Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
1
OasisKV achieves up to 2.1x throughput gains in LLM inference while using significantly less memory, challenging the limits of current HBM constraints.
Achieving high perceptual quality in video compression at bitrates below 0.005 bpp could redefine the limits of efficient video transmission.
RealSkin bridges the gap between real-world images and synthetic 3D models by optimizing correspondences in a learned spectral domain, achieving unprecedented accuracy in attribute transfer.
LLM inference spends up to 97% of its time just *preparing* memory, but offloading that work to an FPGA can more than double inference speed.
