Publications (62)
Strong convergence for the modified Mann's iteration of -strict pseudocontraction
Yisheng Song, Hongjun Wang
In this paper, for an -strict pseudocontraction , we prove strong convergence of the modified Mann's iteration defined by $$x_{n+1}=β_{n}u+γ_nx_n+(1-β_{n}-γ_n)[α_{n}Tx_…
High-performance Estimation of Jamming Covariance Matrix for IRS-aided Directional Modulation Network with a Malicious Attacker
Hangjia He, Ting Su, Hongjun Wang +4
In this paper, we investigate the anti-jamming problem of a directional modulation (DM) system with the aid of intelligent reflecting surface (IRS). As an efficient tool to combat…
MultiEdit: Advancing Instruction-based Image Editing on Diverse and Challenging Tasks
Mingsong Li, Lin Liu, Hongjun Wang +7
Current instruction-based image editing (IBIE) methods struggle with challenging editing tasks, as both editing types and sample counts of existing datasets are limited. Moreover,…
TrajGPT-R: Generating Urban Mobility Trajectory with Reinforcement Learning-Enhanced Generative Pre-trained Transformer
Jiawei Wang, Chuang Yang, Jiawei Yong +6
Mobility trajectories are essential for understanding urban dynamics and enhancing urban planning, yet access to such data is frequently hindered by privacy concerns. This research…
NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
Xin Li, Yeying Jin, Xin Jin +134
This paper reviews the NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images. This challenge received a wide range of impressive solutions, which are devel…
Evaluating the Generalization Ability of Spatiotemporal Model in Urban Scenario
Hongjun Wang, Jiyuan Chen, Tong Pan +4
Spatiotemporal neural networks have shown great promise in urban scenarios by effectively capturing temporal and spatial correlations. However, urban environments are constantly ev…
TrafPS: A Shapley-based Visual Analytics Approach to Interpret Traffic
Zezheng Feng, Yifan Jiang, Hongjun Wang +5
Recent achievements in deep learning (DL) have shown its potential for predicting traffic flows. Such predictions are beneficial for understanding the situation and making decision…
GOF-TTE: Generative Online Federated Learning Framework for Travel Time Estimation
Zhiwen Zhang, Hongjun Wang, Jiyuan Chen +3
Estimating the travel time of a path is an essential topic for intelligent transportation systems. It serves as the foundation for real-world applications, such as traffic monitori…
Crowd Counting using Deep Recurrent Spatial-Aware Network
Lingbo Liu, Hongjun Wang, Guanbin Li +2
Crowd counting from unconstrained scene images is a crucial task in many real-world applications like urban surveillance and management, but it is greatly challenged by the camera'…
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
Yitong Jiang, Hongjun Wang, Collin McCarthy +15
Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining. Subquadratic al…
Resilience Inference for Supply Chains with Hypergraph Neural Network
Zetian Shen, Hongjun Wang, Jiyuan Chen +1
Supply chains are integral to global economic stability, yet disruptions can swiftly propagate through interconnected networks, resulting in substantial economic impacts. Accurate…
Generalist++: A Meta-learning Framework for Mitigating Trade-off in Adversarial Training
Yisen Wang, Yichuan Mo, Hongjun Wang +2
Despite the rapid progress of neural networks, they remain highly vulnerable to adversarial examples, for which adversarial training (AT) is currently the most effective defense. W…
Route to Time and Time to Route: Travel Time Estimation from Sparse Trajectories
Zhiwen Zhang, Hongjun Wang, Zipei Fan +3
Due to the rapid development of Internet of Things (IoT) technologies, many online web apps (e.g., Google Map and Uber) estimate the travel time of trajectory data collected by mob…
Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
Hongjun Wang, Jiyuan Chen, Zhengwei Yin +2
Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on im…
Distributional Discrepancy: A Metric for Unconditional Text Generation
Ping Cai, Xingyuan Chen, Peng Jin +2
The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However,…
See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View
Fanfu Xue, En Yu, Yantian Shen +5
UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized a…
