Search papers, labs, and topics across Lattice.
The University of Sydney
3
0
5
Injecting world-awareness into speculative decoding leads to a 1.5x speedup in task success rates while reducing near-contact failures by nearly 19%.
HorizonServe achieves up to 4.9x better SLO attainment and drastically lowers latency for omni-model serving by intelligently coordinating GPU resource allocation.
Touch is not just an add-on; it fundamentally enhances object representation, leading to dramatic improvements in physical property estimation and manipulation tasks.
