Search papers, labs, and topics across Lattice.
Shanghai Academy of AI for Science, Fudan University
3
0
6
By decoupling trend and residual information, PMDformer achieves unprecedented accuracy in long-term time series forecasting, setting a new benchmark in the field.
CrossFlow achieves a remarkable 1.62 FID score with a single function evaluation, redefining the efficiency of image generation by eliminating the need for a separate decoder.
Dramatically cut the simulation budget for PDE surrogate training by using RL to intelligently allocate mesh points.
