A5002351613- Mobile Crowdsensing and Crowdsourcing
- Transportation and Mobility Innovations
- Data Mining Algorithms and Applications
- Imbalanced Data Classification Techniques
- Risk and Safety Analysis
- Fault Detection and Control Systems
- Rough Sets and Fuzzy Logic
- Optimization and Search Problems
- Blockchain Technology Applications and Security
- Caching and Content Delivery
- Nuclear Engineering Thermal-Hydraulics
- Auction Theory and Applications
- Model Reduction and Neural Networks
- Adversarial Robustness in Machine Learning
- Privacy-Preserving Technologies in Data
- Complex Network Analysis Techniques
- Recommender Systems and Techniques
- Machine Learning in Materials Science
Tangshan College
2024
Beijing Institute of Technology
2022-2024
Online spatial crowdsourcing platforms provide popular O2O services in people's daily. Users submit real-time tasks through the Internet and require platform to immediately assign workers serve them. However, imbalance distribution of leads rejection some tasks, which reduces profit platform. In this paper, we propose that similar can form an alliance make full use global service supply cooperation. We name problem as <underline xmlns:mml="http://www.w3.org/1998/Math/MathML"...
A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, lags far behind full-model fine-tuning, limiting scope application. In this paper, we leverage the powerful LLMs to synthesize task-specific data for soft prompts. We first introduce a distribution-aligned weighted generator (DawGen) method encourage generating in-distribution that aligns with real data. Then, train prompts both synthetic and datasets using gradient...