Lequan Yu
YOU?
Author Swipe
View article: FDP: A Frequency-Decomposition Preprocessing Pipeline for Unsupervised Anomaly Detection in Brain MRI
FDP: A Frequency-Decomposition Preprocessing Pipeline for Unsupervised Anomaly Detection in Brain MRI Open
Due to the diversity of brain anatomy and the scarcity of annotated data, supervised anomaly detection for brain MRI remains challenging, driving the development of unsupervised anomaly detection (UAD) approaches. Current UAD methods typic…
View article: Cross-Modal Alignment via Variational Copula Modelling
Cross-Modal Alignment via Variational Copula Modelling Open
Various data modalities are common in real-world applications (e.g., electronic health records, medical images and clinical notes in healthcare). It is essential to develop multimodal learning methods to aggregate various information from …
View article: Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process
Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process Open
Developing effective multimodal fusion approaches has become increasingly essential in many real-world scenarios, such as health care and finance. The key challenge is how to preserve the feature expressiveness in each modality while learn…
View article: MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning
MedMMV: A Controllable Multimodal Multi-Agent Framework for Reliable and Verifiable Clinical Reasoning Open
Recent progress in multimodal large language models (MLLMs) has demonstrated promising performance on medical benchmarks and in preliminary trials as clinical assistants. Yet, our pilot audit of diagnostic cases uncovers a critical failure…
View article: Large Material Gaussian Model for Relightable 3D Generation
Large Material Gaussian Model for Relightable 3D Generation Open
The increasing demand for 3D assets across various industries necessitates efficient and automated methods for 3D content creation. Leveraging 3D Gaussian Splatting, recent large reconstruction models (LRMs) have demonstrated the ability t…
View article: A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers Open
Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a compre…
View article: Automated cardiac magnetic resonance interpretation derived from prompted large language models
Automated cardiac magnetic resonance interpretation derived from prompted large language models Open
LLMs demonstrated outstanding performance in the automated classification and diagnosis of targeted CMR interpretations, especially with informative prompts, suggesting the potential for these models to serve as adjunct tools in CMR diagno…
View article: Democratizing large language model-based graph data augmentation via latent knowledge graphs
Democratizing large language model-based graph data augmentation via latent knowledge graphs Open
Data augmentation is necessary for graph representation learning due to the scarcity and noise present in graph data. Most of the existing augmentation methods overlook the context information inherited from the dataset as they rely solely…
View article: HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis
HyperPath: Knowledge-Guided Hyperbolic Semantic Hierarchy Modeling for WSI Analysis Open
Pathology is essential for cancer diagnosis, with multiple instance learning (MIL) widely used for whole slide image (WSI) analysis. WSIs exhibit a natural hierarchy -- patches, regions, and slides -- with distinct semantic associations. W…
View article: From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining
From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining Open
Electrocardiograms (ECGs) play a vital role in monitoring cardiac health and diagnosing heart diseases. However, traditional deep learning approaches for ECG analysis rely heavily on large-scale manual annotations, which are both time-cons…
View article: StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation
StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation Open
In the current research landscape, multimodal autoregressive (AR) models have shown exceptional capabilities across various domains, including visual understanding and generation. However, complex tasks such as style-aligned text-to-image …
View article: Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior
Feature Preserving Shrinkage on Bayesian Neural Networks via the R2D2 Prior Open
Bayesian neural networks (BNNs) treat neural network weights as random variables, which aim to provide posterior uncertainty estimates and avoid overfitting by performing inference on the posterior weights. However, the selection of approp…
View article: Large Images Are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
Large Images Are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting Open
While Implicit Neural Representations (INRs) have demonstrated significant success in image representation, they are often hindered by large training memory and slow decoding speed. Recently, Gaussian Splatting (GS) has emerged as a promis…
View article: Dynamic Entity-Masked Graph Diffusion Model for Histopathology Image Representation Learning
Dynamic Entity-Masked Graph Diffusion Model for Histopathology Image Representation Learning Open
Significant disparities between the features of natural images and those inherent to histopathological images make it challenging to directly apply and transfer pre-trained models from natural images to histopathology tasks. Moreover, the …
View article: Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation
Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation Open
Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation. Despite their strong perfor…
View article: Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs
Democratizing Large Language Model-Based Graph Data Augmentation via Latent Knowledge Graphs Open
Data augmentation is necessary for graph representation learning due to the scarcity and noise present in graph data. Most of the existing augmentation methods overlook the context information inherited from the dataset as they rely solely…
View article: Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting Open
While Implicit Neural Representations (INRs) have demonstrated significant success in image representation, they are often hindered by large training memory and slow decoding speed. Recently, Gaussian Splatting (GS) has emerged as a promis…
View article: From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics Open
The depth of neural networks is a critical factor for their capability, with deeper models often demonstrating superior performance. Motivated by this, significant efforts have been made to enhance layer aggregation - reusing information f…
View article: Automatic identification of human spermatozoa with zona pellucida-binding capability using deep learning
Automatic identification of human spermatozoa with zona pellucida-binding capability using deep learning Open
STUDY QUESTION Can a deep-learning algorithm, independent of World Health Organization (WHO) sperm morphology grading, be used to identify human spermatozoa with zona pellucida (ZP)-binding capability in assisted reproductive technology (A…
View article: CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis
CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis Open
View article: Predicting Neoadjuvant Chemotherapy Response in Gastric Cancer Using Pathology-Based Ensemble Learning
Predicting Neoadjuvant Chemotherapy Response in Gastric Cancer Using Pathology-Based Ensemble Learning Open
View article: Aligning knowledge concepts to whole slide images for precise histopathology image analysis
Aligning knowledge concepts to whole slide images for precise histopathology image analysis Open
View article: Dynamic Entity-Masked Graph Diffusion Model for histopathological image Representation Learning
Dynamic Entity-Masked Graph Diffusion Model for histopathological image Representation Learning Open
Significant disparities between the features of natural images and those inherent to histopathological images make it challenging to directly apply and transfer pre-trained models from natural images to histopathology tasks. Moreover, the …
View article: A Novel Platform Featuring Nanomagnetic Ligand Fishing Based on Fixed-Orientation Immobilized Magnetic Beads for Screening Potential Cyclooxygenase-2 Inhibitors from Panax notoginseng Leaves
A Novel Platform Featuring Nanomagnetic Ligand Fishing Based on Fixed-Orientation Immobilized Magnetic Beads for Screening Potential Cyclooxygenase-2 Inhibitors from Panax notoginseng Leaves Open
A novel screening platform based on an Fe3O4@C@PDA-Ni2+@COX-2 ligand fishing combination with high-performance liquid chromatography–mass spectrometry was first designed, synthesized, and employed to screen and identify COX-2 inhibitors fr…
View article: Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis
Aligning Knowledge Concepts to Whole Slide Images for Precise Histopathology Image Analysis Open
Due to the large size and lack of fine-grained annotation, Whole Slide Images (WSIs) analysis is commonly approached as a Multiple Instance Learning (MIL) problem. However, previous studies only learn from training data, posing a stark con…
View article: Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement Open
Whole slide image (WSI) analysis is gaining prominence within the medical imaging field. Recent advances in pathology foundation models have shown the potential to extract powerful feature representations from WSIs for downstream tasks. Ho…
View article: Camera-view supervision for bird's-eye-view semantic segmentation
Camera-view supervision for bird's-eye-view semantic segmentation Open
Bird's-eye-view Semantic Segmentation (BEVSS) is a powerful and crucial component of planning and control systems in many autonomous vehicles. Current methods rely on end-to-end learning to train models, leading to indirectly supervised an…
View article: CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis
CTPD: Cross-Modal Temporal Pattern Discovery for Enhanced Multimodal Electronic Health Records Analysis Open
Integrating multimodal Electronic Health Records (EHR) data, such as numerical time series and free-text clinical reports, has great potential in predicting clinical outcomes. However, prior work has primarily focused on capturing temporal…
View article: ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities
ToolBridge: An Open-Source Dataset to Equip LLMs with External Tool Capabilities Open
Through the integration of external tools, large language models (LLMs) such as GPT-4o and Llama 3.1 significantly expand their functional capabilities, evolving from elementary conversational agents to general-purpose assistants. We argue…
View article: Multi-sensor Learning Enables Information Transfer across Different Sensory Data and Augments Multi-modality Imaging
Multi-sensor Learning Enables Information Transfer across Different Sensory Data and Augments Multi-modality Imaging Open
Multi-modality imaging is widely used in clinical practice and biomedical research to gain a comprehensive understanding of an imaging subject. Currently, multi-modality imaging is accomplished by post hoc fusion of independently reconstru…