Publications (100)
Dynamic Momentum Recalibration in Online Gradient Learning
Zhipeng Yao, Rui Yu, Guisong Chang +3
Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insuffici…
Computer-Using World Model
Yiming Guan, Rui Yu, John Zhang +15
Agents operating in complex software environments benefit from reasoning about the consequences of their actions, as even a single incorrect user interface (UI) operation can derai…
Nodal Manifolds Bounded by Exceptional Points on Non-Hermitian Honeycomb Lattices and Electrical-Circuit Realizations
Kaifa Luo, Jiajin Feng, Y. X. Zhao +1
Topological semimetals feature a diversity of nodal manifolds including nodal points, various nodal lines and surfaces, and recently novel quantum states in non-Hermitian systems h…
Unleashing the Potential of Mamba: Boosting a LiDAR 3D Sparse Detector by Using Cross-Model Knowledge Distillation
Rui Yu, Runkai Zhao, Jiagen Li +3
The LiDAR 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving. However, many existing LiDAR det…
Spectroscopic evidence for bulk-band inversion and three-dimensional massive Dirac fermions in ZrTe5
Zhi-Guo Chen, R. Y. Chen, R. D. Zhong +8
Three-dimensional topological insulators (3D TIs) represent novel states of quantum matters in which surface states are protected by time-reversal symmetry and an inversion occurs…
NeRF-Enhanced Outpainting for Faithful Field-of-View Extrapolation
Rui Yu, Jiachen Liu, Zihan Zhou +1
In various applications, such as robotic navigation and remote visual assistance, expanding the field of view (FOV) of the camera proves beneficial for enhancing environmental perc…
Evidence for a Dirac nodal-line semimetal in SrAs
Shichao Li, Zhaopeng Guo, Dongzhi Fu +11
Dirac nodal-line semimetals with the linear bands crossing along a line or loop, represent a new topological state of matter. Here, by carrying out magnetotransport measurements an…
From Nodal Chain Semimetal To Weyl Semimetal in HfC
Rui Yu, Quansheng Wu, Zhong Fang +1
Based on first-principles calculations and effective model analysis, we propose that the WC-type HfC, in the absence of spin-orbit coupling (SOC), can host a three-dimensional noda…
First Principles Studies on 3-Dimentional Strong Topological Insulators: Bi2Te3, Bi2Se3 and Sb2Te3
Wei Zhang, Rui Yu, Hai-Jun Zhang +2
Bi2Se3, Bi2Te3 and Sb2Te3 compounds are recently predicted to be 3-dimentional (3D) strong topological insulators. In this paper, based on ab-initio calculations, we study in detai…
Gluonic evanescent operators: two-loop anomalous dimensions
Qingjun Jin, Ke Ren, Gang Yang +1
Evanescent operators are a special class of operators that vanish in four-dimensional spacetime but are non-zero in dimensions. In this paper, we continue our systematic…
Divide and Fuse: A Re-ranking Approach for Person Re-identification
Rui Yu, Zhichao Zhou, Song Bai +1
As re-ranking is a necessary procedure to boost person re-identification (re-ID) performance on large-scale datasets, the diversity of feature becomes crucial to person reID for it…
Future Does Matter: Boosting 3D Object Detection with Temporal Motion Estimation in Point Cloud Sequences
Rui Yu, Runkai Zhao, Cong Nie +3
Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limit…
Non-Hermitian Structure and Exceptional Points in Yang-Mills Theory from Analytic Continuation of Nc
Qingjun Jin, Ke Ren, Gang Yang +1
We show that analytic continuation of the number of colors, Nc, naturally endows Yang-Mills theory with a non-Hermitian structure. By examining the spectrum of the dilatation opera…
Reward Models in Deep Reinforcement Learning: A Survey
Rui Yu, Shenghua Wan, Yucen Wang +4
In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are intr…
Gluonic evanescent operators: classification and one-loop renormalization
Qingjun Jin, Ke Ren, Gang Yang +1
Evanescent operators are a special class of operators that vanish classically in four-dimensional spacetime, while in general dimensions they are non-zero and are expected to have…
FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data
Bing Han, Chen Zhu, Dong Han +22
Vision-driven field monitoring is central to digital agriculture, yet models built on general-domain pretrained backbones often fail to generalize across tasks, owing to the intera…
UDQL: Bridging The Gap between MSE Loss and The Optimal Value Function in Offline Reinforcement Learning
Yu Zhang, Rui Yu, Zhipeng Yao +3
