Search papers, labs, and topics across Lattice.
3
0
9
D DianShi-RxnDB is presented, a large-scale, fine-grained organic reaction data platform built via a fully automated extraction and normalization pipeline integrating patent text, images, and reaction schemes integrating patent text, images, and reaction schemes.
Traditional load balancing in EP MoE serving can lead to inefficiencies, but a new makespan-aware dispatcher achieves up to 15.5% throughput gains by adapting to varying compute and memory constraints.
JAGG slashes the backward pass cost in GRPO training of diffusion models by nearly 50%, enabling efficient high-resolution text-to-image generation.
