Publications (53)
Structured Click Control in Transformer-based Interactive Segmentation
Long Xu, Yongquan Chen, Rui Huang +2
Click-point-based interactive segmentation has received widespread attention due to its efficiency. However, it's hard for existing algorithms to obtain precise and robust response…
DMMRL: Disentangled Multi-Modal Representation Learning via Variational Autoencoders for Molecular Property Prediction
Long Xu, Junping Guo, Jianbo Zhao +2
Molecular property prediction constitutes a cornerstone of drug discovery and materials science, necessitating models capable of disentangling complex structure-property relationsh…
An Efficient Spatial-Temporal Trajectory Planner for Autonomous Vehicles in Unstructured Environments
Zhichao Han, Yuwei Wu, Tong Li +8
As a core part of autonomous driving systems, motion planning has received extensive attention from academia and industry. However, real-time trajectory planning capable of spatial…
Towards Efficient Trajectory Generation for Ground Robots beyond 2D Environment
Jingping Wang, Long Xu, Haoran Fu +5
With the development of robotics, ground robots are no longer limited to planar motion. Passive height variation due to complex terrain and active height control provided by specia…
Deep Learning Eliminates Massive Dust Storms from Images of Tianwen-1
Hongyu Li, Jia Li, Xin Ren +1
Dust storms may remarkably degrade the imaging quality of Martian orbiters and delay the progress of mapping the global topography and geomorphology. To address this issue, this pa…
DCVC-MV: Deep Contextual Multiview Video Compression with Efficient Inter-View Prediction
Xihua Sheng, Yingwen Zhang, Long Xu +1
Multiview video is a key format for 3D applications such as free-viewpoint broadcasting and virtual reality, yet its large data volume poses significant challenges for efficient st…
Optimal Selective Orientation of Chiral Molecules Using Femtosecond Laser Pulses
Long Xu, Ilia Tutunnikov, Yehiam Prior +1
We present a comprehensive study of enantioselective orientation of chiral molecules excited by a pair of delayed cross-polarized femtosecond laser pulses. We show that by optimizi…
Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking
Long Xu, Peng Gao, Wen-Jia Tang +2
Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead…
Long-Lasting Orientation of Symmetric-top Molecules Excited by Two-Color Femtosecond Pulses
Long Xu, Ilia Tutunnikov, Yehiam Prior +1
Impulsive orientation of symmetric-top molecules excited by two-color femtosecond pulses is considered. In addition to the well-known transient orientation appearing immediately af…
An Efficient Trajectory Planner for Car-like Robots on Uneven Terrain
Long Xu, Kaixin Chai, Zhichao Han +4
Autonomous navigation of ground robots on uneven terrain is being considered in more and more tasks. However, uneven terrain will bring two problems to motion planning: how to asse…
Image Quality Assessment for Omnidirectional Cross-reference Stitching
Kaiwen Yu, Jia Li, Yu Zhang +2
Along with the development of virtual reality (VR), omnidirectional images play an important role in producing multimedia content with immersive experience. However, despite variou…
Echo-enhanced molecular orientation at high temperatures
Ilia Tutunnikov, Long Xu, Yehiam Prior +1
Ultrashort laser pulses are widely used for transient field-free molecular orientation -- a phenomenon important in chemical reaction dynamics, ultrafast molecular imaging, high ha…
Multi-Channel Interference in Resonance-Like Enhancement of High-Order Above-Threshold Ionization
Long Xu, Libin Fu
The intensity-dependent resonance-like enhancement phenomenon in high-order above-threshold ionization spectrum is a typical quantum effect for atoms or molecules in the intense la…
MORE: A Multilingual Document Parsing Benchmark and Evaluation
Long Xu, Binghong Wu, Tinghao Yu +6
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critica…
"Molecular waveplate" for the control of ultrashort pulses carrying orbital angular momentum
Chengqing Xu, Lixin He, Wanchen Tao +8
Ultrashort laser pulses carrying orbital angular momentum (OAM) have become essential tools in Atomic, Molecular, and Optical (AMO) studies, particularly for investigating strong-f…
Real-time Spatial-temporal Traversability Assessment via Feature-based Sparse Gaussian Process
Zhenyu Hou, Senming Tan, Zhihao Zhang +6
Terrain analysis is critical for the practical ap- plication of ground mobile robots in real-world tasks, espe- cially in outdoor unstructured environments. In this paper, we propo…
SF-TIM: A Simple Framework for Enhancing Quadrupedal Robot Jumping Agility by Combining Terrain Imagination and Measurement
Ze Wang, Yang Li, Long Xu +7
Dynamic jumping on high platforms and over gaps differentiates legged robots from wheeled counterparts. Dynamic locomotion on abrupt surfaces, as opposed to walking on rough terrai…
Droplet penetration through an inclined mesh
Long Xu, Shaoqiang Zong, Jiguang Hao +1
Droplets with different Weber numbers We impacting meshes at various inclination angles were investigated using high-speed photography. It was found that the droplet mesh penetrati…
