Search papers, labs, and topics across Lattice.
Affiliation:
4
0
6
A single unified framework achieves state-of-the-art performance in both action-conditioned world modeling and real-world robotic manipulation by dynamically routing specialized experts.
CAER redefines how we train world models by ensuring that only the most relevant tokens drive learning, leading to substantial gains in video generation quality.
Selective curation of ego-centric video data can boost robot manipulation success rates by over 28% with less than 5% of the original dataset.
Attention from your LLM can be used to significantly improve preference optimization, outperforming existing methods without needing a separate reward model or heuristic token weighting.
