Publications (60)
Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
Hanjiang Lai, Yan Pan, Ye Liu +1
Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks. For most existing hashing methods, an image is first encode…
MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features
Bo Zhou, Jiapeng Xie, Yan Pan +2
Identifying moving objects is an essential capability for autonomous systems, as it provides critical information for pose estimation, navigation, collision avoidance, and static m…
Cool-Fusion: Fuse Large Language Models without Training
Cong Liu, Xiaojun Quan, Yan Pan +3
We focus on the problem of fusing two or more heterogeneous large language models (LLMs) to leverage their complementary strengths. One of the challenges of model fusion is high co…
ERNIE-Image Technical Report
Jiaxiang Liu, Zhida Feng, Pengyu Zou +46
We introduce ERNIE-Image, an open-source text-to-image generation model built upon an 8B single-stream DiT architecture. ERNIE-Image aims to bridge the gap between current open-sou…
Sub-Mbps key-rate continuous-variable quantum key distribution with local-local-oscillator over 100 km fiber
Yaodi Pi, Heng Wang, Yan Pan +6
We experimentally demonstrated a sub-Mbps key rate Gaussian-modulated coherent-state continuous-variable quantum key distribution (CV-QKD) over 100 km transmission distance. To eff…
High-rate discrete-modulated continuous-variable quantum key distribution with composable security
Mingze Wu, Yan Pan, Junhui Li +8
Continuous-variable quantum key distribution holds the potential to generate high secret key rates, making it a prime candidate for high-rate metropolitan quantum network applicati…
Improving Deep Binary Embedding Networks by Order-aware Reweighting of Triplets
Jikai Chen, Hanjiang Lai, Libing Geng +1
In this paper, we focus on triplet-based deep binary embedding networks for image retrieval task. The triplet loss has been shown to be most effective for the ranking problem. Howe…
OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown Environments
Bo Zhou, Chuanzhao Lu, Yan Pan +1
Autonomous exploration in complex and cluttered environments is essential for various applications. However, there are many challenges due to the lack of global heuristic informati…
ATI-CTLO:Adaptive Temporal Interval-based Continuous-Time LiDAR-Only Odometry
Bo Zhou, Jiajie Wu, Yan Pan +1
The motion distortion in LiDAR scans caused by aggressive robot motion and varying terrain features significantly impacts the positioning and mapping performance of 3D LiDAR odomet…
High-rate continuous-variable quantum key distribution over 100 km fiber with composable security
Heng Wang, Yang Li, Ting Ye +14
Quantum key distribution (QKD), providing a way to generate secret keys with information-theoretic security,is arguably one of the most significant achievements in quantum informat…
ViT2Hash: Unsupervised Information-Preserving Hashing
Qinkang Gong, Liangdao Wang, Hanjiang Lai +2
Unsupervised image hashing, which maps images into binary codes without supervision, is a compressor with a high compression rate. Hence, how to preserving meaningful information o…
3DCaricShop: A Dataset and A Baseline Method for Single-view 3D Caricature Face Reconstruction
Yuda Qiu, Xiaojie Xu, Lingteng Qiu +4
Caricature is an artistic representation that deliberately exaggerates the distinctive features of a human face to convey humor or sarcasm. However, reconstructing a 3D caricature…
GAFD-CC: Global-Aware Feature Decoupling with Confidence Calibration for OOD Detection
Kun Zou, Yongheng Xu, Jianxing Yu +3
Out-of-distribution (OOD) detection is paramount to ensuring the reliability and robustness of learning models in real-world applications. Existing post-hoc OOD detection methods d…
Improved Search in Hamming Space using Deep Multi-Index Hashing
Hanjiang Lai, Yan Pan
Similarity-preserving hashing is a widely-used method for nearest neighbour search in large-scale image retrieval tasks. There has been considerable research on generating efficien…
HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
Xi Zhang, Siyu Zhou, Jiashi Feng +5
As the rapid growth of multi-modal data, hashing methods for cross-modal retrieval have received considerable attention. Deep-networks-based cross-modal hashing methods are appeali…
Accelerating Locality-Driven Integration in Quantum Chemistry with Block-Structured Matrix Multiplication
Xinran Wei, Yan Pan, Fusong Ju +8
Locality-driven integration is a pervasive computational pattern in quantum chemistry, arising whenever spatially localized basis functions interact through numerical quadrature or…
Can depth-adaptive BERT perform better on binary classification tasks
Jing Fan, Xin Zhang, Sheng Zhang +2
In light of the success of transferring language models into NLP tasks, we ask whether the full BERT model is always the best and does it exist a simple but effective method to fin…
Enhanced Multi-Tuple Extraction for Alloys: Integrating Pointer Networks and Augmented Attention
Mengzhe Hei, Zhouran Zhang, Qingbao Liu +6
Extracting high-quality structured information from scientific literature is crucial for advancing material design through data-driven methods. Despite the considerable research in…
On Kronecker's Solvability Theorem
Yan Pan, Yuzhen Chen
Kronecker's 1856 paper contains a solvability theorem that is useful to construct unsolvable algebraic equations. We show how Kronecker's solvability theorem can be derived natural…
High-Rate 16-node quantum access network based on passive optical network
Yan Pan, Yiming Bian, Yang Li +12
Quantum key distribution can provide information-theoretical secure communication, which is now heading towards building the quantum secure network for real-world applications. In…
How to Build Robust FAQ Chatbot with Controllable Question Generator?
