Xianye Yu
The existence condition for first-order derivative of self-intersection local time for dimensional fractional Brownian motion can be obtained in Yu (2021). In this…
Volatility Estimation of General Gaussian Ornstein-Uhlenbeck Process
Salwa Bajja, Qian Yu
In this article we study the asymptotic behaviour of the realized quadratic variation of a process , where is a -Hölder continuous process wit…
Further Theoretical Study of Distribution Separation Method for Information Retrieval
Peng Zhang, Qian Yu, Yuexian Hou +3
Recently, a Distribution Separation Method (DSM) is proposed for relevant feedback in information retrieval, which aims to approximate the true relevance distribution by separating…
Higher order derivative of self-intersection local time for fractional Brownian motion
Qian Yu
We consider the existence and Hölder continuity conditions for the -th order derivatives of self-intersection local time for -dimensional fractional Brownian motion, where $…
Empowering LLMs to Understand and Generate Complex Vector Graphics
Ximing Xing, Juncheng Hu, Guotao Liang +3
The unprecedented advancements in Large Language Models (LLMs) have profoundly impacted natural language processing but have yet to fully embrace the realm of scalable vector graph…
Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation
Xiaoting Han, Lei Qi, Qian Yu +4
Unsupervised domain adaptation (UDA) methods have shown their promising performance in the cross-modality medical image segmentation tasks. These typical methods usually utilize a…
ELBO-T2IAlign: A Generic ELBO-Based Method for Calibrating Pixel-level Text-Image Alignment in Diffusion Models
Qin Zhou, Zhiyang Zhang, Jinglong Wang +5
Diffusion models excel at image generation. Recent studies have shown that these models not only generate high-quality images but also encode text-image alignment information throu…
Contrastive Learning for Knowledge-Based Question Generation in Large Language Models
Zhenhong Zhang, Jiajing Chen, Weiyan Shi +3
With the rapid development of artificial intelligence technology, especially the increasingly widespread application of question-and-answer systems, high-quality question generatio…
Ultralarge polarization in ferroelectric hafnia-based thin films
Han Wu, Kun Lin, Qinghua Zhang +15
Hafnia-based ferroelectrics have become a valuable class of electronic functional materials at the nanoscale, showing great potential for next-generation memory and logic devices.…
HI Depletion Begins Well Beyond the Virial Radius: A FAST Stacking Study of 36 Galaxy Clusters to 5R200
Cheng Cheng, Chuan-Peng Zhang, Edo Ibar +10
The paper uses FAST and DESI data to stack HI spectra of galaxies in 36 nearby clusters, showing that neutral hydrogen content is already depleted out to five times the virial radi…
Human-centric Spatio-Temporal Video Grounding With Visual Transformers
Zongheng Tang, Yue Liao, Si Liu +5
In this work, we introduce a novel task - Humancentric Spatio-Temporal Video Grounding (HC-STVG). Unlike the existing referring expression tasks in images or videos, by focusing on…
Trapping electrons in a room-temperature microwave Paul trap
Clemens Matthiesen, Qian Yu, Jinen Guo +2
We demonstrate trapping of electrons in a millimeter-sized quadrupole Paul trap driven at 1.6~GHz in a room-temperature ultra-high vacuum setup. Cold electrons are introduced into…
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMs
Hongfei Xia, Hongru Wang, Zeming Liu +3
Large Language Models (LLMs) have exhibited great performance in autonomously calling various tools in external environments, leading to better problem solving and task automation…
Hierarchical SVG Tokenization: Learning Compact Visual Programs for Scalable Vector Graphics Modeling
Ximing Xing, Ziteng Xue, Zhenxi Li +8
Recent large language models have shifted SVG generation from differentiable rendering optimization to autoregressive program synthesis. However, existing approaches still rely on…
SketchSampler: Sketch-based 3D Reconstruction via View-dependent Depth Sampling
Chenjian Gao, Qian Yu, Lu Sheng +2
Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape. Existing works…
Gating-adapted Wavelet Multiresolution Analysis for Exposure Sequence Modeling in CTR prediction
Xiaoxiao Xu, Zhiwei Fang, Qian Yu +7
The exposure sequence is being actively studied for user interest modeling in Click-Through Rate (CTR) prediction. However, the existing methods for exposure sequence modeling brin…
Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding
Yi Xin, Qi Qin, Siqi Luo +29
We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by util…
Large Scale Scene Text Verification with Guided Attention
