Search papers, labs, and topics across Lattice.
The University of Hong Kong
4
0
9
Achieve superhuman robot dexterity with 10x fewer demonstrations by decoupling intent and action through latent world modeling.
By disentangling semantic and contextual cues in vision-language models, PCA-Seg achieves state-of-the-art open-vocabulary segmentation with only 0.35M additional parameters per block.
Quantizing large vision-language models just got a whole lot better: a new token-level sensitivity metric closes the accuracy gap with full-precision models by up to 1.6% in 3-bit weight-only quantization.
Conformal factuality for RAG breaks down when faced with distribution shifts or distractors, forcing a trade-off between factuality and informativeness.