Yan Pan, Mingyang Ma, Bernhard Pflugfelder +1
Many unanswerable adversarial questions fool the question-answer (QA) system with some plausible answers. Building a robust, frequently asked questions (FAQ) chatbot needs a large…
Feature Pyramid Hashing
Yifan Yang, Libing Geng, Hanjiang Lai +2
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval. Most deep hashing approaches use the high layer to extract the powerful…
Pioneering Deterministic Scheduling and Network Structure Optimization for Time-Critical Computing Tasks in Industrial IoT
Yujiao Hu, Yining Zhu, Huayu Zhang +5
The Industrial Internet of Things (IIoT) has become a critical technology to accelerate the process of digital and intelligent transformation of industries. As the cooperative rela…
An Iteration-Free Fixed-Point Estimator for Diffusion Inversion
Yifei Chen, Kaiyu Song, Yan Pan +3
Diffusion inversion aims to recover the initial noise corresponding to a given image such that this noise can reconstruct the original image through the denoising diffusion process…
Secure Combination of Untrusted Time information Based on Optimized Dempster-Shafer Theory
Yang Li, Yujie Luo, Yichen Zhang +16
Secure precision time synchronization is important for applications of Cyber-Physical Systems. However, several attacks, especially the Time Delay Attack (TDA), deteriorates the pe…
A Faster LLM-enhanced Algorithm For Path Planning in Large-scale Grid Maps
Junlin Zeng, Xin Zhang, Xiang Zhao +1
Path planning in grid maps, arising from various applications, has garnered significant attention. Existing methods, such as A*, Dijkstra, and their variants, work well for small-s…
Continuous-variable quantum key distribution over 28.6 km fiber with an integrated silicon photonic receiver chip
Yiming Bian, Yan Pan, Xuesong Xu +7
Quantum key distribution, which ensures information-theoretically secret key generation, is currently advancing through photonic integration to achieve high performance, cost reduc…
Performance Analysis and Optimization for Laser-Phase-Noise based Quantum Random Number Generation
Jinlu Liu, Jie Yang, Yu Gao +8
The quantum random number generation based on laser phase noise, which is featured with high random number generation rate and ease for photonic integration, has been extensively i…
Two Simple Principles for Diffusion-Based Test-Time Adaptation
Kaiyu Song, Hanjiang Lai, Yan Pan +2
Recently, diffusion-based test-time adaptations (TTA) have shown great advances, which leverage a diffusion model to map the images in the unknown test domain to the training domai…
Phase-reference intensity attack on continuous-variable quantum key distribution with a real local oscillator
Yun Shao, Yang Li, Heng Wang +5
In practical continuous-variable quantum key distribution system using local local oscillator (LLO CV-QKD), the phase noise related to coherent detection and phase-reference pulse…
Modelling Sentence Pairs with Tree-structured Attentive Encoder
Yao Zhou, Cong Liu, Yan Pan
We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing atten…
Camera-LiDAR Fusion with Latent Contact for Place Recognition in Challenging Cross-Scenes
Yan Pan, Jiapeng Xie, Jiajie Wu +1
Although significant progress has been made, achieving place recognition in environments with perspective changes, seasonal variations, and scene transformations remains challengin…
An Ultra-fast Quantum Random Number Generation Scheme Based on Laser Phase Noise
Jie Yang, Mei Wu, Yichen Zhang +13
Based on the intrinsic random property of quantum mechanics, quantum random number generators allow for access of truly unpredictable random sequence and are now heading towards hi…
Secure two-way fiber-optic time transfer against sub-ns asymmetric delay attack
Yang Li, Jinlong Hu, Li Ma +14
Two-way fiber-optic time transfer is a promising precise time synchronization technique with sub-nanosecond accuracy. However, asymmetric delay attack is a serious threat which can…