The Mean Square Error (MSE) is commonly utilized to estimate the solution of the optimal value function in the vast majority of offline reinforcement learning (RL) models and has a…
On the moderate deviation principles in the sparse multi-type ErdÅs Rényi random graph
Rui Yu, Wen Sun
This paper investigate the sparse multi-type ErdÅs Rényi random graphs studied in Söderberg~\cite{soderberg2002general} and also Bollobás et al.~\cite{bollobas2007phase}. Altho…
Topological nodal states in circuit lattice
Kaifa Luo, Rui Yu, Hongming Weng
The search for artificial structure with tunable topological properties is an interesting research direction of today's topological physics. Here, we introduce a scheme to realize…
Elucidating Representation Degradation Problem in Diffusion Model Training
Zhipeng Yao, Dazhou Li, Zitong Zhang +6
Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As nois…
Topological Aspect and Quantum Magnetoresistance of -AgTe
Wei Zhang, Rui Yu, Wanxiang Feng +4
To explain the unusual non-saturating linear magnetoresistance observed in silver chalcogenides, the quantum scenario has been proposed based on the assumption of gapless linear en…
Towards Robust Human Trajectory Prediction in Raw Videos
Rui Yu, Zihan Zhou
Human trajectory prediction has received increased attention lately due to its importance in applications such as autonomous vehicles and indoor robots. However, most existing meth…
Top2Pano: Learning to Generate Indoor Panoramas from Top-Down View
Zitong Zhang, Suranjan Gautam, Rui Yu
Generating immersive 360° indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to…
Highly-efficient spintronic terahertz emitter enabled by metal-dielectric photonic crystal
Zheng Feng, Rui Yu, Yu Zhou +9
Spintronic terahertz (THz) emitter provides the advantages such as apparently broader spectrum, significantly lower cost, and more flexibility in compared with the commercial THz e…
Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval
Zhichuan Wang, Yang Zhou, Zhe Liu +5
Open-set 3D object retrieval (3DOR) is an emerging task aiming to retrieve 3D objects of unseen categories beyond the training set. Existing methods typically utilize all modalitie…
From Detection to Association: Learning Discriminative Object Embeddings for Multi-Object Tracking
Yuqing Shao, Yuchen Yang, Rui Yu +5
End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong dete…
Computer-Aided Layout Generation for Building Design: A Review
Jiachen Liu, Yuan Xue, Haomiao Ni +3
Generating realistic building layouts for automatic building design has been studied in both the computer vision and architecture domains. Traditional approaches from the architect…
4D spinless topological insulator in a periodic electric circuit
Rui Yu, Y. X. Zhao, Andreas P. Schnyder
According to the mathematical classification of topological band structures, there exist a number of fascinating topological states in dimensions larger than three with exotic boun…
Topologically protected Dirac plasmons in graphene
Deng Pan, Rui Yu, Hongxing Xu +1
Topological optical states exhibit unique immunity to defects and the ability to propagate without losses rendering them ideal for photonic applications.A powerful class of such st…
Non-abelian gauge fields in circuit systems
Jiexiong Wu, Zhu Wang, Yuanchuan Biao +8
Circuits can provide a platform to study novel physics and have been used, for example, to explore various topological phases. Gauge fields-particularly, non-Abelian gauge fields-c…
Hydrogen-induced magnetism in graphene: a simple effective model description
Shuai Li, Rui Yu, Jin-Hua Gao +1
Hydrogen adatoms induced magnetic moment on graphene has been observed in atomic scale in a recent experiment [Gonzalez-Herrero et al., Science 352, 437 (2016)]. Here, we demonstra…
Deep-Person: Learning Discriminative Deep Features for Person Re-Identification
Xiang Bai, Mingkun Yang, Tengteng Huang +3
Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor. However, the spatial context b…
MoreStyle: Relax Low-frequency Constraint of Fourier-based Image Reconstruction in Generalizable Medical Image Segmentation
Haoyu Zhao, Wenhui Dong, Rui Yu +3
The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets. To address the challenge of…
Partonic quasidistributions in two-dimensional QCD
Yu Jia, Shuangran Liang, Xiaonu Xiong +1
