Jiawei Xu

Interactive Graph Visualization and Teaming Recommendation in an Interdisciplinary Project's Talent Knowledge Graph

2025 · Proceedings of the Association for Information Science and Technology

Interactive visualization of large scholarly knowledge graphs combined with LLM reasoning shows promise but remains under‐explored. We address this gap by developing an interactive visualization system for the Cell Map for AI Talent Knowledge Graph …

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent

2024 · arXiv (Cornell University)

We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. HyperAgent allows for the efficient incremental approximation of posteriors associated with an optimal action-value function ($Q^\star$) without the …

Research on AI Computational Energy Consumption Optimization and Green AI

2025 · SHS Web of Conferences

With the rapid development of Artificial Intelligence (AI), many deep learning models have been extensively applied in various fields, and correspondingly, the environmental issues arising from the development of AI have become one of the …