Search papers, labs, and topics across Lattice.
The Chinese University of Hong Kong
4
0
7
Robot policies can now test and refine manipulation plans entirely within a learned visual simulator across ten distinct embodiments, gaining up to 21.4 percentage points in task success without any target-domain fine-tuning.
Local interaction control in self-supervised denoising can dramatically enhance performance, revealing hidden regional dynamics that traditional methods overlook.
UnityShots achieves unprecedented cross-shot coherence in multi-shot video generation, outperforming open-source benchmarks and rivaling top closed-source systems.
Optimizing data mixtures through gradient descent can drastically reduce training costs and improve model performance without the need for extensive simulations.