As a sequel of our preceding work [1] we carry out a comprehensive comparative study between the quasi parton distribution functions (PDFs), distribution amplitudes (DAs) and their…
-Orbital Topological Insulator and Semimetal in Antifluorite CuS Family: Contrasting Spin Helicities, Nodal Box, and Hybrid Surface States
Xian-Lei Sheng, Zhi-Ming Yu, Rui Yu +2
We reveal a class of three-dimensional -orbital topological materials in the antifluorite CuS family. Derived from the unique properties of low-energy states, their…
Solving Jigsaw Puzzles with Linear Programming
Rui Yu, Chris Russell, Lourdes Agapito
We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles. We formulate jigsaw solving as a set of successive global convex relaxations of the stan- dar…
Quantized Anomalous Hall Effect in Magnetic Topological Insulators
Rui Yu, Wei Zhang, H. J. Zhang +3
The Hall effect, the anomalous Hall effect and the spin Hall effect are fundamental transport processes in solids arising from the Lorentz force and the spin-orbit coupling respect…
Gauge-invariant decomposition of meson energy in two-dimensional QCD
Yu Jia, Rui Yu, Xiaonu Xiong
This work is driven by our curiosity towards some basic questions in QCD: how is the energy of a moving hadron partitioned among different gauge-invariant sectors in QCD Hamiltonia…
Near-the-origin divergence of Klein-Gordon wave functions for hydrogen-like atoms and operator product expansion
Yingsheng Huang, Yu Jia, Rui Yu
There have been some long-standing puzzles related to the Coulomb solutions of the Klein-Gordon and Dirac equations, namely how to understand the physics underlying the weakly dive…
Spatial-aware Attention Generative Adversarial Network for Semi-supervised Anomaly Detection in Medical Image
Zerui Zhang, Zhichao Sun, Zelong Liu +4
Medical anomaly detection is a critical research area aimed at recognizing abnormal images to aid in diagnosis.Most existing methods adopt synthetic anomalies and image restoration…
Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading
Qi Liu-Yin, Rui Yu, Lourdes Agapito +2
We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera. Unlike previo…
Efficient Dual-domain Image Dehazing with Haze Prior Perception
Lirong Zheng, Yanshan Li, Rui Yu +1
Transformers offer strong global modeling for single-image dehazing but come with high computational costs. Most methods rely on spatial features to capture long-range dependencies…
Topological Node-Line Semimetal in Compressed Black Phosphorus
Jianzhou Zhao, Rui Yu, Hongming Weng +1
Based on first-principles calculations and tight-binding model analysis, we propose that black phosphorus (BP) can host a three-dimensional topological node-line semimetal state un…
An equivalent expression of Z2 Topological Invariant for band insulators using Non-Abelian Berry's connection
Rui Yu, Xiao Liang Qi, Andrei Bernevig +2
We introduce a new expression for the Z2 topological invariant of band insulators using non- Abelian Berry's connection. Our expression can identify the topological nature of a gen…
Signal Processing Meets SGD: From Momentum to Filter
Zhipeng Yao, Rui Yu, Guisong Chang +3
In deep learning, stochastic gradient descent (SGD) and its momentum-based variants are widely used for optimization. However, the internal dynamics of these methods remain underex…
Common-agency Games for Multi-Objective Test-Time Alignment
Baiting Chen, Tong Zhu, Rui Yu +1
Aligning large language models (LLMs) with human preferences is inherently multi-objective: different users and evaluation criteria impose heterogeneous and often conflicting requi…
Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing
Lirong Zheng, Yanshan Li, Rui Yu +1
Image dehazing is crucial for reliable visual perception, yet it remains highly challenging under real-world non-uniform haze conditions. Although Transformer-based methods excel a…
Cascade Transformers for End-to-End Person Search
Rui Yu, Dawei Du, Rodney LaLonde +4
The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, a…
Interaction-driven Quantum Anomalous Hall Effect in Halogenated Hematite Nanosheets
Qi-Feng Liang, Jian Zhou, Rui Yu +2
Based on first-principle calculations and model analysis, we show that the quantum anomalous Hall (QAH) insulating phase can be realized in the functionalized hematite (…
Feasibility of Interactive 3D Map for Remote Sighted Assistance
Jingyi Xie, Rui Yu, Sooyeon Lee +3