Thinking Before You Speak: A Proactive Test-time Scaling Approach
Cong Liu, Wenchang Chai, Hejun Wu +3
Large Language Models (LLMs) often exhibit deficiencies with complex reasoning tasks, such as maths, which we attribute to the discrepancy between human reasoning patterns and thos…
Regularizing Deep Hashing Networks Using GAN Generated Fake Images
Libing Geng, Yan Pan, Jikai Chen +1
Recently, deep-networks-based hashing (deep hashing) has become a leading approach for large-scale image retrieval. It aims to learn a compact bitwise representation for images via…
Safety-Critical LiDAR-Inertial Odometry with On-Manifold Deterministic Protection Level
Yueqi Zhu, Yan Pan, Chufan Rui +3
In safety-critical scenarios, the protection level of the autonomous navigation system is crucial for enabling mobile robots to perform safe tasks. However, existing studies on pro…
Few-Shot Nested Named Entity Recognition
Hong Ming, Jiaoyun Yang, Lili Jiang +2
While Named Entity Recognition (NER) is a widely studied task, making inferences of entities with only a few labeled data has been challenging, especially for entities with nested…
TriDeliver: Cooperative Air-Ground Instant Delivery with UAVs, Couriers, and Crowdsourced Ground Vehicles
Junhui Gao, Yan Pan, Qianru Wang +4
Instant delivery, shipping items before critical deadlines, is essential in daily life. While multiple delivery agents, such as couriers, Unmanned Aerial Vehicles (UAVs), and crowd…
Transductive Zero-Shot Hashing via Coarse-to-Fine Similarity Mining
Hanjiang Lai, Yan Pan
Zero-shot Hashing (ZSH) is to learn hashing models for novel/target classes without training data, which is an important and challenging problem. Most existing ZSH approaches explo…
Experimental Demonstration of High-Rate Discrete-Modulated Continuous-Variable Quantum Key Distribution System
Yan Pan, Heng Wang, Yun Shao +5
A high-rate continuous-variable quantum key distribution (CV-QKD) system based on high-order discrete modulation is experimentally investigated. With the help of the novel system s…
Deep Recurrent Regression for Facial Landmark Detection
Hanjiang Lai, Shengtao Xiao, Yan Pan +5
We propose a novel end-to-end deep architecture for face landmark detection, based on a deep convolutional and deconvolutional network followed by carefully designed recurrent netw…
The Future of Cognitive Strategy-enhanced Persuasive Dialogue Agents: New Perspectives and Trends
Mengqi Chen, Bin Guo, Hao Wang +6
Persuasion, as one of the crucial abilities in human communication, has garnered extensive attention from researchers within the field of intelligent dialogue systems. We humans te…
Simple and Fast Polarization Tracking algorithm for Continuous-Variable Quantum Key Distribution System Using Orthogonal Pilot Tone
Yan Pan, Heng Wang, Yun Shao +6
To reduce the influence of random channel polarization variation, especially fast polarization perturbation,for continuous-variable quantum key distribution (CV-QKD) systems, a sim…
Convergence and Complexity of an Adaptive Planewave Method for Eigenvalue Computations
Xiaoying Dai, Yan Pan, Bin Yang +1
In this paper, we study the adaptive planewave discretization for a cluster of eigenvalues of second-order elliptic partial differential equations. We first design an a posteriori…
Integrating Graph Partitioning and Matching for Trajectory Analysis in Video Surveillance
Liang Lin, Yongyi Lu, Yan Pan +1
In order to track the moving objects in long range against occlusion, interruption, and background clutter, this paper proposes a unified approach for global trajectory analysis. I…
Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
Kaiyu Song, Hanjiang Lai, Yan Pan +2
Training-free conditional generation based on flow matching aims to leverage pre-trained unconditional flow matching models to perform conditional generation without retraining. Re…
