Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong, Shenzhen
3
5
4
FlexiSLM can operate at frame rates as low as 4.0 Hz while maintaining high-quality speech, effectively halving inference time compared to traditional models.
Fusing spatial and temporal foundation models with anatomical priors dramatically improves rare pathology detection in capsule endoscopy, achieving state-of-the-art results.
A unified benchmark reveals the trade-offs between pixel-wise accuracy and perceptual realism in state-of-the-art image super-resolution techniques.
