papers

Publications (62)

eess.IV2026

Blind Quality Enhancement for G-PCC Compressed Dynamic Point Clouds

Tian Guo, Hui Yuan, Chang Sun +3

Point cloud compression often introduces noticeable reconstruction artifacts, which makes quality enhancement necessary. Existing approaches typically assume prior knowledge of the…

physics.optics2019

Frequency comb generation at 800nm in waveguide array quantum well diode lasers

Chang Sun, Mark Dong, Niall M. Mangan +3

A traveling wave model for a semiconductor diode laser based on quantum wells is presented as well as a comprehensive theoretical model of the lasing dynamics produced by the inten…

eess.IV2021

A Lightweight Structure Aimed to Utilize Spatial Correlation for Sparse-View CT Reconstruction

Yitong Liu, Ken Deng, Chang Sun +1

Sparse-view computed tomography (CT) is known as a widely used approach to reduce radiation dose while accelerating imaging through lowered projection views and correlated calculat…

cs.CY2018

Analyzing Partitioned FAIR Health Data Responsibly

Chang Sun, Lianne Ippel, Birgit Wouters +11

It is widely anticipated that the use of health-related big data will enable further understanding and improvements in human health and wellbeing. Our current project, funded throu…

eess.IV2026

Point Cloud Feature Coding for Object Detection over an Error-Prone Cloud-Edge Collaborative System

Chongzhen Tian, Hui Yuan, Pan Zhao +3

Cloud-edge collaboration enhances machine perception by combining the strengths of edge and cloud computing. Edge devices capture raw data (e.g., 3D point clouds) and extract salie…

eess.IV2022

A Lightweight Dual-Domain Attention Framework for Sparse-View CT Reconstruction

Chang Sun, Ken Deng, Yitong Liu +1

Computed Tomography (CT) plays an essential role in clinical diagnosis. Due to the adverse effects of radiation on patients, the radiation dose is expected to be reduced as low as…

cs.AR2026

da4ml: Distributed Arithmetic for Real-time Neural Networks on FPGAs

Chang Sun, Zhiqiang Que, Vladimir Loncar +2

Neural networks with a latency requirement on the order of microseconds, like the ones used at the CERN Large Hadron Collider, are typically deployed on FPGAs fully unrolled and pi…

cs.CV2024

JEP-KD: Joint-Embedding Predictive Architecture Based Knowledge Distillation for Visual Speech Recognition

Chang Sun, Hong Yang, Bo Qin

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limita…

physics.optics2019

Stable Numerical Schemes for Nonlinear Dispersive Equations with Counter-Propagation and Gain Dynamics

Chang Sun, Niall Mangan, Mark Dong +3

We develop a stable and efficient numerical scheme for modeling the optical field evolution in a nonlinear dispersive cavity with counter propagating waves and complex, semiconduct…

physics.ins-det2022

Fast Muon Tracking with Machine Learning Implemented in FPGA

Chang Sun, Takumi Nakajima, Yuki Mitsumori +2

In this work, we present a new approach for fast tracking on multiwire proportional chambers with neural networks. The tracking networks are developed and adapted for the first-lev…

cs.CV2026

CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

Mahmoud Ibrahim, Bart Elen, Chang Sun +2

Generative models are increasingly used to augment medical imaging datasets for fairer AI, yet a key assumption often goes unexamined: that generators produce equally high-quality…

physics.flu-dyn2025

A Central Differential Flux with High-Order Dissipation for Robust Simulations of Transcritical Flows

Bonan Xu, Chang Sun, Peixu Guo

The simulation of transcritical flows remains challenging due to strong thermodynamic nonlinearities that induce spurious pressure oscillations in conventional schemes.While primit…

hep-ex2025

JEDI-linear: Fast and Efficient Graph Neural Networks for Jet Tagging on FPGAs

Zhiqiang Que, Chang Sun, Sudarshan Paramesvaran +8

Graph Neural Networks (GNNs), particularly Interaction Networks (INs), have shown exceptional performance for jet tagging at the CERN High-Luminosity Large Hadron Collider (HL-LHC)…

hep-ex2025

RINO: Renormalization Group Invariance with No Labels

Zichun Hao, Raghav Kansal, Abhijith Gandrakota +4

A common challenge with supervised machine learning (ML) in high energy physics (HEP) is the reliance on simulations for labeled data, which can often mismodel the underlying colli…

cs.LG2026

PQuantML: A Tool for End-to-End Hardware-aware Model Compression

Roope Niemi, Anastasiia Petrovych, Arghya Ranjan Das +9

PQuantML is a new open-source, hardware-aware neural network model compression library tailored to end-to-end workflows. Motivated by the need to deploy performant models to enviro…

eess.SP2020

Deep reinforcement learning for optical systems: A case study of mode-locked lasers

