Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
3
OrthoSkillVLA preserves prior skills in pretrained VLA models while seamlessly integrating new ones, outperforming traditional methods in both simulated and real-world scenarios.
A multi-agent forensic reasoning framework outperforms leading closed-source models in deepfake detection by leveraging diverse analytical perspectives on forgery cues.
Lip articulation accuracy improves dramatically when phoneme information is integrated into audio-driven rendering, reducing closure violations and enhancing realism.
Robot control gets a whole lot faster: ProbeFlow slashes action decoding latency by 14.8x in Vision-Language-Action models, all without retraining.
