Search papers, labs, and topics across Lattice.
Shanghai Jiao Tong University
4
0
8
11
Deltoris achieves a staggering 34.2脳 speedup for real-time VLA inference, revolutionizing how embodied AI can operate on edge devices.
Unified generation of temporally structured audio achieves unprecedented speaker similarity and cross-turn consistency without task-specific branches.
V-Steer boosts the accuracy of language model instruction hierarchies to 92% by intelligently editing cached values without the need for retraining.
Achieve optimal advertising feed re-ranking by baking constraints directly into neural decoding, sidestepping the usual latency and constraint-handling limitations of generative approaches.