What Can We Learn from Harry Potter? An Exploratory Study of Visual Representation Learning from Atypical Videos
Qiyue Sun, Qiming Huang, Yang Yang +2
Humans usually show exceptional generalisation and discovery ability in the open world, when being shown uncommon new concepts. Whereas most existing studies in the literature focu…
Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation
Weining Ren, Hongjun Wang, Xiao Tan +1
We present Fin3R, a simple, effective, and general fine-tuning method for feed-forward 3D reconstruction models. The family of feed-forward reconstruction model regresses pointmap…
Panoptic Captioning: An Equivalence Bridge for Image and Text
Kun-Yu Lin, Hongjun Wang, Weining Ren +1
This work introduces panoptic captioning, a novel task striving to seek the minimum text equivalent of images, which has broad potential applications. We take the first step toward…
Towards Resilient Transportation: A Conditional Transformer for Accident-Informed Traffic Forecasting
Hongjun Wang, Jiawei Yong, Jiawei Wang +2
Traffic prediction remains a key challenge in spatio-temporal data mining, despite progress in deep learning. Accurate forecasting is hindered by the complex influence of external…
Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting
Hongjun Wang, Jiyuan Chen, Lingyu Zhang +2
Spatiotemporal Graph Neural Networks (ST-GNNs) and Transformers have shown significant promise in traffic forecasting by effectively modeling temporal and spatial correlations. How…
MHPO: Modulated Hazard-aware Policy Optimization for Stable Reinforcement Learning
Hongjun Wang, Wei Liu, Weibo Gu +2
Regulating the importance ratio is critical for the training stability of Group Relative Policy Optimization (GRPO) based frameworks. However, prevailing ratio control methods, suc…
Restricted Boltzmann Machines with Gaussian Visible Units Guided by Pairwise Constraints
Jielei Chu, Hongjun Wang, Hua Meng +2
Restricted Boltzmann machines (RBMs) and their variants are usually trained by contrastive divergence (CD) learning, but the training procedure is an unsupervised learning approach…
HarmoQ: Harmonized Post-Training Quantization for High-Fidelity Image
Hongjun Wang, Jiyuan Chen, Xuan Song +1
Post-training quantization offers an efficient pathway to deploy super-resolution models, yet existing methods treat weight and activation quantization independently, missing their…
Multi-local Collaborative AutoEncoder
Jielei Chu, Hongjun Wang, Jing Liu +2
The excellent performance of representation learning of autoencoders have attracted considerable interest in various applications. However, the structure and multi-local collaborat…
AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field
Chen Liang, Zhaoqi Huang, Haofen Wang +8
Large language models (LLMs), as a novel information technology, are seeing increasing adoption in the Architecture, Engineering, and Construction (AEC) field. They have shown thei…
Self-Ensemble Adversarial Training for Improved Robustness
Hongjun Wang, Yisen Wang
Due to numerous breakthroughs in real-world applications brought by machine intelligence, deep neural networks (DNNs) are widely employed in critical applications. However, predict…
Dissecting Out-of-Distribution Detection and Open-Set Recognition: A Critical Analysis of Methods and Benchmarks
Hongjun Wang, Sagar Vaze, Kai Han
Detecting test-time distribution shift has emerged as a key capability for safely deployed machine learning models, with the question being tackled under various guises in recent y…
Adding A Filter Based on The Discriminator to Improve Unconditional Text Generation
Xingyuan Chen, Ping Cai, Peng Jin +3
The autoregressive language model (ALM) trained with maximum likelihood estimation (MLE) is widely used in unconditional text generation. Due to exposure bias, the generated texts…
Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM
Jielei Chu, Hongjun Wang, Jing Liu +2
In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering i…
Robust Traffic Forecasting against Spatial Shift over Years
Hongjun Wang, Jiyuan Chen, Tong Pan +4
Recent advancements in Spatiotemporal Graph Neural Networks (ST-GNNs) and Transformers have demonstrated promising potential for traffic forecasting by effectively capturing both t…
GSPN-2: Efficient Parallel Sequence Modeling
Hongjun Wang, Yitong Jiang, Collin McCarthy +12
