data-driven approaches
Data-driven approaches prioritize the use of empirical data to inform and guide AI models and decisions, in contrast to rule-based systems. This allows for the development of more adaptable and scalable solutions.
- Breaking the Discretization Barrier of Continuous Physics Simulation Learning
- Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
- FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution
- MaNGO — Adaptable Graph Network Simulators via Meta-Learning
- OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems
- Web-Scale Collection of Video Data for 4D Animal Reconstruction