Search papers, labs, and topics across Lattice.
12
0
10
VAIC enables humanoid robots to perform complex tasks in real-world settings without the need for perfect state observability, significantly advancing their practical deployment.
SeClaw reveals that existing benchmarks fall short in capturing the complexities of agent behavior, enabling a more nuanced evaluation of security risks in autonomous systems.
Robots can now learn to "handle with care," reducing grip force by over 70% in gentle manipulation tasks, thanks to a new vision-tactile-language model and benchmark.
Humanoid robots can now traverse complex parkour environments with significantly improved success rates by explicitly reasoning about future body states.
Closing the real-to-sim gap in continuum dynamics requires modeling subtle material properties beyond simple isotropy – and MoSA shows how to do it.
Achieve real-time 360° robotic vision with RobotPan, which drastically reduces the number of Gaussians needed for reconstruction and view synthesis compared to previous feed-forward methods.
Forget finetuning: this training-free method achieves state-of-the-art zero-shot 3D visual grounding, even in messy, real-world environments.
Sparse-view 3D Gaussian Splatting gets a major boost by incorporating priors from geometry foundation models and VLMs to overcome the limitations of color residual heuristics.
Ditch VAEs and AMP: SLMP learns structured motion priors in a spherical latent space, enabling stable random sampling of diverse and valid humanoid behaviors without information loss.
Turns out, robotic manipulation policies struggle with tasks requiring memory, and this benchmark reveals the architectural design choices that actually matter for improving performance.
Generate superhuman humanoid motion data at scale by closing the loop between policy performance and data difficulty, surpassing limitations of fixed datasets.
Humanoid robots can now learn complex, terrain-aware motions directly from video using a low-cost pipeline, eliminating the need for expensive MoCap data and manual motion design.
