137 citations · 189 across the 26 of their papers we have counts for
29 papers
Diagnose-to-Generate: Eliminating Structural Distortions in Flow Models via Patch-Level Grounded Alignment
Yifan Li, Lishuai Gao, Tong Zhang +8
Flow-based image generators achieve strong semantic synthesis but still produce localized structural distortions, such as malformed hands and limbs. Existing post-training methods…
TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents
Chengqi Dong, Chuhuai Yue, Hang He +6
We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform broadcast of trajectory-leve…
ASAP: Advancing Medical Volumetric Representation Learning with Anatomy-aware Semantically-adaptive Pre-training
Rongsheng Wang, Fenghe Tang, Zihang Jiang +10
Learning transferable and interpretable representations from medical volumetric scans remains challenging due to complex anatomical structures and weak, heterogeneous supervision p…
Concept-to-Pixel: Prompt-Free Universal Medical Image Segmentation
Haoyun Chen, Fenghe Tang, Wenxin Ma +1
Universal medical image segmentation seeks to use a single foundational model to handle diverse tasks across multiple imaging modalities. However, existing approaches often rely he…
MMRad-22K: A Structured Multimodal Evidence Dataset for Chest X-ray Report Generation
Yichen Zhao, Zelin Peng, Fenghe Tang +3
Chest X-ray (CXR) reporting follows a region-based clinical workflow in which radiologists inspect anatomical regions and integrate localized findings into a final report. However,…
UCAD: Uncertainty-guided Contour-aware Displacement for semi-supervised medical image segmentation
Chengbo Ding, Fenghe Tang, Shaohua Kevin Zhou
Existing displacement strategies in semi-supervised segmentation only operate on rectangular regions, ignoring anatomical structures and resulting in boundary distortions and seman…
Training Multi-Image Vision Agents via End2End Reinforcement Learning
Chengqi Dong, Chuhuai Yue, Hang He +7
Recent VLM-based agents aim to replicate OpenAI O3's "thinking with images" via tool use, yet most open-source methods restrict inputs to a single image, limiting their applicabili…
Equivariant Sampling for Improving Diffusion Model-based Image Restoration
Chenxu Wu, Qingpeng Kong, Peiang Zhao +5
Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion mode…
MedReason-R1: Learning to Reason for CT Diagnosis with Reinforcement Learning and Local Zoom
Yifan Li, Fenghe Tang, Yingtai Li +1
General-purpose large Vision-Language Models (VLMs) demonstrate strong capabilities in generating detailed descriptions for natural images. However, their performance in the medica…
U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking
Fenghe Tang, Chengqi Dong, Wenxin Ma +7
Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread a…
SimCroP: Radiograph Representation Learning with Similarity-driven Cross-granularity Pre-training
Rongsheng Wang, Fenghe Tang, Qingsong Yao +8
Medical vision-language pre-training shows great potential in learning representative features from massive paired radiographs and reports. However, in computed tomography (CT) sca…
LGMSNet: Thinning a medical image segmentation model via dual-level multiscale fusion
Chengqi Dong, Fenghe Tang, Rongge Mao +2
Medical image segmentation plays a pivotal role in disease diagnosis and treatment planning, particularly in resource-constrained clinical settings where lightweight and generaliza…
Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation
Fenghe Tang, Bingkun Nian, Jianrui Ding +6
In clinical practice, medical image analysis often requires efficient execution on resource-constrained mobile devices. However, existing mobile models-primarily optimized for natu…
U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV
Hongbo Ye, Fenghe Tang, Peiang Zhao +4
Achieving equity in healthcare accessibility requires lightweight yet high-performance solutions for medical image segmentation, particularly in resource-limited settings. Existing…
Pre-Trained LLM is a Semantic-Aware and Generalizable Segmentation Booster
Fenghe Tang, Wenxin Ma, Zhiyang He +3
With the advancement of Large Language Model (LLM) for natural language processing, this paper presents an intriguing finding: a frozen pre-trained LLM layer can process visual tok…
AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIP
Wenxin Ma, Xu Zhang, Qingsong Yao +6
Anomaly detection (AD) identifies outliers for applications like defect and lesion detection. While CLIP shows promise for zero-shot AD tasks due to its strong generalization capab…
Hi-End-MAE: Hierarchical encoder-driven masked autoencoders are stronger vision learners for medical image segmentation
Fenghe Tang, Qingsong Yao, Wenxin Ma +3
Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabe…
3DGR-CAR: Coronary artery reconstruction from ultra-sparse 2D X-ray views with a 3D Gaussians representation
Xueming Fu, Yingtai Li, Fenghe Tang +4
Reconstructing 3D coronary arteries is important for coronary artery disease diagnosis, treatment planning and operation navigation. Traditional reconstruction techniques often req…
HySparK: Hybrid Sparse Masking for Large Scale Medical Image Pre-Training
Fenghe Tang, Ronghao Xu, Qingsong Yao +5
The generative self-supervised learning strategy exhibits remarkable learning representational capabilities. However, there is limited attention to end-to-end pre-training methods…
MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation
Fenghe Tang, Bingkun Nian, Yingtai Li +4
Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging.…
APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
Zikang Xu, Fenghe Tang, Quan Quan +2
Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. Ho…
Inspecting Model Fairness in Ultrasound Segmentation Tasks
Zikang Xu, Fenghe Tang, Quan Quan +3
With the rapid expansion of machine learning and deep learning (DL), researchers are increasingly employing learning-based algorithms to alleviate diagnostic challenges across dive…
MobileUtr: Revisiting the relationship between light-weight CNN and Transformer for efficient medical image segmentation
Fenghe Tang, Bingkun Nian, Jianrui Ding +4
Due to the scarcity and specific imaging characteristics in medical images, light-weighting Vision Transformers (ViTs) for efficient medical image segmentation is a significant cha…
SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution
Bingkun Nian, Fenghe Tang, Jianrui Ding +4
Dynamic convolution demonstrates outstanding representation capabilities, which are crucial for natural image segmentation. However, it fails when applied to medical image segmenta…