Search papers, labs, and topics across Lattice.
University of Southern California (USC), Los Angeles, CA, USA
4
0
6
6
FOLIO slashes memory costs while achieving state-of-the-art accuracy in streaming video understanding by focusing on what truly matters in the data.
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.
