Search papers, labs, and topics across Lattice.
University of Electronic Science and Technology of China
2
0
5
5
UPrompt achieves a remarkable 7.3 rSum improvement over existing models on MSCOCO, redefining the standards for cross-task generalization in vision-language tasks.
SNNs get a serious boost in accuracy and efficiency thanks to "Stable Spike," which uses bitwise AND operations to distill consistent, meaningful signals from noisy spike trains.