Remote sighted assistance (RSA) has emerged as a conversational assistive technology, where remote sighted workers, i.e., agents, provide real-time assistance to users with vision…
JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
Jiaxin Song, Yixu Wang, Jie Li +4
Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them incre…
Gluonic evanescent operators: negative-norm states and complex anomalous dimensions
Qingjun Jin, Ke Ren, Gang Yang +1
In this paper, we build on our previous work to further investigate the role of evanescent operators in gauge theories, with a particular focus on their contribution to violations…
Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing
Rui Yu, Yifeng Li, Wenpeng Lu +1
In natural language processing (NLP), the context of a word or sentence plays an essential role. Contextual information such as the semantic representation of a passage or historic…
BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining
Jie Hao, Rui Yu, Wei Zhang +3
Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approac…
From Lossy to Verified: A Provenance-Aware Tiered Memory for Agents
Qiming Zhu, Shunian Chen, Rui Yu +2
Long-horizon agents often compress interaction histories into write-time summaries. This creates a fundamental write-before-query barrier: compression decisions are made before the…
Boundary Flat Bands with Topological Spin Textures Protected by Sub-chiral Symmetry
Yijie Mo, Xiao-Jiao Wang, Rui Yu +1
Chiral symmetry plays an indispensable role in topological classifications as well as in the understanding of the origin of bulk or boundary flat bands. The conventional definition…
Meson-meson scattering in two-dimensional QCD
Guo-Ying Chen, Yingsheng Huang, Yu Jia +1
We extend the formalism pioneered by Callan, Coote and Gross to investigate the meson-meson scattering within the framework of 't Hooft model, i.e., the two-dimensional QCD in the…
Light-cone and quasi generalized parton distributions in the 't Hooft model
Yu Jia, Zhewen Mo, Xiaonu Xiong +1
We present a comprehensive study of the light-cone generalized parton distribution (GPD) and quasi-GPD of a flavor-neutral meson in the 't Hooft model, {\it i.e.}, two-dimensional…
Attention-Guided Perturbation Network for Industrial Anomaly Detection
Tingfeng Huang, Weijia Kong, Yuxuan Cheng +8
In unsupervised image anomaly detection, reconstruction-based methods learn normal patterns for data reconstruction, but often undesirably reconstruct anomalous regions at inferenc…
Realization of a Hopf insulator in circuit systems
Zhu Wang, Xu-Tao Zeng, Yuanchuan Biao +2
Three-dimensional (3D) two-band Hopf insulators are a paradigmatic example of topological phases beyond the topological classifications based on powerful methods like -theory an…
Data-Driven Distributed State Estimation and Behavior Modeling in Sensor Networks
Rui Yu, Zhenyuan Yuan, Minghui Zhu +1
Nowadays, the prevalence of sensor networks has enabled tracking of the states of dynamic objects for a wide spectrum of applications from autonomous driving to environmental monit…
Magnetic-field-induced electronic instability of Weyl-like fermions in compressed black phosphorus
Lixuan Zheng, Kaifa Luo, Zeliang Sun +14
Revealing the role of Coulomb interaction in topological semimetals with Dirac/Weyl-like band dispersion shapes a new frontier in condensed matter physics. Topological node-line se…
FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making
Yucen Wang, Rui Yu, Shenghua Wan +2
Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrat…
Deciphering the coalescence behavior of Coulomb-Schrödinger atomic wave functions from an operator product expansion
Yingsheng Huang, Yu Jia, Rui Yu
We revisit the coalescence behavior of the atomic Schrödinger wave functions from the angle of an operator product expansion (OPE) within the nonrelativistic Coulomb-Schrödinger…
Topological Nodal Line Semimetal and Dirac Semimetal State in Antiperovskite CuPdN
Rui Yu, Hongming Weng, Zhong Fang +2
Based on first-principles calculation and effective model analysis, we propose that the cubic antiperovskite material CuPdN can host a three-dimensional (3D) topological nodal…
Large Fermi-arc and robust Weyl semimetal phase in AgS
Zhenwei Wang, Kaifa Luo, Jianzhou Zhao +1
Three-dimensional Dirac and Weyl semimetals have attracted widespread interest in condensed matter physics and material science. Here, based on first-principles calculations and sy…
