Publications (77)
Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustness
Long Dang, Thushari Hapuarachchi, Kaiqi Xiong +1
Adversarial training is an effective method to improve the machine learning (ML) model robustness. Most existing studies typically consider the Rectified linear unit (ReLU) activat…
Impulsive Noise Mitigation in Powerline Communications Using Sparse Bayesian Learning
Jing Lin, Marcel Nassar, Brian L. Evans
Additive asynchronous and cyclostationary impulsive noise limits communication performance in OFDM powerline communication (PLC) systems. Conventional OFDM receivers assume additiv…
Nonlinear Transformations Against Unlearnable Datasets
Thushari Hapuarachchi, Jing Lin, Kaiqi Xiong +2
Automated scraping stands out as a common method for collecting data in deep learning models without the authorization of data owners. Recent studies have begun to tackle the priva…
SkillMimic: Learning Basketball Interaction Skills from Demonstrations
Yinhuai Wang, Qihan Zhao, Runyi Yu +10
Traditional reinforcement learning methods for human-object interaction (HOI) rely on labor-intensive, manually designed skill rewards that do not generalize well across different…
A Novel Context driven Critical Integrative Levels (CIL) Approach: Advancing Human-Centric and Integrative Lighting Asset Management in Public Libraries with Practical Thresholds
Jing Lin, Nina Mylly, Per Olof Hedekvist +1
This paper proposes the context driven Critical Integrative Levels (CIL), a novel approach to lighting asset management in public libraries that aligns with the transformative visi…
Soliton Transitions Mediated by Skin-Mode Localization and Band Nonreciprocity
Shanyue Li, Mengying Hu, Jing Lin +3
Solitons, typically resulting from a competition between band dispersion and nonlinearity, occur in lattices featuring the non-Hermitian skin effect as nonlinearity increases, acco…
RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
Hanlin Tang, Yang Lin, Jing Lin +4
The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this…
DeepNC: A Fast GNN-based Pre-Verification Surrogate for TSN Configuration
Jiayi Zhu, Jing Lin, Zelong Tian +2
Time-Sensitive Networking (TSN) is critical to deterministic communication in safety-critical domains, with formal verification such as Network Calculus (NC) serving as the corners…
SDQM: Synthetic Data Quality Metric for Object Detection Dataset Evaluation
Ayush Zenith, Arnold Zumbrun, Neel Raut +1
The performance of machine learning models depends heavily on training data. The scarcity of large-scale, well-annotated datasets poses significant challenges in creating robust mo…
In situ mixer calibration for superconducting quantum circuits
Nan Wu, Jing Lin, Changrong Xie +17
Mixers play a crucial role in superconducting quantum computing, primarily by facilitating frequency conversion of signals to enable precise control and readout of quantum states.…
Geometry-induced Exceptional Point Detached from Fermi Arcs
Yuancheng Zhao, Jia-Xin Zhong, Jing Lin +2
Exceptional points (EPs), ubiquitous non-Hermitian degeneracies, are central features in band structures where non-Hermitian Fermi arcs connect EPs and eigenvalue knots encircle th…
One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
Jing Lin, Ailing Zeng, Haoqian Wang +2
Whole-body mesh recovery aims to estimate the 3D human body, face, and hands parameters from a single image. It is challenging to perform this task with a single network due to res…
Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
Diandian Gu, Jing Lin, Gaohong Liu +25
We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and ap…
ChatHuman: Chatting about 3D Humans with Tools
Jing Lin, Yao Feng, Weiyang Liu +1
Numerous methods have been proposed to detect, estimate, and analyze properties of people in images, including 3D pose, shape, contact, human-object interaction, and emotion. While…
UniMo: Unified Motion Generation and Understanding with Chain of Thought
Guocun Wang, Kenkun Liu, Jing Lin +3
Existing 3D human motion generation and understanding methods often exhibit limited interpretability, restricting effective mutual enhancement between these inherently related task…
Mahalanobis distance-based robust approaches against false data injection attacks on dynamic power state estimation
Jing Lin, Kaiqi Xiong
Many researchers have studied false data injection (FDI) attacks in power state estimation, but existing state estimation approaches are still highly vulnerable to FDI attacks. In…
DPoser: Diffusion Model as Robust 3D Human Pose Prior
Junzhe Lu, Jing Lin, Hongkun Dou +4
This work targets to construct a robust human pose prior. However, it remains a persistent challenge due to biomechanical constraints and diverse human movements. Traditional prior…
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
Jing Lin, Ruisi Wang, Junzhe Lu +10
Despite recent advances in 3D human motion generation (MoGen) on standard benchmarks, existing text-to-motion models still face a fundamental bottleneck in their generalization cap…
Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
Yuanhao Cai, Jing Lin, Haoqian Wang +5