Chang Sun, Eurika Kaiser, Steven L. Brunton +1

We demonstrate that deep reinforcement learning (deep RL) provides a highly effective strategy for the control and self-tuning of optical systems. Deep RL integrates the two leadin…

cs.SD2025

DualStream Contextual Fusion Network: Efficient Target Speaker Extraction by Leveraging Mixture and Enrollment Interactions

Ke Xue, Rongfei Fan, Shanping Yu +2

Target speaker extraction focuses on extracting a target speech signal from an environment with multiple speakers by leveraging an enrollment. Existing methods predominantly rely o…

cs.CV2026

Streamlined Open-Vocabulary Human-Object Interaction Detection

Chang Sun, Dongliang Liao, Changxing Ding

Open-vocabulary human-object interaction (HOI) detection aims to localize and recognize all human-object interactions in an image, including those unseen during training. Existing…

cs.CV2026

SLAMFormer-: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing

Zhijian Fang, Weicheng Zheng, Yijun Yuan +7

We introduce the Infinite SLAM Transformer (SLAMFormer-), the first geometric transformer capable of supporting both long-range frontend and backend processing without an e…

cs.SD2026

Omni-directional attention mechanism based on Mamba for speech separation

Ke Xue, Chang Sun, Rongfei Fan +2

Mamba, a selective state-space model (SSM), has emerged as an efficient alternative to Transformers for speech modeling, enabling long-sequence processing with linear complexity. W…

nlin.PS2018

Stability and Dynamics of Microring Combs: Elliptic function solutions of the Lugiato-Lefever equation

Chang Sun, Travis Askham, J. Nathan Kutz

We consider a new class of periodic solutions to the Lugiato-Lefever equations (LLE) that govern the electromagnetic field in a microresonator cavity. Specifically, we rigorously c…

eess.IV2024

Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction

Chang Sun, Hui Yuan, Xiaolong Mao +2

In point cloud geometry compression, most octreebased context models use the cross-entropy between the onehot encoding of node occupancy and the probability distribution predicted…

eess.IV2026

Inter-LPCM: Learning-based Inter-Frame Predictive Coding for LiDAR Point Cloud Compression

Chang Sun, Hui Yuan, Shiqi Jiang +3

Because LiDAR sensors acquire point clouds with a fixed angular resolution, the resulting data can be systematically parameterized and efficiently compressed in the spherical coord…

cs.LG2022

Physical Logic Enhanced Network for Small-Sample Bi-Layer Metallic Tubes Bending Springback Prediction

Chang Sun, Zili Wang, Shuyou Zhang +2

Bi-layer metallic tube (BMT) plays an extremely crucial role in engineering applications, with rotary draw bending (RDB) the high-precision bending processing can be achieved, howe…

cs.CV2026

Segmentation of Gray Matters and White Matters from Brain MRI data

Chang Sun, Rui Shi, Tsukasa Koike +3

Accurate segmentation of brain tissues such as gray matter and white matter from magnetic resonance imaging is essential for studying brain anatomy, diagnosing neurological disorde…

cs.AR2025

hls4ml: A Flexible, Open-Source Platform for Deep Learning Acceleration on Reconfigurable Hardware

Jan-Frederik Schulte, Benjamin Ramhorst, Chang Sun +50

We present hls4ml, a free and open-source platform that translates machine learning (ML) models from modern deep learning frameworks into high-level synthesis (HLS) code that can b…

cs.DL2021

Knowledge Graph for Microdata of Statistics Netherlands

Chang Sun

Statistics Netherlands (CBS) hosted a huge amount of data not only on the statistical level but also on the individual level. With the development of data science technologies, mor…

eess.IV2021

Real-Time Limited-View CT Inpainting and Reconstruction with Dual Domain Based on Spatial Information

Ken Deng, Chang Sun, Yitong Liu +1

Low-dose Computed Tomography is a common issue in reality. Current reduction, sparse sampling and limited-view scanning can all cause it. Between them, limited-view CT is general i…

cs.CY2023

TAPS Responsibility Matrix: A tool for responsible data science by design

Visara Urovi, Remzi Celebi, Chang Sun +6

Data science is an interdisciplinary research area where scientists are typically working with data coming from different fields. When using and analyzing data, the scientists impl…

astro-ph.HE2025

From Black Hole to Galaxy: Neural Operator: Framework for Accretion and Feedback Dynamics

Nihaal Bhojwani, Chuwei Wang, Hai-Yang Wang +3

Modeling how supermassive black holes co-evolve with their host galaxies is notoriously hard because the relevant physics spans nine orders of magnitude in scale-from milliparsecs…

cs.LG2019

Privacy-Preserving Generalized Linear Models using Distributed Block Coordinate Descent