Exotic Node Line in ternary MgSrSi-type crystals
Jinling Lian, Lixian Yu, Qi-Feng Liang +3
Node line (NL) band-touchings protected by mirror symmetry (named as -NL), the product of inversion and time reversal symmetry (-NL), or nonsymmorphic symmet…
Quantum anomalous Hall effect and related topological electronic states
Hongming Weng, Rui Yu, Xiao Hu +2
Over a long period of exploration, the successful observation of quantized version of anomalous Hall effect (AHE) in thin film of magnetically-doped topological insulator completed…
Building AI Literacy at Home: How Families Navigate Children's Self-Directed Learning with AI
Jingyi Xie, Chuhao Wu, Ge Wang +4
As generative AI becomes embedded in children's learning spaces, families face new challenges in guiding its use. Middle childhood (ages 7-13) is a critical stage where children se…
Determine the chirality of Weyl fermions from the circular dichroism spectra of time-dependent ARPES
Rui Yu, Hongming Weng, Zhong Fang +2
We show that the intensity of pumped states near Weyl point is different when pumped with left- and right-handed circular polarized light, which leads to a special circular dichroi…
Dirac semimetal in type IV magnetic space group
Guiyuan Hua, Simin Nie, Zhida Song +3
Analogues of the elementary particles, Dirac fermions in condensed matter have received extensive attention for both scientific interest and device applications. In this work, we g…
Topological Insulator to Dirac Semimetal Transition Driven by Sign Change of Spin-Orbit Coupling in Thallium Nitride
Xian-Lei Sheng, Zhijun Wang, Rui Yu +3
Based on the first-principles calculations, we reveal that TlN, a simple binary compound with Wurtzite structure, is a three-dimensional (3D) topological insulator (TI) with effect…
PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes
Bin Tan, Rui Yu, Yujun Shen +1
This paper presents PlanarSplatting, an ultra-fast and accurate surface reconstruction approach for multiview indoor images. We take the 3D planes as the main objective due to thei…
Symmetry-enforced three-dimensional Dirac phononic crystals
Xiangxi Cai, Liping Ye, Chunyin Qiu +4
Dirac semimetals, the materials featured with discrete linearly crossing points (called Dirac points) between four bands, are critical states of topologically distinct phases. Such…
Enhancing the Travel Experience for People with Visual Impairments through Multimodal Interaction: NaviGPT, A Real-Time AI-Driven Mobile Navigation System
He Zhang, Nicholas J. Falletta, Jingyi Xie +4
Assistive technologies for people with visual impairments (PVI) have made significant advancements, particularly with the integration of artificial intelligence (AI) and real-time…
SF-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Question Answering
Rui Yu, Tianyi Wang, Ruixia Liu +1
Efficient question-answering (QA) over extensive scientific literature is essential for evidence-based engineering decision-making. Retrieval-augmented generation (RAG) is increasi…
Topological Node-Line Semimetal in Three Dimensional Graphene Networks
Hongming Weng, Yunye Liang, Qiunan Xu +4
Graphene, a two dimensional (2D) carbon sheet, acquires many of its amazing properties from the Dirac point nature of its electronic structures with negligible spin-orbit coupling.…
Fairness-Aware Graph Representation Learning with Limited Demographic Information
Zichong Wang, Zhipeng Yin, Liping Yang +4
Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning meth…
Pseudo-Spin, Real-Spin and Spin Polarization of Photo-emitted Electrons
Rui Yu, Hongming Weng, Zhong Fang +1
In this work, we discuss the connections between pseudo spin, real spin of electrons in material and spin polarization of photo-emitted electrons out of material. By investigating…
Topological states of non-Dirac electrons on triangular lattice
Qi-Feng Liang, Rui Yu, Jian Zhou +1
We demonstrate the possibility of topological states for non-Dirac electrons. Specifically it is shown that, because of the crystal symmetry and time reversal symmetry,…
Near-the-origin divergence of Dirac wave functions of hydrogen and operator product expansion
Yingsheng Huang, Yu Jia, Rui Yu
There is a long-standing puzzle concerning the Coulomb solutions of the Dirac equation, i.e., what is the physics governing the weakly divergent near-the-origin behavior of the Dir…
Is Yang-Mills Theory Unitary in Fractional Spacetime Dimensions?