A parallel orbital-updating based plane-wave basis method for electronic structure calculations
Yan Pan, Xiaoying Dai, Stefano de Gironcoli +3
Motivated by the recently proposed parallel orbital-updating approach in real space method, we propose a parallel orbital-updating based plane-wave basis method for electronic stru…
Optimizing Evaluation Metrics for Multi-Task Learning via the Alternating Direction Method of Multipliers
Ge-Yang Ke, Yan Pan, Jian Yin +1
Multi-task learning (MTL) aims to improve the generalization performance of multiple tasks by exploiting the shared factors among them. Various metrics (e.g., F-score, Area Under t…
Toward Understanding Why Adam Converges Faster Than SGD for Transformers
Yan Pan, Yuanzhi Li
While stochastic gradient descent (SGD) is still the most popular optimization algorithm in deep learning, adaptive algorithms such as Adam have established empirical advantages ov…
Hierarchical Intention-Aware Expressive Motion Generation for Humanoid Robots
Lingfan Bao, Yan Pan, Tianhu Peng +2
Effective human-robot interaction requires robots to identify human intentions and generate expressive, socially appropriate motions in real-time. Existing approaches often rely on…
Highly stable power control for chip-based continuous-variable quantum key distribution system
Yiming Bian, Yang Li, Xuesong Xu +7
Quantum key distribution allows secret key generation with information theoretical security. It can be realized with photonic integrated circuits to benefit the tiny footprints and…
Performance analysis for OFDM-based multi-carrier continuous-variable quantum key distribution with arbitrary modulation protocol
Heng Wang, Yan Pan, Yun Shao +9
Multi-carrier continuous-variable quantum key distribution (CV-QKD) is considered to be a promising way to boost the secret key rate (SKR) over the existing single-carrier CV-QKD s…
High-rate discrete-modulated continuous-variable quantum key distribution with composable security
Mingze Wu, Yan Pan, Junhui Li +8
Continuous-variable quantum key distribution holds the potential to generate high secret key rates, making it a prime candidate for high-rate metropolitan quantum network applicati…
Improving Entropy-Based Test-Time Adaptation from a Clustering View
Guoliang Lin, Hanjiang Lai, Yan Pan +1
Domain shift is a common problem in the realistic world, where training data and test data follow different data distributions. To deal with this problem, fully test-time adaptatio…
Calf-Integrated Arms for Bimanual Quadruped Loco-Manipulation
Yan Pan, Yuanchuan Ren, Chipui Chan +2
Most quadruped loco-manipulation designs trade manipulation capability against stance. A trunk-mounted arm sits high and usually carries a single arm; using the legs as manipulator…
Distributed Low Precision Training Without Mixed Precision
Zehua Cheng, Weiyang Wang, Yan Pan +1
Low precision training is one of the most popular strategies for deploying the deep model on limited hardware resources. Fixed point implementation of DCNs has the potential to all…
Personalized and Occupational-aware Age Progression by Generative Adversarial Networks
Siyu Zhou, Weiqiang Zhao, Jiashi Feng +4
Face age progression, which aims to predict the future looks, is important for various applications and has been received considerable attentions. Existing methods and datasets are…
CoRaiS: Lightweight Real-Time Scheduler for Multi-Edge Cooperative Computing
Yujiao Hu, Qingmin Jia, Jinchao Chen +4
Multi-edge cooperative computing that combines constrained resources of multiple edges into a powerful resource pool has the potential to deliver great benefits, such as a tremendo…
Sub-Gbps key rate four-state continuous-variable quantum key distribution within metropolitan area
Heng Wang, Yang Li, Yaodi Pi +7
Continuous-variable quantum key distribution (CVQKD) has potential advantages of high secret key rate, which is very suitable for high-speed metropolitan network application. Howev…