Search papers, labs, and topics across Lattice.
Institute of Software, University of Chinese Academy of Sciences, Chinese Academy of Sciences
2
0
4
Over-smoothing in time series forecasts can be mitigated by a novel framework that preserves distinct dynamic modes, leading to more accurate and diverse predictions.
Self-distillation can be more effective than learning from an external teacher, but only if you optimize for preference gaps instead of blindly matching the teacher's output distribution.
