Search papers, labs, and topics across Lattice.
5
0
7
0
Latent reasoning can beat explicit Chain-of-Thought – but only if you force it to learn causal dynamics via a visual world model, not just language.
Ditch expensive, rendering-based RL for autonomous driving: PerlAD uses offline data to train agents in a fast, vector-space pseudo-simulation, outperforming prior methods by 10% on driving score.
Diffusion models can achieve a 10x performance boost in real-world autonomous driving when optimized for trajectory representation, loss space, and augmented with reinforcement learning.
Ditch the discrete anchors: MeanFuser achieves state-of-the-art autonomous driving trajectory generation by using a continuous Gaussian Mixture Noise representation and a mean-flow formulation for faster, more robust planning.
Achieve state-of-the-art performance in vision-language-action tasks with Xiaomi-Robotics-0, a model that executes smoothly in real-time on real robots using a consumer-grade GPU.
