Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology
4
0
5
0
LISA accelerates training and enhances output quality in visual-condition generation by aligning side network features with likelihood scores, all without extra inference costs.
SPAR bridges the critical gap between semantic perception and pixel-level generation, achieving unprecedented quality in visual outputs without external supervision.
Achieving up to 46% token compression without sacrificing accuracy, HMPO revolutionizes the efficiency of chain-of-thought reasoning in large language models.
Decoupling radial and angular dynamics in vision-language model adaptation unlocks significant gains in few-shot performance, outperforming existing flow matching methods.