Efficient vision transformer remains a bottleneck for high-resolution images and long-video related real-world applications. Generalized Spatial Propagation Network (GSPN) addresse…
ST-ExpertNet: A Deep Expert Framework for Traffic Prediction
Hongjun Wang, Jiyuan Chen, Zipei Fan +3
Recently, forecasting the crowd flows has become an important research topic, and plentiful technologies have achieved good performances. As we all know, the flow at a citywide lev…
Accurate Cutting-point Estimation for Robotic Lychee Harvesting through Geometry-aware Learning
Gengming Zhang, Hao Cao, Kewei Hu +4
Accurately identifying lychee-picking points in unstructured orchard environments and obtaining their coordinate locations is critical to the success of lychee-picking robots. Howe…
Accelerating Flood Warnings by 10 Hours: The Power of River Network Topology in AI-enhanced Flood Forecasting
Hongjun Wang, Jiyuan Chen, Yinqiang Zheng +1
Climate change-driven floods demand advanced forecasting models, yet Graph Neural Networks (GNNs) underutilize river network topology due to tree-like structures causing over-squas…
STGformer: Efficient Spatiotemporal Graph Transformer for Traffic Forecasting
Hongjun Wang, Jiyuan Chen, Tong Pan +4
Traffic forecasting is a cornerstone of smart city management, enabling efficient resource allocation and transportation planning. Deep learning, with its ability to capture comple…
Multitask Weakly Supervised Learning for Origin Destination Travel Time Estimation
Hongjun Wang, Zhiwen Zhang, Zipei Fan +4
Travel time estimation from GPS trips is of great importance to order duration, ridesharing, taxi dispatching, etc. However, the dense trajectory is not always available due to the…
The Detection of Distributional Discrepancy for Text Generation
Xingyuan Chen, Ping Cai, Peng Jin +4
The text generated by neural language models is not as good as the real text. This means that their distributions are different. Generative Adversarial Nets (GAN) are used to allev…
HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts
Hongjun Wang, Sagar Vaze, Kai Han
Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they…
Micro-supervised Disturbance Learning: A Perspective of Representation Probability Distribution
Jielei Chu, Jing Liu, Hongjun Wang +3
The instability is shown in the existing methods of representation learning based on Euclidean distance under a broad set of conditions. Furthermore, the scarcity and high cost of…
A Hamiltonian Monte Carlo Method for Probabilistic Adversarial Attack and Learning
Hongjun Wang, Guanbin Li, Xiaobai Liu +1
Although deep convolutional neural networks (CNNs) have demonstrated remarkable performance on multiple computer vision tasks, researches on adversarial learning have shown that de…
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Inclusion AI, Tiwei Bie, Haoxing Chen +15
We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its…
Easy Begun is Half Done: Spatial-Temporal Graph Modeling with ST-Curriculum Dropout
Hongjun Wang, Jiyuan Chen, Tong Pan +7
Spatial-temporal (ST) graph modeling, such as traffic speed forecasting and taxi demand prediction, is an important task in deep learning area. However, for the nodes in graph, the…
STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs
Ye Wang, Hongjun Wang, Hao Fang +7
Unified multimodal models (UMMs) aim to integrate visual understanding and generation within a single architecture, but architectural unification alone does not ensure semantic con…
Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
Hongjun Wang, Po Hu, Kai Han
Generalized Category Discovery (GCD) aims to categorize unlabelled instances from both known and unknown classes by transferring knowledge from labelled data of known classes. Exis…
Baseline correction for FAST radio recombination lines: a modified penalized least squares smoothing technique
Bin Liu, Lixin Wang, Junzhi Wang +2
A pilot project has been proceeded to map 1 deg on the Galactic plane for radio recombination lines (RRLs) using the Five hundred meter Aperture Spherical Telescope (FAST). The…
Parallel Sequence Modeling via Generalized Spatial Propagation Network
Hongjun Wang, Wonmin Byeon, Jiarui Xu +6
We present the Generalized Spatial Propagation Network (GSPN), a new attention mechanism optimized for vision tasks that inherently captures 2D spatial structures. Existing attenti…
