Search papers, labs, and topics across Lattice.
Affiliation:
7
0
8
ModAR is introduced, the first WAM to autoregressively denoise multiple future modalities before predicting actions, and it is found that ModAR's sequential generation outperforms existing WAM formulations, with the highest average success rate at all evaluated data scales.
Modern VLMs already encode much of what is needed for specialized domains; the challenge is learning how to ask, suggests modern VLMs already encode much of what is needed for specialized domains; the challenge is learning how to ask.
Dense 4D reconstruction no longer collapses after a few dozen frames: directly re-querying 3D trajectory endpoints across video chunks breaks the long-standing temporal horizon bottleneck in feed-forward dynamic scene reconstruction.
A single model can replace multiple specialized pipelines for rendering refinement, achieving significant quality improvements with minimal finetuning.
Open-vocabulary monocular 3D detectors mislabel correctly localized objects due to prompt sensitivity, revealing a critical gap in their semantic understanding.
