New Solution
Research on "new solutions" spans diverse areas, focusing on improving efficiency and accuracy across various machine learning and data analysis tasks. Current efforts concentrate on developing novel algorithms and model architectures, such as transformer networks and graph neural networks, to address challenges in video object segmentation, large language model acceleration, federated learning, and vulnerability detection. These advancements aim to enhance the performance and applicability of existing technologies, leading to more efficient and robust systems in fields ranging from healthcare and finance to software engineering and cybersecurity. The ultimate goal is to create more powerful, scalable, and reliable solutions for a wide range of applications.
Papers
New Solutions on LLM Acceleration, Optimization, and Application
Yingbing Huang, Lily Jiaxin Wan, Hanchen Ye, Manvi Jha, Jinghua Wang, Yuhong Li, Xiaofan Zhang, Deming Chen
Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
Laiqiao Qin, Tianqing Zhu, Wanlei Zhou, Philip S. Yu