Chenyu You
YOU?
Author Swipe
View article: 3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation
3D Wavelet Latent Diffusion Model for Whole-Body MR-to-CT Modality Translation Open
Magnetic Resonance (MR) imaging plays an essential role in contemporary clinical diagnostics. It is increasingly integrated into advanced therapeutic workflows, such as hybrid Positron Emission Tomography/Magnetic Resonance (PET/MR) imagin…
View article: Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions Open
Synthesizing realistic Martian landscape videos is crucial for mission rehearsal and robotic simulation. However, this task poses unique challenges due to the scarcity of high-quality Martian data and the significant domain gap between Mar…
View article: HOMER: Homography-Based Efficient Multi-view 3D Object Removal
HOMER: Homography-Based Efficient Multi-view 3D Object Removal Open
3D object removal is an important sub-task in 3D scene editing, with broad applications in scene understanding, augmented reality, and robotics. However, existing methods struggle to achieve a desirable balance among consistency, usability…
View article: PET Head Motion Estimation Using Supervised Deep Learning with Attention
PET Head Motion Estimation Using Supervised Deep Learning with Attention Open
Head movement poses a significant challenge in brain positron emission tomography (PET) imaging, resulting in image artifacts and tracer uptake quantification inaccuracies. Effective head motion estimation and correction are crucial for pr…
View article: Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks
Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks Open
Large language models (LLMs) are widely adapted for downstream applications through fine-tuning, a process named customization. However, recent studies have identified a vulnerability during this process, where malicious samples can compro…
View article: Imaging foundation model for universal enhancement of non-ideal measurement CT
Imaging foundation model for universal enhancement of non-ideal measurement CT Open
Non-ideal measurement computed tomography (NICT) employs suboptimal imaging protocols to expand CT applications. However, the resulting trade-offs degrade image quality, limiting clinical acceptability. Although deep learning methods have …
View article: A Flow-based Truncated Denoising Diffusion Model for super-resolution Magnetic Resonance Spectroscopic Imaging
A Flow-based Truncated Denoising Diffusion Model for super-resolution Magnetic Resonance Spectroscopic Imaging Open
Magnetic Resonance Spectroscopic Imaging (MRSI) is a non-invasive imaging technique for studying metabolism and has become a crucial tool for understanding neurological diseases, cancers and diabetes. High spatial resolution MRSI is needed…
View article: Medical image registration via neural fields
Medical image registration via neural fields Open
Image registration is an essential step in many medical image analysis tasks. Traditional methods for image registration are primarily optimization-driven, finding the optimal deformations that maximize the similarity between two images. R…
View article: Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations
Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations Open
Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive a…
View article: Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation
Cross-Modal Conditioned Reconstruction for Language-guided Medical Image Segmentation Open
Recent developments underscore the potential of textual information in enhancing learning models for a deeper understanding of medical visual semantics. However, language-guided medical image segmentation still faces a challenging issue. P…
View article: Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations
Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations Open
Fine-tuning pre-trained vision-language models, like CLIP, has yielded success on diverse downstream tasks. However, several pain points persist for this paradigm: (i) directly tuning entire pre-trained models becomes both time-intensive a…
View article: Rescuing missing data in connectome-based predictive modeling
Rescuing missing data in connectome-based predictive modeling Open
Recent evidence suggests brain-phenotype predictions may require very large sample sizes. However, as the sample size increases, missing data also increase. Conventional methods, like complete-case analysis, discard useful information and …
View article: Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP
Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP Open
In recent years, foundation models (FMs) have solidified their role as cornerstone advancements in the deep learning domain. By extracting intricate patterns from vast datasets, these models consistently achieve state-of-the-art results ac…
View article: A medical multimodal large language model for future pandemics
A medical multimodal large language model for future pandemics Open
Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Since most neural networks are supervised, their performance…
View article: Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration
Heteroscedastic Uncertainty Estimation Framework for Unsupervised Registration Open
