Search papers, labs, and topics across Lattice.
3
0
6
5
Vision GNNs can achieve near 100x speedups on FPGAs by decoupling graph construction from feature updates, enabling concurrent execution without significant accuracy loss after fine-tuning.
Edge devices can now learn continuously from visual data with 40x faster speed and 380x better energy efficiency, thanks to a novel FPGA accelerator design.
LMMs can gain surprising robustness and visual understanding by learning to denoise corrupted visual tokens, even without extra inference overhead.
