Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology of China
2
0
4
FAiT outperforms traditional Transformers by capturing evolving spectral characteristics in time series data, enabling sharper forecasts of transient signals.
Medical MLLMs can achieve state-of-the-art reasoning performance, rivaling trillion-parameter models, by learning interpretable latent spaces with visual-semantic supervision, even without increasing inference costs.
