Search papers, labs, and topics across Lattice.
4
0
4
7
CAT's trajectory-level continuous action representation significantly enhances robotic manipulation success rates by eliminating representational redundancy and ensuring temporal consistency.
Language models can now be rigorously evaluated on their ability to generate falsifiable research ideas, not just stylistic fluency.
Future tactile states can be predicted more effectively from intermediate action features, transforming how we approach tactile supervision in robotic manipulation.
Grounding action representations in environmental context can drastically improve robotic manipulation performance, especially for complex tasks.
