Search papers, labs, and topics across Lattice.
D observations into, DGS-based methods [47, 25] represent the scene as a volume or a
4
9
4
7
Achieve robust robot manipulation across diverse viewpoints without camera calibration by synthesizing novel views with a geometry-aware video diffusion model.
Pocket-sized VLA models can now achieve state-of-the-art robot manipulation performance by pre-training on a curated multimodal dataset and injecting manipulation-relevant representations into the action space.
Zero-shot RL agents can now learn better representations by focusing on dynamics-relevant image regions, leading to state-of-the-art generalization performance.
Imagine training robots to manipulate objects in the real world, but entirely within a high-fidelity, diffusion-based dream.
