Search papers, labs, and topics across Lattice.
2
0
4
0
RL fine-tuning unlocks a 6x performance gain for in-place trajectory editing in autonomous driving, demonstrating the power of aligning diffusion planners with reinforcement learning.
A surprisingly simple change to the motion latent space鈥攔epresenting each body joint with its own token鈥攄ramatically improves text-to-motion generation quality, outperforming monolithic latent vector approaches.