In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a…
LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations
Lei Shi, Zhimeng Liu, Yi Yang +13
The extraction of Metal-Organic Frameworks (MOFs) synthesis route from literature has been crucial for the logical MOFs design with desirable functionality. The recent advent of la…
Human-Centric and Integrative Lighting Asset Management in Public Libraries: Qualitative Insights and Challenges from a Swedish Field Study
Jing Lin, Per Olof Hedekvist, Nina Mylly +4
Traditional lighting source reliability evaluations, often covering just half of a lamp's volume, can misrepresent real-world performance. To overcome these limitations,adopting ad…
Binarized Spectral Compressive Imaging
Yuanhao Cai, Yuxin Zheng, Jing Lin +3
Existing deep learning models for hyperspectral image (HSI) reconstruction achieve good performance but require powerful hardwares with enormous memory and computational resources.…
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
Yuanhao Cai, Jing Lin, Xiaowan Hu +5
Hyperspectral image (HSI) reconstruction aims to recover the 3D spatial-spectral signal from a 2D measurement in the coded aperture snapshot spectral imaging (CASSI) system. The HS…
Dynamic Low-Rank Sparse Adaptation for Large Language Models
Weizhong Huang, Yuxin Zhang, Xiawu Zheng +4
Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Ada…
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
Yuanhao Cai, Jing Lin, Zudi Lin +5
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image…
Multi-function Robotized Surgical Dissector for Endoscopic Pulmonary Thromboendarterectomy: Preclinical Study and Evaluation
Runfeng Zhu, Xin Zhong, Qingxiang Zhao +3
Patients suffering chronic severe pulmonary thromboembolism need Pulmonary Thromboendarterectomy (PTE) to remove the thromb and intima located inside pulmonary artery (PA). During…
PAS: A Position-Aware Similarity Measurement for Sequential Recommendation
Zijie Zeng, Jing Lin, Weike Pan +2
The common item-based collaborative filtering framework becomes a typical recommendation method when equipped with a certain item-to-item similarity measurement. On one hand, we re…
2026 Roadmap on Artificial Intelligence and Machine Learning for Smart Manufacturing
Jay Lee, Hanqi Su, Marco Macchi +50
The evolution of artificial intelligence (AI) and machine learning (ML) is reshaping smart manufacturing by providing new capabilities for efficiency, adaptability, and autonomy ac…
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
Jing Lin, Xiaowan Hu, Yuanhao Cai +5
How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised…
Trailing Waves
Yongsheng Shao, Liang Zeng, Jing Lin
We report a special phenomenon: trailing waves. They are generated by the propagation of elastic waves in plates at large frequency-thickness (fd) product. Unlike lamb waves and bu…
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
Xiaoning Liu, Zongwei Wu, Ao Li +109
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective netw…
PhysHOI: Physics-Based Imitation of Dynamic Human-Object Interaction
Yinhuai Wang, Jing Lin, Ailing Zeng +3
Humans interact with objects all the time. Enabling a humanoid to learn human-object interaction (HOI) is a key step for future smart animation and intelligent robotics systems. Ho…
Driving behavior-guided battery health monitoring for electric vehicles using machine learning
Nanhua Jiang, Jiawei Zhang, Weiran Jiang +4
An accurate estimation of the state of health (SOH) of batteries is critical to ensuring the safe and reliable operation of electric vehicles (EVs). Feature-based machine learning…
Enhanced Digital Twin for Human-Centric and Integrated Lighting Asset Management in Public Libraries: From Corrective to Predictive Maintenance
Jing Lin, Jingchun Shen
Lighting asset management in public libraries has traditionally been reactive, focusing on corrective maintenance, addressing issues only when failures occur. Although standards no…
Towards Fine-Grained Human Motion Video Captioning
Guorui Song, Guocun Wang, Zhe Huang +4
Generating accurate descriptions of human actions in videos remains a challenging task for video captioning models. Existing approaches often struggle to capture fine-grained motio…
DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
Junzhe Lu, Jing Lin, Hongkun Dou +8
We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent…
ZIF-90 treats fungal keratitis by promoting macrophage apoptosis and inhibiting inflammatory response
Xueyun Fu, Jing Lin, Qian Wang +6
Fungal keratitis is a severe vision-threatening corneal infection with a prognosis influenced by fungal virulence and the host's immune defense mechanisms. The immune system, throu…
Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Jing Lin, Ailing Zeng, Shunlin Lu +4
In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expression…
Unveiling non-Hermitian band structures with non-Bloch supercells
Jia-Xin Zhong, Jing Lin, Kai Chen +3
Real-valued band structures are foundational to analyzing periodic systems within the Hermitian description and have been experimentally well-established over recent decades. In co…