Deep learning methods for unsupervised registration often rely on objectives that assume a uniform noise level across the spatial domain (e.g. mean-squared error loss), but noise distributions are often heteroscedastic and input-dependent …
View article: Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model Open
Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have sh…
View article: MARGANVAC: metal artifact reduction method based on generative adversarial network with variable constraints
MARGANVAC: metal artifact reduction method based on generative adversarial network with variable constraints Open
Objective. Metal artifact reduction (MAR) has been a key issue in CT imaging. Recently, MAR methods based on deep learning have achieved promising results. However, when deploying deep learning-based MAR in real-world clinical scenarios, t…
View article: LLMRec: Benchmarking Large Language Models on Recommendation Task
LLMRec: Benchmarking Large Language Models on Recommendation Task Open
Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversational models. However, the application of LLMs in the recommendation domain has n…
View article: Attention Calibration for Transformer-based Sequential Recommendation
Attention Calibration for Transformer-based Sequential Recommendation Open
Transformer-based sequential recommendation (SR) has been booming in recent years, with the self-attention mechanism as its key component. Self-attention has been widely believed to be able to effectively select those informative and relev…
View article: A Multimodal Large Language Modelling Deep Learning Framework for the Future Pandemic
A Multimodal Large Language Modelling Deep Learning Framework for the Future Pandemic Open
Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Typical applications include 1) medical report generation, 2…
View article: A Multiclass Radiomics Method–Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans
A Multiclass Radiomics Method–Based WHO Severity Scale for Improving COVID-19 Patient Assessment and Disease Characterization From CT Scans Open
Objectives The aim of this study was to evaluate the severity of COVID-19 patients' disease by comparing a multiclass lung lesion model to a single-class lung lesion model and radiologists' assessments in chest computed tomography scans. M…
View article: Hybrid-CSR: Coupling Explicit and Implicit Shape Representation for Cortical Surface Reconstruction
Hybrid-CSR: Coupling Explicit and Implicit Shape Representation for Cortical Surface Reconstruction Open
We present Hybrid-CSR, a geometric deep-learning model that combines explicit and implicit shape representations for cortical surface reconstruction. Specifically, Hybrid-CSR begins with explicit deformations of template meshes to obtain c…
View article: Multimodal Prompt Learning for Product Title Generation with Extremely Limited Labels
Multimodal Prompt Learning for Product Title Generation with Extremely Limited Labels Open
Generating an informative and attractive title for the product is a crucial task for e-commerce. Most existing works follow the standard multimodal natural language generation approaches, e.g., image captioning, and employ the large scale …
View article: Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation
Multi-task Item-attribute Graph Pre-training for Strict Cold-start Item Recommendation Open
Recommendation systems suffer in the strict cold-start (SCS) scenario, where the user-item interactions are entirely unavailable. The ID-based approaches completely fail to work. Cold-start recommenders, on the other hand, leverage item co…
View article: Rescuing missing data in connectome-based predictive modeling
Rescuing missing data in connectome-based predictive modeling Open
Recent evidence suggests brain-behavior predictions may require very large sample sizes. However, as the sample size increases, the amount of missing data also increases. Conventional methods, like complete-case analysis, discard useful in…
View article: Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset
Benchmarking Large Language Models on CMExam -- A Comprehensive Chinese Medical Exam Dataset Open
Recent advancements in large language models (LLMs) have transformed the field of question answering (QA). However, evaluating LLMs in the medical field is challenging due to the lack of standardized and comprehensive datasets. To address …
View article: Large Language Models Are Partially Primed in Pronoun Interpretation
Large Language Models Are Partially Primed in Pronoun Interpretation Open
While a large body of literature suggests that large language models (LLMs) acquire rich linguistic representations, little is known about whether they adapt to linguistic biases in a human-like way. The present study probes this question …
View article: A Large Language Modelling Deep Learning Framework for the Next Pandemic
A Large Language Modelling Deep Learning Framework for the Next Pandemic Open
Deep neural networks have been integrated into the whole clinical decision procedure which can improve the efficiency of diagnosis and alleviate the heavy workload of physicians. Typical applications include 1) medical report generation, 2…