Dafang He, Yeqing Li, Alexander Gorban +5
Many tasks are related to determining if a particular text string exists in an image. In this work, we propose a new framework that learns this task in an end-to-end way. The frame…
Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training
Ximing Xing, Chuang Wang, Haitao Zhou +4
Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance o…
Numerical Investigations of Electron Dynamics in a Linear Paul Trap
Andris Huang, Edith Hausten, Qian Yu +6
Trapped electrons have emerged as an interesting platform for quantum information processing due to their light mass, two-level spin states, and potential for fully electronic mani…
Exponential Euler method for stiff SDEs driven by fractional Brownian motion
Haozhe Chen, Zhaotong Shen, Qian Yu
In a recent paper by Kamrani et al. (2024), exponential Euler method for stiff stochastic differential equations with additive fractional Brownian noise was discussed, and the conv…
Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation
Qinghe Ma, Jian Zhang, Zekun Li +3
Large pretrained visual foundation models exhibit impressive general capabilities. However, the extensive prior knowledge inherent in these models can sometimes be a double-edged s…
Crossbar-Net: A Novel Convolutional Network for Kidney Tumor Segmentation in CT Images
Qian Yu, Yinghuan Shi, Jinquan Sun +3
Due to the irregular motion, similar appearance and diverse shape, accurate segmentation of kidney tumor in CT images is a difficult and challenging task. To this end, we present a…
Towards Automatic Power Battery Detection: New Challenge, Benchmark Dataset and Baseline
Xiaoqi Zhao, Youwei Pang, Zhenyu Chen +5
We conduct a comprehensive study on a new task named power battery detection (PBD), which aims to localize the dense cathode and anode plates endpoints from X-ray images to evaluat…
Coded Fourier Transform
Qian Yu, Mohammad Ali Maddah-Ali, A. Salman Avestimehr
We consider the problem of computing the Fourier transform of high-dimensional vectors, distributedly over a cluster of machines consisting of a master node and multiple worker nod…
VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
Guotao Liang, Zhangcheng Wang, Chuang Wang +6
Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains c…
TrackGo: A Flexible and Efficient Method for Controllable Video Generation
Haitao Zhou, Chuang Wang, Rui Nie +4
Recent years have seen substantial progress in diffusion-based controllable video generation. However, achieving precise control in complex scenarios, including fine-grained object…
Polynomially Coded Regression: Optimal Straggler Mitigation via Data Encoding
Songze Li, Seyed Mohammadreza Mousavi Kalan, Qian Yu +2
We consider the problem of training a least-squares regression model on a large dataset using gradient descent. The computation is carried out on a distributed system consisting of…
Review-based Question Generation with Adaptive Instance Transfer and Augmentation
Qian Yu, Lidong Bing, Qiong Zhang +2
Online reviews provide rich information about products and service, while it remains inefficient for potential consumers to exploit the reviews for fulfilling their specific inform…
Minimax Regret of Switching-Constrained Online Convex Optimization: No Phase Transition
Lin Chen, Qian Yu, Hannah Lawrence +1
We study the problem of switching-constrained online convex optimization (OCO), where the player has a limited number of opportunities to change her action. While the discrete anal…
Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter
Jinglong Wang, Xiawei Li, Jing Zhang +5
The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial l…
Existence and Hölder continuity conditions for self-intersection local time of Rosenblatt process
Qian Yu, Guangjun Shen, Xiuwei Yin
We consider the existence and Hölder continuity conditions for the self-intersection local time of Rosenblatt process. Moreover, we study the cases of intersection local time and…
Orthogonal Annotation Benefits Barely-supervised Medical Image Segmentation
Heng Cai, Shumeng Li, Lei Qi +3
Recent trends in semi-supervised learning have significantly boosted the performance of 3D semi-supervised medical image segmentation. Compared with 2D images, 3D medical volumes i…
An Incremental Update Framework for Online Recommenders with Data-Driven Prior
Chen Yang, Jin Chen, Qian Yu +10
Online recommenders have attained growing interest and created great revenue for businesses. Given numerous users and items, incremental update becomes a mainstream paradigm for le…
DCRNN: A Deep Cross approach based on RNN for Partial Parameter Sharing in Multi-task Learning
Jie Zhou, Qian Yu