Zeolitic Imidazolate Framework-8 offers an anti-inflammatory and antifungal method in the treatment of Aspergillus fungus keratitis in vitro and in vivo
Xueyun Fu, Xue Tian, Jing Lin +10
Background: Fungal keratitis is a serious blinding eye disease. Traditional drugs used to treat fungal keratitis commonly have the disadvantages of low bioavailability, poor disper…
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
Yuanhao Cai, Hao Bian, Jing Lin +3
When enhancing low-light images, many deep learning algorithms are based on the Retinex theory. However, the Retinex model does not consider the corruptions hidden in the dark or i…
ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition
Shen Lin, Jing Lin, Junhao Dong +2
Machine unlearning in Vision-Language Models (VLMs) is typically performed at the image or instance level, making it difficult to precisely remove target knowledge without affectin…
StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation
Guangda Liu, Yiquan Wang, Chengwei Li +6
Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, mod…
Algebraic skin effect in two-dimensional non-Hermitian metamaterials
Mingyang Li, Jing Lin, Kun Ding
Metamaterials have unlocked unprecedented control over light by leveraging novel mechanisms to expand their functionality. Non-Hermitian physics further enhances the tunability of…
Timeripple: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space
Wenxuan Miao, Yulin Sun, Aiyue Chen +8
The recent surge in video generation has shown the growing demand for high-quality video synthesis using large vision models. Existing video generation models are predominantly bas…
EPIC: Abstraction and Polymorphism of In-Network Collectives on Ethernet
Yitao Yuan, Jianglong Nie, Tianyu Bai +28
In-Network Collective (INC) acceleration holds immense potential for optimizing AI training and inference; however, its cross-layer nature has historically hindered investment and…
HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
Xiaowan Hu, Yuanhao Cai, Jing Lin +5
The rapid development of deep learning provides a better solution for the end-to-end reconstruction of hyperspectral image (HSI). However, existing learning-based methods have two…
Active Learning Under Malicious Mislabeling and Poisoning Attacks
Jing Lin, Ryan Luley, Kaiqi Xiong
Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language pr…
Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset
Yuhong Zhang, Jing Lin, Ailing Zeng +7
In this paper, we introduce Motion-X++, a large-scale multimodal 3D expressive whole-body human motion dataset. Existing motion datasets predominantly capture body-only poses, lack…
ML Attack Models: Adversarial Attacks and Data Poisoning Attacks
Jing Lin, Long Dang, Mohamed Rahouti +1
Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However,…
MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention
Jianlin Yu, Jing Lin, Linghui Kong +13
The quadratic cost of attention is a major bottleneck in diffusion-based video generation models. MXFP4 attention provides a promising path toward efficient inference, but direct M…
Unveiling Non-Hermitian Spectral Topology in Hyperbolic Lattices with Non-Abelian Translation Symmetry
Mengying Hu, Jing Lin, Kun Ding
The hyperbolic lattice (HBL) has emerged as a compelling platform for exploring matter in non-Euclidean space. Among its notable features, the breakdown of the conventional Bloch t…
Flow-Guided Sparse Transformer for Video Deblurring
Jing Lin, Yuanhao Cai, Xiaowan Hu +7
Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring. However, CNN-based methods show limitations in capturing long-range…
Foundation-Assisted Active Learning for Object Detection Annotation
Jinchang Zhang, Arnold Zumbrun, Jing Lin +1
The annotation cost for remote sensing object detection is high, while existing active learning methods still face several challenges in object detection scenarios, including the c…
Projecting and comparing non-pharmaceutical interventions to contain COVID-19 in major economies
Jingjing He, Xuefei Guan, Xiaochang Duan +2
Non-pharmaceutical interventions (NPIs) such as quarantine, self-isolation, social distancing, and virus-contact tracing can greatly reduce the spread of the virus during a pandemi…
EchoMotion: Unified Human Video and Motion Generation via Dual-Modality Diffusion Transformer
Yuxiao Yang, Hualian Sheng, Sijia Cai +6
Video generation models have advanced significantly, yet they still struggle to synthesize complex human movements due to the high degrees of freedom in human articulation. This li…
Hybrid physics-based and data-driven modeling with calibrated uncertainty for lithium-ion battery degradation diagnosis and prognosis
Jing Lin, Yu Zhang, Edwin Khoo
Advancing lithium-ion batteries (LIBs) in both design and usage is key to promoting electrification in the coming decades to mitigate human-caused climate change. Inadequate unders…
Health diagnosis and recuperation of aged Li-ion batteries with data analytics and equivalent circuit modeling
Riko I Made, Jing Lin, Jintao Zhang +8
