Search papers, labs, and topics across Lattice.
4
0
6
Sparse visual prompts generated by LoRSP achieve robust adaptation with significantly fewer parameters, challenging the efficiency of traditional dense prompting methods.
Existing referring detection models fall apart when confronted with the scale variations and complexity of aerial imagery, but a new framework closes the gap.
Forget hand-crafting prompts for each graph component – LR-GMP learns a single, low-rank prompt that works across nodes, edges, and weights, boosting generalization.
A nested Mixture-of-Experts architecture lets neural operators pre-trained on diverse PDEs transfer more effectively to downstream tasks.
