Search papers, labs, and topics across Lattice.
The Hong Kong Polytechnic University
2
0
5
AIR achieves a staggering 400x inference speedup for cross-domain recommendations without sacrificing semantic quality, revolutionizing industrial applications of LLMs.
GPT-4o gets outperformed by 2.19% on a new smart glasses VQA benchmark, thanks to a retrieval-augmented agent that first identifies the object of interest.