Battery health assessment and recuperation play a crucial role in the utilization of second-life Li-ion batteries. However, due to ambiguous aging mechanisms and lack of correlatio…
Seed3D 1.0: From Images to High-Fidelity Simulation-Ready 3D Assets
Jiashi Feng, Xiu Li, Jing Lin +25
Developing embodied AI agents requires scalable training environments that balance content diversity with physics accuracy. World simulators provide such environments but face dist…
AI+CAD Data Representation Architecture: From DeepCAD Solid Modeling to WHUCAD Industrial-Level Parametric Feature Modeling
Rubin Fan, Fazhi He, Yuxin Liu +4
In July 2025, Study Times, sponsored by the Party School of the Central Committee of the CPC, pointed out that 95% of industrial software for R&D and design in China relies on impo…
FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
Guangda Liu, Chengwei Li, Zhenyu Ning +5
Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant depl…
DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization
Yuantian Shao, Yuanteng Chen, Peisong Wang +5
Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by sm…
TopoMesh: High-Fidelity Mesh Autoencoding via Topological Unification
Guan Luo, Xiu Li, Rui Chen +6
The dominant paradigm for high-fidelity 3D generation relies on a VAE-Diffusion pipeline, where the VAE's reconstruction capability sets a firm upper bound on generation quality. A…
Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks
Tianhe Ren, Shilong Liu, Ailing Zeng +14
We introduce Grounded SAM, which uses Grounding DINO as an open-set object detector to combine with the segment anything model (SAM). This integration enables the detection and seg…
Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction
Yuanhao Cai, Jing Lin, Xiaowan Hu +5
Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i.e., recovering the 3D hyperspectral images (HSIs) from a 2D…
An Adversarial Attack Defending System for Securing In-Vehicle Networks
Yi Li, Jing Lin, Kaiqi Xiong
In a modern vehicle, there are over seventy Electronics Control Units (ECUs). For an in-vehicle network, ECUs communicate with each other by following a standard communication prot…
Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions
Jianan Wang, Boyang Li, Xiangyu Fan +2
The task of video and text sequence alignment is a prerequisite step toward joint understanding of movie videos and screenplays. However, supervised methods face the obstacle of li…
HumanTOMATO: Text-aligned Whole-body Motion Generation
Shunlin Lu, Ling-Hao Chen, Ailing Zeng +4
This work targets a novel text-driven whole-body motion generation task, which takes a given textual description as input and aims at generating high-quality, diverse, and coherent…
Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers
Haosong Liu, Yuge Cheng, Wenxuan Miao +8
Video diffusion transformers (vDiTs) have made tremendous progress in text-to-video generation, but their high compute demands pose a major challenge for practical deployment. Whil…
A comprehensive review on convolutional neural network in machine fault diagnosis
Jinyang Jiao, Ming Zhao, Jing Lin +1
With the rapid development of manufacturing industry, machine fault diagnosis has become increasingly significant to ensure safe equipment operation and production. Consequently, m…
BinaryHPE: 3D Human Pose and Shape Estimation via Binarization
Zhiteng Li, Yulun Zhang, Jing Lin +5
3D human pose and shape estimation (HPE) aims to reconstruct the 3D human body, face, and hands from a single image. Although powerful deep learning models have achieved accurate e…
HumanMM: Global Human Motion Recovery from Multi-shot Videos
Yuhong Zhang, Guanlin Wu, Ling-Hao Chen +8
In this paper, we present a novel framework designed to reconstruct long-sequence 3D human motion in the world coordinates from in-the-wild videos with multiple shot transitions. S…
ChatPose: Chatting about 3D Human Pose
Yao Feng, Jing Lin, Sai Kumar Dwivedi +3
We introduce ChatPose, a framework employing Large Language Models (LLMs) to understand and reason about 3D human poses from images or textual descriptions. Our work is motivated b…
RainFusion2.0: Temporal-Spatial Awareness and Hardware-Efficient Block-wise Sparse Attention
Aiyue Chen, Yaofu Liu, Junjian Huang +6
In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applicati…
RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy
Aiyue Chen, Bin Dong, Jingru Li +4
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computati…
Identifiability Study of Lithium-Ion Battery Capacity Fade Using Degradation Mode Sensitivity for a Minimally and Intuitively Parametrized Electrode-Specific Cell Open-Circuit Voltage Model
Jing Lin, Edwin Khoo
When two electrode open-circuit potentials form a full-cell OCV (open-circuit voltage) model, cell-level SOH (state of health) parameters related to LLI (loss of lithium inventory)…
Improving Machine Learning Robustness via Adversarial Training
Long Dang, Thushari Hapuarachchi, Kaiqi Xiong +1
As Machine Learning (ML) is increasingly used in solving various tasks in real-world applications, it is crucial to ensure that ML algorithms are robust to any potential worst-case…