Search papers, labs, and topics across Lattice.
2
0
5
Diffusion Transformers waste up to 66% of their conditional embedding space without sacrificing generation quality, hinting at opportunities for more efficient conditioning.
Unlock the potential of your offline RL data: a new framework achieves state-of-the-art performance on D4RL benchmarks by quantifying and leveraging data uncertainty with a computationally efficient Rank-One MIMO architecture.
