A5100767742- Software Engineering Research
- Parallel Computing and Optimization Techniques
- Natural Language Processing Techniques
- Autonomous Vehicle Technology and Safety
- Advanced Neural Network Applications
- Topic Modeling
- Speech and dialogue systems
- Fault Detection and Control Systems
- Gas Sensing Nanomaterials and Sensors
- Advanced Battery Technologies Research
- Remote Sensing and LiDAR Applications
- Intellectual Capital and Performance Analysis
- Technology Assessment and Management
- Innovation and Knowledge Management
- Urban and Freight Transport Logistics
- Manufacturing Process and Optimization
- Robotics and Sensor-Based Localization
- Advanced Data Storage Technologies
- Interconnection Networks and Systems
Nanjing University of Science and Technology
2024
Shandong Normal University
2023-2024
Yantai University
2023
Xiamen University
2019
Wuhan University of Science and Technology
2019
Large Language Models (LLMs) perform well on basic programming problems. However, they encounter challenges when dealing with complex tasks involving the use of diverse algorithmic and data structure skills, particularly competition-level Notably, ChatGPT exhibits proficient performance problems it has encountered during its pre-training phase, but this deteriorates faced novel Consequently, enhancing ability LLMs to address unfamiliar emerged as a pivotal research focus. The problem-solving...
Lane line detection is a fundamental and critical task for geographic information perception of driverless advanced assisted driving. However, the traditional lane method relies on manual adjustment parameters, has poor universality, heavy workload, robustness. Most deep learning-based methods make it difficult to effectively balance accuracy efficiency. To improve comprehensive ability in natural traffic environment, algorithm based mixed-attention mechanism residual network (ResNet) row...
Code completion aims to enhance programming productivity by predicting potential code based on the current context. Recently, pre-trained language models (LMs) have become prominent in this field. Various approaches been proposed fine-tune LMs using supervised fine-tuning (SFT) techniques for completion. However, inherent exposure bias of these can cause errors accumulate early sequence completion, leading even more subsequent completions. To address problem, deep reinforcement learning...
Large Language Models (LLMs) demonstrate proficiency in handling fundamental programming problems but struggle with complex new types. The study presents KareCoder, integrating knowledge into code generation. Initial tests reveal KareCoder's significant success the Pass@1 metric for competitive problems.
Online 3D multi-object tracking (MOT) has recently received significant research interests due to the expanding demand of perception in advanced driver assistance systems (ADAS) and autonomous driving (AD). Among existing MOT frameworks for ADAS AD, conventional point object (POT) framework using tracking-by-detection (TBD) strategy been well studied accepted LiDAR 4D imaging radar clouds. In contrast, extended (EOT), another important which accepts joint-detection-and-tracking (JDT)...
-We propose a method that relates to real-time monitoring for internal temperature of battery pack based on compression sensing and deep learning theory, belonging the technical field thermal management. According experimental all positions when charging, discharging under different load conditions same type pack, we apply neural network algorithm in train simulated model which is suitable specific kind packs. Then call by software predict packs, thereby completing global In this paper, use...
As a powerful organizational driving force to promote innovation and development of the international community, new R&D institutions are increasingly becoming entry point for achieving double breakthroughs in technological economic development. Based on definition cause formation institutions, this paper analyses characteristics operation mode Wuhan. Then, puts forward some suggestions prospects problems Wuhan's institutions.