Search papers, labs, and topics across Lattice.
6
0
6
SurveilNav achieves state-of-the-art navigation success rates by seamlessly integrating robot perception with multi-view surveillance, transforming how robots can navigate complex environments.
Achieving high-quality robotic manipulation with a single inference step could revolutionize real-time interaction in complex environments.
Monocular RGB input can now provide reliable metric localization and obstacle perception, solving scale ambiguity in real-time.
Zero-shot image retrieval gets a major boost from a hierarchical multi-agent system that evolves its reasoning at test time, outperforming previous methods on standard benchmarks.
Laplacian kernels offer a theoretically sound and empirically superior alternative to Gaussian kernels for linear attention, finally bridging the gap between efficient computation and expressive power in Transformers.
Achieve sub-centimeter robotic placement accuracy from compositional language instructions by decomposing the task into visual goal representation and goal-conditioned execution.
