- Advanced Image and Video Retrieval Techniques
- Traffic control and management
- Microbial Community Ecology and Physiology
- Marine and coastal plant biology
- Spine and Intervertebral Disc Pathology
- Acute Myocardial Infarction Research
- Marine Biology and Ecology Research
- Network Security and Intrusion Detection
- Robotics and Sensor-Based Localization
- Multimodal Machine Learning Applications
- Cerebrospinal fluid and hydrocephalus
- Invertebrate Immune Response Mechanisms
- Coronary Interventions and Diagnostics
- Gut microbiota and health
- Spinal Fractures and Fixation Techniques
- Microbial Inactivation Methods
- Microscopic Colitis
- Reinforcement Learning in Robotics
- Advanced MRI Techniques and Applications
- Autonomous Vehicle Technology and Safety
- Medical Imaging and Analysis
- Antiplatelet Therapy and Cardiovascular Diseases
- Radiomics and Machine Learning in Medical Imaging
- Neurobiology and Insect Physiology Research
- Healthcare and Venom Research
Sichuan University
2024
Nanjing Medical University
2024
Hangzhou Medical College
2024
Zhejiang Provincial People's Hospital
2024
Shanxi University
2024
Horizon Robotics (China)
2024
First Institute of Oceanography
2023
Ministry of Natural Resources
2023
Wenzhou Medical University
2007-2014
First Affiliated Hospital of Wenzhou Medical University
2007
Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and open-loop gap. In this work, we establish a 3DGS-based closed-loop Reinforcement (RL) training paradigm. By leveraging 3DGS techniques, construct photorealistic digital replica of real physical world, enabling AD policy to extensively explore state space learn handle out-of-distribution scenarios through large-scale trial error. To...
To explore the rehabilitation effect and compliance of lumbar abdominal muscle training in patients with osteoporotic vertebral compression fracture (OVCF) after percutaneous balloon vertebroplasty (PKP).
Introduction: Heart failure (HF) may induce bowel hypoperfusion, leading to hypoxia of the villa wall and occurrence Clostridioides difficile infection (CDI). However, risk factors for development CDI in HF patients have yet be fully illustrated, especially because a lack evidence from real-world data. Methods: Clinical data survival situations with admitted ICU were extracted Medical Information Mart Intensive Care (MIMIC)-IV database. For developing model that can predict 28-day all-cause...
Potassium sorbate (PS) is a preservative widely used in the food, pharmaceutical, and cosmetics industries. Improper careless use of PS can lead to various health issues potential environmental problems. Drosophila capable making rapid sensitive responses stress or other stimuli. Here we utilized as model organism evaluate toxicity PS. Our study revealed that ingestion reduced lifespan fecundity Drosophila. In addition, excessive led cell apoptosis ROS accumulation midgut. Furthermore,...
Macroalgae and macroalgae-associated bacteria together constitute the most efficient metabolic cycling system in ocean. Their interactions, especially responses of communities to algae different geographical locations, are mostly unknown. In this study, metagenomics was used analyze microbial diversity associated algal-polysaccharide-degrading enzymes on surface red among three remote regions. There were significant differences community composition At phylum level, Proteobacteria,...
End-to-end autonomous driving demonstrates strong planning capabilities with large-scale data but still struggles in complex, rare scenarios due to limited commonsense. In contrast, Large Vision-Language Models (LVLMs) excel scene understanding and reasoning. The path forward lies merging the strengths of both approaches. Previous methods using LVLMs predict trajectories or control signals yield suboptimal results, as are not well-suited for precise numerical predictions. This paper presents...
Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability end-to-end autonomous driving is promising direction. However, numerous denoising steps in and more dynamic, open-world nature traffic scenes pose substantial challenges generating diverse actions at real-time speed. To address these challenges, we propose novel truncated that incorporates prior anchors...
Macroalgae and macroalgae-associated bacteria together constitute the most efficient metabolic cycling system in ocean. Their interactions, especially responses of communities to algae different geographical locations, is mostly unknown. In this study, metagenomics was used analyze microbial diversity associated algal polysaccharide-degrading enzymes on surface red among three remote regions. There were significant differences community composition At phylum level, Proteobacteria,...