12 papers
CLUE: Clinically Aligned Patient-Level Ultrasound Diagnosis via Evidence-Aware Multi-Instance Learning
Qin-Yi Zhang, Linying Cao, De-Xing Huang +7
Patient-level ultrasound diagnosis demands not only high predictive accuracy but also clinically aligned mitigation of asymmetric diagnostic risks. While Multi-Instance Learning (M…
VeCAS: Vessel-Focused Contrast-Free Angiogram Synthesis for Vascular Interventions
De-Xing Huang, Chen-Yu Wang, Hao Liang +10
X-ray angiography relies on iodinated contrast agents to visualize vascular structures during image-guided interventions. However, contrast administration carries risks of adverse…
Vascular anatomy-aware self-supervised pre-training for X-ray angiogram analysis
De-Xing Huang, Chaohui Yu, Xiao-Hu Zhou +8
Objective: X-ray angiography is the gold standard imaging modality for cardiovascular diseases. However, current deep learning approaches for X-ray angiogram analysis are severely…
REASON: Probability map-guided dual-branch fusion framework for gastric content assessment
Nu-Fnag Xiao, De-Xing Huang, Le-Tian Wang +8
Accurate assessment of gastric content from ultrasound is critical for stratifying aspiration risk at induction of general anesthesia. However, traditional methods rely on manual t…
VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning
Si-Cheng Wang, Tian-Yu Xiang, Xiao-Hu Zhou +6
Reinforcement learning (RL) is a promising avenue for post-training vision-language-action (VLA) models, but practical deployment is hindered by sparse rewards and unstable trainin…
Task-Oriented Learning for Automatic EEG Denoising
Tian-Yu Xiang, Zheng Lei, Xiao-Hu Zhou +7
Electroencephalography (EEG) denoising methods typically depend on manual intervention or clean reference signals. This work introduces a task-oriented learning framework for autom…
VasoMIM: Vascular Anatomy-Aware Masked Image Modeling for Vessel Segmentation
De-Xing Huang, Xiao-Hu Zhou, Mei-Jiang Gui +7
Accurate vessel segmentation in X-ray angiograms is crucial for numerous clinical applications. However, the scarcity of annotated data presents a significant challenge, which has…
Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends
Tian-Yu Xiang, Ao-Qun Jin, Xiao-Hu Zhou +11
Vision-language-action (VLA) models extend vision-language models (VLM) by integrating action generation modules for robotic manipulation. Leveraging the strengths of VLM in vision…
CAS-IQA: Teaching Vision-Language Models for Synthetic Angiography Quality Assessment
Bo Wang, De-Xing Huang, Xiao-Hu Zhou +5
Synthetic X-ray angiographies generated by modern generative models hold great potential to reduce the use of contrast agents in vascular interventional procedures. However, low-qu…
VLA Model-Expert Collaboration for Bi-directional Manipulation Learning
Tian-Yu Xiang, Ao-Qun Jin, Xiao-Hu Zhou +8
The emergence of vision-language-action (VLA) models has given rise to foundation models for robot manipulation. Although these models have achieved significant improvements, their…
Learning Novel Skills from Language-Generated Demonstrations
Ao-Qun Jin, Tian-Yu Xiang, Xiao-Hu Zhou +8
Robots are increasingly deployed across diverse domains to tackle tasks requiring novel skills. However, current robot learning algorithms for acquiring novel skills often rely on…
CROP: Conservative Reward for Model-based Offline Policy Optimization
Hao Li, Xiao-Hu Zhou, Shu-Hai Li +6
Offline reinforcement learning (RL) aims to optimize a policy using collected data without online interactions. Model-based approaches are particularly appealing for addressing off…