Search papers, labs, and topics across Lattice.
5
0
4
5
Fine-tuning vision-language models with latent actions can dramatically improve robotic manipulation performance, revealing critical design choices that matter most.
Action-conditioned verification can boost success rates in mobile manipulation tasks by over 8% while enhancing timely recall by nearly 30%.
Trustworthiness in embodied intelligence isn't just about performance; it's about managing risk across a multi-layered framework that ensures safety and reliability in real-world applications.
Future visual cues can dramatically enhance navigation performance, even when not accessible during actual deployment.
Web-scale video pretraining lets robots handle real-world chaos better than vision-language models trained on curated robotics datasets.
