Search papers, labs, and topics across Lattice.
The Hong Kong University of Science and Technology (Guangzhou)
2
0
6
Serving LoRA adapters at scale doesn't have to crush your latency SLOs: InfiniLoRA disaggregates LoRA execution to achieve 3x higher throughput and dramatically improved tail latency.
Finally, a real-time 4D world simulator exists that allows for consistent and controllable scene evolution from a single monocular video.