Erik-Jan van Kesteren, Chang Sun, Daniel L. Oberski +2

Combining data from varied sources has considerable potential for knowledge discovery: collaborating data parties can mine data in an expanded feature space, allowing them to explo…

physics.ins-det2025

Fast Jet Tagging with MLP-Mixers on FPGAs

Chang Sun, Jennifer Ngadiuba, Maurizio Pierini +1

We explore the innovative use of MLP-Mixer models for real-time jet tagging and establish their feasibility on resource-constrained hardware like FPGAs. MLP-Mixers excel in process…

cs.CL2026

Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law

Noah Scharrenberg, Chang Sun

Large language models (LLM) trained on web-scale corpora generate output that may infringe copyright, yet existing technical safeguards focus narrowly on verbatim memorisation. EU…

cs.LG2024

Empirical Privacy Evaluations of Generative and Predictive Machine Learning Models -- A review and challenges for practice

Flavio Hafner, Chang Sun

Synthetic data generators, when trained using privacy-preserving techniques like differential privacy, promise to produce synthetic data with formal privacy guarantees, facilitatin…

cs.LG2024

Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges

Mahmoud Ibrahim, Yasmina Al Khalil, Sina Amirrajab +6

This paper presents a comprehensive systematic review of generative models (GANs, VAEs, DMs, and LLMs) used to synthesize various medical data types, including imaging (dermoscopic…

cs.AI2020

Knowledge Graphs Evolution and Preservation -- A Technical Report from ISWS 2019

Nacira Abbas, Kholoud Alghamdi, Mortaza Alinam +71

One of the grand challenges discussed during the Dagstuhl Seminar "Knowledge Graphs: New Directions for Knowledge Representation on the Semantic Web" and described in its report is…

hep-ex2026

Patch Hierarchical Attention Transformer for Efficient Particle Jet Tagging

Aaron Wang, Zihan Zhao, Alan Xia +5

Real-time jet tagging is critical for identifying short-lived particle decays in the high-throughput detectors of the Large Hadron Collider, where real-time trigger systems respons…

cs.AI2026

PowerLens: Taming LLM Agents for Safe and Personalized Mobile Power Management

Xingyu Feng, Chang Sun, Yuzhu Wang +5

Battery life remains a critical challenge for mobile devices, yet existing power management mechanisms rely on static rules or coarse-grained heuristics that ignore user activities…

cs.CV2025

Adapting Lightweight Vision Language Models for Radiological Visual Question Answering

Aditya Shourya, Michel Dumontier, Chang Sun

Recent advancements in vision-language systems have improved the accuracy of Radiological Visual Question Answering (VQA) Models. However, some challenges remain across each stage…

cs.SD2024

X-CrossNet: A complex spectral mapping approach to target speaker extraction with cross attention speaker embedding fusion

Chang Sun, Bo Qin

Target speaker extraction (TSE) is a technique for isolating a target speaker's voice from mixed speech using auxiliary features associated with the target speaker. It is another a…

cs.CR2022

Assessing the Solid Protocol in Relation to Security & Privacy Obligations

Christian Esposito, Olaf Hartig, Ross Horne +1

The Solid specification aims to empower data subjects by giving them direct access control over their data across multiple applications. As governments are manifesting their intere…

cs.LG2026

AIE4ML: An End-to-End Framework for Compiling Neural Networks for the Next Generation of AMD AI Engines

Dimitrios Danopoulos, Enrico Lupi, Chang Sun +4

Efficient AI inference on AMD's Versal AI Engine (AIE) is challenging due to tightly coupled VLIW execution, explicit datapaths, and local memory management. Prior work focused on…

math.DS2025

Equivalent Conditions for Domination of -sequences

Chang Sun, Zhenghe Zhang

It is well known that a -sequence is uniformly hyperbolic if and only it satisfies a uniform exponential growth condition. Similarly, for $\mathrm{GL}(2,…

cs.CL2026

Recent Advances in Multimodal Affective Computing: An NLP Perspective

Guimin Hu, Weimin Lyu, Chang Sun +5

Multimodal affective computing has gained increasing attention due to its broad applications in understanding human behavior and intentions, particularly in text-centric multimodal…

cs.HC2025

Towards Computer-Using Personal Agents

Piero A. Bonatti, John Domingue, Anna Lisa Gentile +9

Computer-Using Agents (CUA) enable users to automate increasingly-complex tasks using graphical interfaces such as browsers. As many potential tasks require personal data, we propo…

cs.CV2025

Bilateral Collaboration with Large Vision-Language Models for Open Vocabulary Human-Object Interaction Detection

