Future Reasoning
Future reasoning research explores how artificial intelligence systems can predict, plan, and understand temporal dynamics. Current efforts concentrate on improving the accuracy and efficiency of AI-driven forecasting across diverse domains, from weather prediction using large meteorological models and graph neural networks to financial market analysis and even generating synthetic data for training other models. This field is crucial for advancing AI capabilities in areas like autonomous systems, personalized medicine, and risk management, ultimately impacting both scientific understanding and real-world applications.
Papers
Blueprinting the Future: Automatic Item Categorization using Hierarchical Zero-Shot and Few-Shot Classifiers
Ting Wang, Keith Stelter, Jenn Floyd, Thomas O'Neill, Nathaniel Hendrix, Andrew Bazemore, Kevin Rode, Warren Newton
Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future
Hongyang Li, Yang Li, Huijie Wang, Jia Zeng, Huilin Xu, Pinlong Cai, Li Chen, Junchi Yan, Feng Xu, Lu Xiong, Jingdong Wang, Futang Zhu, Chunjing Xu, Tiancai Wang, Fei Xia, Beipeng Mu, Zhihui Peng, Dahua Lin, Yu Qiao