Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
Embodied Robotics and Automation Lab , University of South Florida , Tampa , FL , USA
6
0
8
6
Bidirectional, change-sensitive memory updates unlock near-perfect recall across megabytes of context, even when trained on much shorter sequences.
A single 3D sonar detector can now accurately estimate a diver's full 6-DoF orientation, unlocking robust underwater human-robot interaction.
Even top-performing Vision Language Models miss 30% of logical anomalies, revealing critical gaps in their reasoning abilities.
LLMs leak training data membership through subtle, gradient-induced shifts in their internal representations, enabling a surprisingly effective new attack.
Autonomous underwater vehicles can now navigate complex environments more effectively by combining the reasoning of vision-language models with dynamics-aware planning, achieving better coverage and zero collisions.
By predicting parameters for classical planners, APPLV offers a way to leverage foundation models for robot navigation while retaining safety guarantees and outperforming end-to-end VLA models.