Yupeng Hu, Changxing Ding, Chang Sun +2

Open vocabulary Human-Object Interaction (HOI) detection is a challenging task that detects all <human, verb, object> triplets of interest in an image, even those that are not pre-…

eess.IV2024

Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss

Chang Sun, Hui Yuan, Shuai Li +2

In point cloud geometry compression, context models usually use the one-hot encoding of node occupancy as the label, and the cross-entropy between the one-hot encoding and the prob…

cs.AR2026

HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference

Chang Sun, Zhiqiang Que, Bakhtiar Zadeh +4

Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitive…

cs.CV2025

VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance

Chang Sun, Dongliang Xie, Wanpeng Xie +2

Visual speech recognition (VSR) aims to transcribe spoken content from silent lip-motion videos and is particularly challenging in Mandarin due to severe viseme ambiguity and perva…

cs.LG2026

The Impact of Machine Learning Uncertainty on the Robustness of Counterfactual Explanations

Leonidas Christodoulou, Chang Sun

Counterfactual explanations are widely used to interpret machine learning predictions by identifying minimal changes to input features that would alter a model's decision. However,…

cs.LG2023

KDSM: An uplift modeling framework based on knowledge distillation and sample matching

Chang Sun, Qianying Li, Guanxiang Wang +2

Uplift modeling aims to estimate the treatment effect on individuals, widely applied in the e-commerce platform to target persuadable customers and maximize the return of marketing…

cs.CV2026

DUGAE: Unified Geometry and Attribute Enhancement via Spatiotemporal Correlations for G-PCC Compressed Dynamic Point Clouds

Pan Zhao, Hui Yuan, Chang Sun +3

Existing post-decoding quality enhancement methods for point clouds are designed for static data and typically process each frame independently. As a result, they cannot effectivel…

physics.ins-det2025

Sub-microsecond Transformers for Jet Tagging on FPGAs

Lauri Laatu, Chang Sun, Arianna Cox +7

We present the first sub-microsecond transformer implementation on an FPGA achieving competitive performance for state-of-the-art high-energy physics benchmarks. Transformers have…

cs.LG2026

JetFormer: A Scalable and Efficient Transformer for Jet Tagging from Offline Analysis to FPGA Triggers

Ruoqing Zheng, Chang Sun, Qibin Liu +7

We present JetFormer, a versatile and scalable encoder-only Transformer architecture for particle jet tagging at the Large Hadron Collider (LHC). Unlike prior approaches that are o…

hep-ex2025

It's not a FAD: first results in using Flows for unsupervised Anomaly Detection at 40 MHz at the Large Hadron Collider

Francesco Vaselli, Chang Sun, Thea Aarrestad +7

We present the first implementation of a Continuous Normalizing Flow (CNF) model for unsupervised anomaly detection within the realistic, high-rate environment of the Large Hadron…

cs.LG2022

Digital-twin-enhanced metal tube bending forming real-time prediction method based on Multi-source-input MTL

Chang Sun, Zili Wang, Shuyou Zhang +3

As one of the most widely used metal tube bending methods, the rotary draw bending (RDB) process enables reliable and high-precision metal tube bending forming (MTBF). The forming…

eess.IV2025

LPCM: Learning-based Predictive Coding for LiDAR Point Cloud Compression

Chang Sun, Hui Yuan, Shiqi Jiang +3

Since the data volume of LiDAR point clouds is very huge, efficient compression is necessary to reduce their storage and transmission costs. However, existing learning-based compre…

cs.LG2025

Enabling Granular Subgroup Level Model Evaluations by Generating Synthetic Medical Time Series

Mahmoud Ibrahim, Bart Elen, Chang Sun +2

We present a novel framework for leveraging synthetic ICU time-series data not only to train but also to rigorously and trustworthily evaluate predictive models, both at the popula…

cs.IR2025

CLLMRec: LLM-powered Cognitive-Aware Concept Recommendation via Semantic Alignment and Prerequisite Knowledge Distillation

Xiangrui Xiong, Yichuan Lu, Zifei Pan +1

The growth of Massive Open Online Courses (MOOCs) presents significant challenges for personalized learning, where concept recommendation is crucial. Existing approaches typically…

cs.AI2026

Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers

Mahmoud Ibrahim, Bart Elen, Chang Sun +2

The paper proposes using a demographically-conditioned synthetic image generator to both improve fairness in training medical image classifiers and to provide more reliable bias de…

#bias mitigation#synthetic data generation#medical imaging#fairness auditing
cs.LG2025

HGQ: High Granularity Quantization for Real-time Neural Networks on FPGAs

Chang Sun, Zhiqiang Que, Thea K. Ã rrestad +4

Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quanti…

cs.LG2022

Improving Correlation Capture in Generating Imbalanced Data using Differentially Private Conditional GANs

Chang Sun, Johan van Soest, Michel Dumontier

Despite the remarkable success of Generative Adversarial Networks (GANs) on text, images, and videos, generating high-quality tabular data is still under development owing to some…