Search papers, labs, and topics across Lattice.
3
0
4
Sparse visual prompts generated by LoRSP achieve robust adaptation with significantly fewer parameters, challenging the efficiency of traditional dense prompting methods.
Relight 3D assets 25x faster with a feed-forward network that distills relightable representations from large reconstruction models, sidestepping expensive per-scene optimization.
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.