Deep-Learning Based Super-Resolution Functional Ultrasound Imaging of Transient Brain-Wide Neurovascular Activity on a Microscopic Scale
Yang Cai, Shaoyuan Yan, Long Xu +3
Transient brain-wide neuroimaging on a microscopic scale is pivotal for brain research, yet existing imaging modalities face challenges in meeting such spatiotemporal requirements.…
SEB-Naver: A SE(2)-based Local Navigation Framework for Car-like Robots on Uneven Terrain
Xiaoying Li, Long Xu, Xiaolin Huang +6
Autonomous navigation of car-like robots on uneven terrain poses unique challenges compared to flat terrain, particularly in traversability assessment and terrain-associated kinema…
Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application
Junqi Liu, Yun Zhang, Xiaoxia Huang +2
Just Recognizable Difference (JRD) boosts coding efficiency for machine vision through visibility threshold modeling, but is currently limited to a single-task scenario. To address…
Ionization-induced Long-lasting Orientation of Symmetric-top Molecules
Long Xu, Ilia Tutunnikov, Yehiam Prior +1
We theoretically consider the phenomenon of field-free long-lasting orientation of symmetric-top molecules ionized by two-color laser pulses. The anisotropic ionization produces a…
Primitive-based Truncated Diffusion for Efficient Trajectory Generation of Differential Drive Mobile Manipulators
Long Xu, Choilam Wong, Yuhang Zhong +3
We present a learning-enhanced motion planner for differential drive mobile manipulators to improve efficiency, success rate, and optimality. For task representation encoder, we pr…
ClickAttention: Click Region Similarity Guided Interactive Segmentation
Long Xu, Shanghong Li, Yongquan Chen +3
Interactive segmentation algorithms based on click points have garnered significant attention from researchers in recent years. However, existing studies typically use sparse click…
LF-3PM: a LiDAR-based Framework for Perception-aware Planning with Perturbation-induced Metric
Kaixin Chai, Long Xu, Qianhao Wang +3
Just as humans can become disoriented in featureless deserts or thick fogs, not all environments are conducive to the Localization Accuracy and Stability (LAS) of autonomous robots…
Understanding tunneling ionization of atoms in laser fields with the essence of multiphoton absorption
Long Xu, Libin Fu
The elaborate energy and momentum spectra of ionized electrons from atoms in laser fields suggest that the ionization dynamics described by tunneling theory should be modified. Alt…
The 1st AI Children Challenge
Boyi Li, Yifan Shen, Houze Yang +7
The First AI Children Challenge aims to advance real-world applications of computer vision and AI in child healthcare, child education, and pediatrics. The 2026 CV4CHL edition feat…
PSF-based Analysis for Detecting Unresolved Wide Binaries
You Wu, Jiao Li, Chao Liu +5
Wide binaries play a crucial role in analyzing the birth environment of stars and the dynamical evolution of clusters. When wide binaries are located at greater distances, their co…
MSCoD: An Enhanced Bayesian Updating Framework with Multi-Scale Information Bottleneck and Cooperative Attention for Structure-Based Drug Design
Long Xu, Yongcai Chen, Fengshuo Liu +1
Structure-Based Drug Design (SBDD) is a powerful strategy in computational drug discovery, utilizing three-dimensional protein structures to guide the design of molecules with impr…
Hunyuan-TurboS: Advancing Large Language Models through Mamba-Transformer Synergy and Adaptive Chain-of-Thought
Tencent Hunyuan Team, Ao Liu, Botong Zhou +248
As Large Language Models (LLMs) rapidly advance, we introduce Hunyuan-TurboS, a novel large hybrid Transformer-Mamba Mixture of Experts (MoE) model. It synergistically combines Mam…
Contextual Modeling for 3D Dense Captioning on Point Clouds
Yufeng Zhong, Long Xu, Jiebo Luo +1
3D dense captioning, as an emerging vision-language task, aims to identify and locate each object from a set of point clouds and generate a distinctive natural language sentence fo…
Enantioselective chiral orientation induced by a combination of a long and a short laser pulse
Long Xu
Enantioselective orientation of chiral molecules excited by a shaped picosecond laser pulse and a delayed femtosecond pulse is considered. Using quantum mechanical simulations, we…
Solar Image Deconvolution by Generative Adversarial Network
Long Xu, Wenqing Sun, Yihua Yan +1
With Aperture synthesis (AS) technique, a number of small antennas can assemble to form a large telescope which spatial resolution is determined by the distance of two farthest ant…
Towards Adaptive Meta-Gradient Adversarial Examples for Visual Tracking
Wei-Long Tian, Peng Gao, Xiao Liu +4
In recent years, visual tracking methods based on convolutional neural networks and Transformers have achieved remarkable performance and have been successfully applied in fields s…
Enantioselective Orientation of Chiral Molecules Induced by Terahertz Pulses with Twisted Polarization
Ilia Tutunnikov, Long Xu, Robert W. Field +3
Chirality and chiral molecules are key elements in modern chemical and biochemical industries. Individual addressing, and the eventual separation of chiral enantiomers has been and…
