Search papers, labs, and topics across Lattice.
Waabi 2 University of Toronto
3
0
7
Forget painstakingly optimizing each urban scene individually: GenRe distills diffusion-based generative priors into 3D Gaussian representations, fixing reconstruction deficiencies in minutes and generalizing to challenging viewpoints.
Forget finicky VQ-based recommendation models: R3-VAE's reference vector and rating-based regularization finally make them stable and effective enough for real-world deployment, boosting MRR by 1.62% in online A/B tests.
Forget quadratic complexity: ULTRA-HSTU achieves 21x faster inference and 4-8% better engagement in large-scale recommendation by co-designing input sequences, sparse attention, and model topology.
