Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
4
A 4B grounding foundation model achieves state-of-the-art visual grounding, outperforming larger models and boosting downstream robotic and autonomous driving performance by up to 24.8% in OOD settings.
Co-training generative world models on 1,880 hours of retargeted human motion and video unlocks an 84% real-world humanoid loco-manipulation success rate while drastically slashing the need for costly teleoperated robot data.
Video generative priors only translate into robust physical control when paired with explicit world-to-action information routing and synchronized joint denoising rather than standard monolithic fine-tuning.
HarnessEval-W transforms world model evaluation from mere scoring to a transparent reasoning process that mirrors human judgment.