In recent years, DL has developed rapidly, and personalized services are exploring using DL algorithms to improve the performance of the recommendation system. For personalized ser…
Product Question Answering in E-Commerce: A Survey
Yang Deng, Wenxuan Zhang, Qian Yu +1
Product question answering (PQA), aiming to automatically provide instant responses to customer's questions in E-Commerce platforms, has drawn increasing attention in recent years.…
Transport in a Single Self-Doped Nanocrystal
Hongyue Wang, Emmanuel Lhuillier, Qian Yu +4
Addressing the optical properties of a single nanoparticle in the infrared is particularly challenging, thus alternative methods for characterizing the conductance spectrum of nano…
GA-Sketching: Shape Modeling from Multi-View Sketching with Geometry-Aligned Deep Implicit Functions
Jie Zhou, Zhongjin Luo, Qian Yu +2
Sketch-based shape modeling aims to bridge the gap between 2D drawing and 3D modeling by providing an intuitive and accessible approach to create 3D shapes from 2D sketches. Howeve…
GenesisTex: Adapting Image Denoising Diffusion to Texture Space
Chenjian Gao, Boyan Jiang, Xinghui Li +2
We present GenesisTex, a novel method for synthesizing textures for 3D geometries from text descriptions. GenesisTex adapts the pretrained image diffusion model to texture space by…
HiNet: Novel Multi-Scenario & Multi-Task Learning with Hierarchical Information Extraction
Jie Zhou, Xianshuai Cao, Wenhao Li +4
Multi-scenario & multi-task learning has been widely applied to many recommendation systems in industrial applications, wherein an effective and practical approach is to carry out…
The Exact Rate-Memory Tradeoff for Caching with Uncoded Prefetching
Qian Yu, Mohammad Ali Maddah-Ali, A. Salman Avestimehr
We consider a basic cache network, in which a single server is connected to multiple users via a shared bottleneck link. The server has a database of files (content). Each user has…
Finding the Optimal Demodulator Under Implementation Constraints
Qian Yu
The common approach of designing a communication device is to maximize a well-defined objective function, e.g., the channel capacity and the cut-off rate. We propose easy-to-implem…
Strong solutions to SDEs with singular drifts driven by fractional Brownian motions
Jiazhen Gu, Qian Yu
In this paper, we establish the strong well-posedness of SDEs with merely integrable time-dependent drifts driven by fractional Brownian motions with Hurst parameter H<1/2. Our res…
The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
Muyang Qiu, Jian Zhang, Lei Qi +3
Despite the recent success of domain generalization in medical image segmentation, voxel-wise annotation for all source domains remains a huge burden. Semi-supervised domain genera…
Deep Learning for Cross-Border Transaction Anomaly Detection in Anti-Money Laundering Systems
Qian Yu, Zhen Xu, Zong Ke
In the context of globalization and the rapid expansion of the digital economy, anti-money laundering (AML) has become a crucial aspect of financial oversight, particularly in cros…
3D-Printed Micro Ion Trap Technology for Scalable Quantum Information Processing
Shuqi Xu, Xiaoxing Xia, Qian Yu +7
Trapped-ion applications, such as in quantum information, precision measurements, optical clocks, and mass spectrometry, rely on specialized high-performance ion traps. The latter…
Limit laws for functionals of self-intersection symmetric alpha-stable processes
Minhao Hong, Qian Yu
In this paper, we prove two limit laws for functionals of self-intersection symmetric alpha-stable processes with alpha\in(1,2). The results are obtained based on the method of mom…
Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentation
Yinghuan Shi, Jian Zhang, Tong Ling +5
In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty. In this paper, we investigate a novel…
Harmonic Coding: An Optimal Linear Code for Privacy-Preserving Gradient-Type Computation
Qian Yu, A. Salman Avestimehr
We consider the problem of distributedly computing a general class of functions, referred to as gradient-type computation, while maintaining the privacy of the input dataset. Gradi…
Uniform-in-Time Smoluchowski-Kramers Approximation in Total Variation for Fractional SDEs
Qian Yu, Jiaxin Zha
Let be a one-dimensional fractional Brownian motion with Hurst index . We study the small-mass limit of the kinetic equation \[ dX_t^μ=Y_t^μ\,dt,\qquad μ\,dY_t^μ…
Network Transplanting (extended abstract)
Quanshi Zhang, Yu Yang, Qian Yu +1
This paper focuses on a new task, i.e., transplanting a category-and-task-specific neural network to a generic, modular network without strong supervision. We design a functionally…