Robustifying Fourier Features Embeddings for Implicit Neural Representations
Mingze Ma, Qingtian Zhu, Yifan Zhan +3
Implicit Neural Representations (INRs) employ neural networks to represent continuous functions by mapping coordinates to the corresponding values of the target function, with appl…
Worldwide wildfire spreading and its severity described by the SIR model
Tong Pan, Hongjun Wang, Jiyuan Chen +1
Global wildfire spreading dynamics and severity are analyzed using the susceptible-infected-recovered (SIR) compartment model. We use the novel FireTracks (FT) Scientific Dataset c…
Motion Blur Robust Wheat Pest Damage Detection with Dynamic Fuzzy Feature Fusion
Han Zhang, Yanwei Wang, Fang Li +1
Motion blur caused by camera shake produces ghosting artifacts that substantially degrade edge side object detection. Existing approaches either suppress blur as noise and lose dis…
Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification
Hongjun Wang, Jiyuan Chen, Zhengwei Yin +2
Cloth-Changing Person Re-Identification (CC-ReID) involves recognizing individuals in images regardless of clothing status. In this paper, we empirically and experimentally demonst…
Causal-Based Supervision of Attention in Graph Neural Network: A Better and Simpler Choice towards Powerful Attention
Hongjun Wang, Jiyuan Chen, Lun Du +3
Recent years have witnessed the great potential of attention mechanism in graph representation learning. However, while variants of attention-based GNNs are setting new benchmarks…
TrafPS: A Visual Analysis System Interpreting Traffic Prediction in Shapley
Yifan Jiang, Zezheng Feng, Hongjun Wang +2
In recent years, deep learning approaches have been proved good performance in traffic flow prediction, many complex models have been proposed to make traffic flow prediction more…
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
Hongjun Wang, Guangrun Wang, Ya Li +2
The success of DNNs has driven the extensive applications of person re-identification (ReID) into a new era. However, whether ReID inherits the vulnerability of DNNs remains unexpl…
Unsupervised Multi-Attention Meta Transformer for Rotating Machinery Fault Diagnosis
Hanyang Wang, Yuxuan Yang, Hongjun Wang +1
The intelligent fault diagnosis of rotating mechanical equipment usually requires a large amount of labeled sample data. However, in practical industrial applications, acquiring en…
Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution
Hongjun Wang, Jiyuan Chen, Yinqiang Zheng +1
Deep learning has led to a dramatic leap on Single Image Super-Resolution (SISR) performances in recent years. %Despite the substantial advancement% While most existing work assume…
Eigenvalues of Laplace operators on non-bipartite graphs
Hongjun Wang, Hongmei Song, Jia Zhao
This paper considers the comparison between the eigenvalues of Laplace operators with the standard conditions and the anti-standard conditions on non-bipartite graphs which are equ…
Generalist: Decoupling Natural and Robust Generalization
Hongjun Wang, Yisen Wang
Deep neural networks obtained by standard training have been constantly plagued by adversarial examples. Although adversarial training demonstrates its capability to defend against…
SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
Hongjun Wang, Sagar Vaze, Kai Han
Generalized Category Discovery (GCD) aims to classify unlabelled images from both `seen' and `unseen' classes by transferring knowledge from a set of labelled `seen' class images.…
HoLens: A Visual Analytics Design for Higher-order Movement Modeling and Visualization
Zezheng Feng, Fang Zhu, Hongjun Wang +4
Higher-order patterns reveal sequential multistep state transitions, which are usually superior to origin-destination analysis, which depicts only first-order geospatial movement p…
Leum-VL Technical Report
Yuxuan He, Chaiming Huang, Yifan Wu +4
A short video succeeds not simply because of what it shows, but because of how it schedules attention -- yet current multimodal models lack the structural grammar to parse or produ…
Deliberate Before You Fly: Vision-Guided Spatial Deliberation for UAV See-and-Reach Navigation
Fanfu Xue, En Yu, Bohang Liu +4
UAV see-and-reach navigation requires an aerial agent to approach a language-specified target visible in its initial view and stop reliably near it. Existing methods typically map…