Search papers, labs, and topics across Lattice.
Affiliation:
5
0
5
2
Treating robot skill calls as runtime-verified execution proposals rather than blind action predictions enables self-correcting VLA autonomy that reaches 97.4% success on LIBERO.
Real-time semantic corrections during video generation can drastically enhance visual fidelity and coherence without retraining the model.
NaviCache redefines how we approach computational efficiency in video generation, achieving superior error judgment and performance without the burdens of traditional calibration methods.
Gazer achieves semantic correction in autoregressive visual models without any training, leading to improved output quality and accuracy.
Ditch slow, irrelevant text-based reasoning: VISUALTHINK-VLA uses visual tokens to speed up vision-language-action policies by 22x while boosting accuracy.
