Search papers, labs, and topics across Lattice.
5
0
8
0
Ignoring the evolving nature of worker performance can lead to suboptimal budget allocation, but this new framework adapts to maximize sensing utility in real-time.
Selecting the right LLM under real-world constraints can lead to significant improvements in service quality and resource efficiency, even in unpredictable environments.
Achieving a 5脳 speedup in kernel-level operations while maintaining accuracy could revolutionize long-context modeling efficiency on NPUs.
Ditching caches for compiler-managed data streams, Li Auto's M100 architecture achieves higher utilization than GPUs on autonomous driving tasks, hinting at a new path for efficient AI inference.
Android agents can now learn much faster by squeezing more value out of each emulator interaction, thanks to a novel "Single State Multiple Actions" training paradigm.