Echoes in Unidirectionally Rotating Molecules
Long Xu, Ilia Tutunnikov, Lianrong Zhou +6
Abstract We report the experimental observation of molecular unidirectional rotation (UDR) echoes, and analyze their origin and behavior both classically and quantum mechanically.…
TopAY: Efficient Trajectory Planning for Differential Drive Mobile Manipulators via Topological Paths Search and Arc Length-Yaw Parameterization
Long Xu, Choilam Wong, Mengke Zhang +3
Differential drive mobile manipulators combine the mobility of wheeled bases with the manipulation capability of multi-joint arms, enabling versatile applications but posing consid…
Intelligence Preschool Education System based on Multimodal Interaction Systems and AI
Long Xu
Rapid progress in AI technologies has generated considerable interest in their potential to address challenges in every field and education is no exception. Improving learning outc…
Long-lasting Molecular Orientation Induced by a Single Terahertz Pulse
Long Xu, Ilia Tutunnikov, Erez Gershnabel +2
Control of molecular rotations by laser fields is an active area of research focusing on the alignment/orientation of otherwise isotropic molecular samples. Oriented molecules are…
When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding
Pingping Zhang, Jinlong Li, Kecheng Chen +6
Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language…
PA-LLaVA: A Large Language-Vision Assistant for Human Pathology Image Understanding
Dawei Dai, Yuanhui Zhang, Long Xu +4
The previous advancements in pathology image understanding primarily involved developing models tailored to specific tasks. Recent studies has demonstrated that the large vision-la…
Direct imaging of enantiomer-specific orientation dynamics in unidirectionally rotating chiral molecules
Kenta Mizuse, Ilia Tutunnikov, Long Xu +7
Selectively controlling the dynamics of molecular enantiomers underlies advances across chemistry, biology, and physics, yet direct imaging of enantiomer-specific motion has so far…
Learning to Plan Maneuverable and Agile Flight Trajectory with Optimization Embedded Networks
Zhichao Han, Long Xu, Liuao Pei +1
In recent times, an increasing number of researchers have been devoted to utilizing deep neural networks for end-to-end flight navigation. This approach has gained traction due to…
Frequency-resolved photon-electronic spectroscopy for excited state population detection
Long Xu, Hui Dong, Libin Fu
Atomic excitation to excited states in strong laser field is the key to high-order harmonic generation below ionization threshold, yet remains unclear mainly due to the lack of pro…
Enhanced Persistent Orientation of Asymmetric-Top Molecules Induced by Cross-Polarized Terahertz Pulses
Long Xu, Ilia Tutunnikov, Yehiam Prior +1
We investigate the persistent orientation of asymmetric-top molecules induced by time-delayed THz pulses that are either collinearly or cross polarized. Our theoretical and numeric…
Visual Attention on the Sun: What Do Existing Models Actually Predict?
Jia Li, Daowei Li, Kui Fu +1
Visual attention prediction is a classic problem that seems to be well addressed in the deep learning era. One compelling concern, however, gradually arise along with the rapidly g…
MST: Adaptive Multi-Scale Tokens Guided Interactive Segmentation
Long Xu, Shanghong Li, Yongquan Chen +2
Interactive segmentation has gained significant attention for its application in human-computer interaction and data annotation. To address the target scale variation issue in inte…
Decentralized Planning for Car-Like Robotic Swarm in Cluttered Environments
Changjia Ma, Zhichao Han, Tingrui Zhang +5
Robot swarm is a hot spot in robotic research community. In this paper, we propose a decentralized framework for car-like robotic swarm which is capable of real-time planning in cl…
Three Dimensional Orientation of Complex Molecules Excited by Two-Color Femtosecond Pulses
Long Xu, Ilia Tutunnikov, Yehiam Prior +1
We study the excitation of asymmetric-top (including chiral) molecules by two-color femtosecond laser pulses. In the cases of non-chiral asymmetric-top molecules excited by an orth…
Image Quality Assessment Guided Deep Neural Networks Training
Zhuo Chen, Weisi Lin, Shiqi Wang +2
For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, dig…
ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment
Mingyu Dong, Chong Xia, Mingyuan Jia +4
Humans exhibit an innate capacity to rapidly perceive and segment objects from video observations, and even mentally assemble them into structured 3D scenes. Replicating such capab…
Tracailer: An Efficient Trajectory Planner for Tractor-Trailer Robots in Unstructured Environments
Long Xu, Kaixin Chai, Boyuan An +11
The tractor-trailer robot consists of a drivable tractor and one or more non-drivable trailers connected via hitches. Compared to typical car-like robots, the addition of trailers…
Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing
Dong Zhao, Jia Li, Hongyu Li +1
Conventional CNNs-based dehazing models suffer from two essential issues: the dehazing framework (limited in interpretability) and the convolution layers (content-independent and i…