Search papers, labs, and topics across Lattice.
Affiliation:
6
0
6
Video diffusion models hallucinate rich scene completions but inevitably drift; anchoring their appearance priors directly inside a 3D geometric latent space eliminates sequential inconsistency and slashes trajectory error by 32%.
Ditching brittle hand-estimator-plus-SLAM cascades for an end-to-end streaming memory network slashes world-space hand tracking error by 21.4% while doubling inference throughput.
Current AI-generated videos that mislead viewers are also the most challenging for existing detection systems to identify, revealing a critical vulnerability in misinformation defenses.
Achieving high-fidelity 3D object generation with up to 300 parts, MegaParts redefines the limits of part-aware modeling through token-efficient autoregressive techniques.