Qingjun Jin, Ke Ren, Gang Yang +1
We present concrete evidence that Yang-Mills theory exhibits non-unitarity in non-integer spacetime dimensions. This violation of unitarity stems from evanescent operators that, wh…
Hidden-symmetry-enforced nexus points of nodal lines in layer-stacked dielectric photonic crystals
Zhongfei Xiong, Ruo-Yang Zhang, Rui Yu +2
It was recently demonstrated that the connectivities of bands emerging from zero frequency in dielectric photonic crystals are distinct from their electronic counterparts with the…
Beyond Visual Perception: Insights from Smartphone Interaction of Visually Impaired Users with Large Multimodal Models
Jingyi Xie, Rui Yu, He Zhang +3
Large multimodal models (LMMs) have enabled new AI-powered applications that help people with visual impairments (PVI) receive natural language descriptions of their surroundings t…
A Human-Centred AI System for Multi-Actor Planning and Collaboration in Family Learning
Si Chen, Jingyi Xie, Yao Li +8
Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Despite growing interest in AI tutors, most existing…
A graphical representation of gluonic operators
Qingjun Jin, Ke Ren, Gang Yang +1
Composite local operators are central to effective field theories (EFTs), as they define interaction vertices in effective Lagrangians and play a fundamental role in investigating…
Model Hamiltonian for topological Kondo insulator SmB6
Rui Yu, HongMing Weng, Xiao Hu +2
Starting from the kp method in combination with first-principles calculations, we systematically derive the effective Hamiltonians that capture the low energy band structures of re…
Topological Nodal Line Semimetals in CaP3 family of materials
Qiunan Xu, Rui Yu, Zhong Fang +2
We propose that CaP3 family of materials, which include CaP3, CaAs3, SrP3, SrAs3 and BaAs3 can host a three-dimensional topological nodal line semimetal states. Based on first-prin…
Node-Surface and Node-Line Fermions From Nonsymmorphic Lattice Symmetries
Qi-Feng Liang, Jian Zhou, Rui Yu +2
We propose a kind of novel topological quantum state of semimetals in a quasi-one-dimensional (1D) crystals BaMX (M = V, Nb or Ta; X = S or Se) family by using symmetry analysi…
Unimodal-driven Distillation in Multimodal Emotion Recognition with Dynamic Fusion
Jiagen Li, Rui Yu, Huihao Huang +1
Multimodal Emotion Recognition in Conversations (MERC) identifies emotional states across text, audio and video, which is essential for intelligent dialogue systems and opinion ana…
First-principles study on the bulk and two-dimensional structures of AMnBi(A =K, Rb, Cs)-family materials
Ziming Zhu, Chunyan Liao, Si Li +6
Magnetic materials with high mobilities are intriguing subject of research from both fundamental and application perspectives. Based on first-principle calculations, we investigate…
Hard-Aware Point-to-Set Deep Metric for Person Re-identification
Rui Yu, Zhiyong Dou, Song Bai +3
Person re-identification (re-ID) is a highly challenging task due to large variations of pose, viewpoint, illumination, and occlusion. Deep metric learning provides a satisfactory…
"Learning Together": AI-Mediated Support for Parental Involvement in Everyday Learning
Yao Li, Jingyi Xie, Ya-Fang Lin +5
Family learning takes place in everyday routines where children and caregivers read, practice, and develop new skills together. Although AI is increasingly present in learning envi…
Emerging Practices for Large Multimodal Model (LMM) Assistance for People with Visual Impairments: Implications for Design
Jingyi Xie, Rui Yu, He Zhang +3
People with visual impairments perceive their environment non-visually and often use AI-powered assistive tools to obtain textual descriptions of visual information. Recent large v…
WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising
Haoyu Zhao, Yuliang Gu, Zhou Zhao +3
In clinical examinations and diagnoses, low-dose computed tomography (LDCT) is crucial for minimizing health risks compared with normal-dose computed tomography (NDCT). However, re…
DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model
Rui Yu, Xianghang Zhang, Runkai Zhao +2
End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive foc…
Progressive Feature Fusion Network for Enhancing Image Quality Assessment
Kaiqun Wu, Xiaoling Jiang, Rui Yu +4
Image compression has been applied in the fields of image storage and video broadcasting. However, it's formidably tough to distinguish the subtle quality differences between those…
Topological phases in pyrochlore thallium niobate TlNbO
Wei Zhang, Kaifa Luo, Zhendong Chen +4
The discovery of new topological electronic materials brings a chance to uncover novel physics and plays a key role in observing and controlling various intriguing phenomena. Up to…
Reinforcing VLAs in Task-Agnostic World Models
Yucen Wang, Rui Yu, Fengming Zhang +5
Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly…
Towards In-the-wild 3D Plane Reconstruction from a Single Image
Jiachen Liu, Rui Yu, Sili Chen +2
3D plane reconstruction from a single image is a crucial yet challenging topic in 3D computer vision. Previous state-of-the-art (SOTA) methods have focused on training their system…