2 citations · 4 across the 18 of their papers we have counts for
18 papers
DiffPrune: differentiable information throttling for token pruning in vision-language models
Landi He, Mingde Yao, Shawn Young +1
Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. The key is to learn a score that measures whether a token…
Decoupling semantics from vision: A framework for faithful visual-text compression evaluation
Yonghan Gao, Zehong Chen, Lijian Xu +3
Recent visual-text compression (VTC) methods, typified by DeepSeek-OCR, report impressive high token compression ratios for long-context modeling tasks by leveraging text-to-image…
PathSelect: Sequential Token Selection for Whole Slide Pathology
Jingzhi Chen, Landi He, Zehong Chen +2
Gigapixel Whole-Slide Images (WSIs) present a fundamental computational bottleneck for vision-language models (VLMs) due to extreme sequence lengths. Existing approaches predominan…
Stepwise Token Selection for Efficient Multimodal Large Language Models
Landi He, Shawn Young, Lijian Xu
In multimodal large language models (MLLMs), inference cost is largely dominated by the visual token prefix rather than the language backbone, making token reduction a key factor f…
Learnable Token Sparsification for Efficient Gigapixel Whole Slide Image Reasoning
Jingzhi Chen, Landi He, Zhuo Chen +2
The processing of gigapixel whole slide images within vision language models faces a major difficulty due to an excessive number of visual tokens. Existing solutions typically rely…
A unified multi-task framework enables interpretable chest radiograph analysis
Lijian Xu, Ziyu Ni, Xinglong Liu +3
While multimodal deep learning has advanced medical imaging analysis, existing black-box systems \textcolor{black}{may remain confined to isolated tasks, often overlooking} the tru…
Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models
Landi He, Mingde Yao, Shawn Young +1
Visual token pruning reduces the computational cost of Vision-Language Models (VLMs) by removing redundant visual tokens. Existing methods typically rely on Gumbel-Softmax to appro…
Efficient Chest X-ray Representation Learning via Semantic-Partitioned Contrastive Learning
Wangyu Feng, Shawn Young, Lijian Xu
Self-supervised learning (SSL) has emerged as a powerful paradigm for Chest X-ray (CXR) analysis under limited annotations. Yet, existing SSL strategies remain suboptimal for medic…
The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating
Landi He, Xiaoyu Yang, Lijian Xu
Visual tokens dominate inference cost in vision-language models (VLMs), yet many carry redundant information. Existing pruning methods alleviate this but typically rely on attentio…
TC-SSA: Token Compression via Semantic Slot Aggregation for Gigapixel Pathology Reasoning
Zhuo Chen, Shawn Young, Lijian Xu
The application of large vision-language models to computational pathology holds great promise for diagnostic assistants but faces a critical computational bottleneck: the gigapixe…
Fewer Tokens, Greater Scaling: Self-Adaptive Visual Bases for Efficient and Expansive Representation Learning
Shawn Young, Xingyu Zeng, Lijian Xu
This paper investigates the fundamental relationship between model capacity and the minimal number of visual tokens required to preserve image semantics. Inspired by the Minimum De…
One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation
Xiaoyu Yang, Lijian Xu, Hongsheng Li +1
This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called occluded image contrastive learning (OCL). Our OCL ap…
A foundation model for generalizable disease diagnosis in chest X-ray images
Lijian Xu, Ziyu Ni, Hao Sun +2
Medical artificial intelligence (AI) is revolutionizing the interpretation of chest X-ray (CXR) images by providing robust tools for disease diagnosis. However, the effectiveness o…
MedViLaM: A multimodal large language model with advanced generalizability and explainability for medical data understanding and generation
Lijian Xu, Hao Sun, Ziyu Ni +2
Medicine is inherently multimodal and multitask, with diverse data modalities spanning text, imaging. However, most models in medical field are unimodal single tasks and lack good…
Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models
Xiaoyu Yang, Lijian Xu, Hao Sun +2
Visual grounding (VG) occupies a pivotal position in multi-modality vision-language models. In this study, we propose ViLaM, a large multi-modality model, that supports multi-tasks…
Learning A Multi-Task Transformer Via Unified And Customized Instruction Tuning For Chest Radiograph Interpretation
Lijian Xu, Ziyu Ni, Xinglong Liu +3
The emergence of multi-modal deep learning models has made significant impacts on clinical applications in the last decade. However, the majority of models are limited to single-ta…
Voxel2Hemodynamics: An End-to-end Deep Learning Method for Predicting Coronary Artery Hemodynamics
Ziyu Ni, Linda Wei, Lijian Xu +4
Local hemodynamic forces play an important role in determining the functional significance of coronary arterial stenosis and understanding the mechanism of coronary disease progres…
Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network
Xiaoyu Yang, Lijian Xu, Simon Yu +3
Segmentation of the coronary artery is an important task for the quantitative analysis of coronary computed tomography angiography (CCTA) images and is being stimulated by the fiel…