Search papers, labs, and topics across Lattice.
7
0
10
Achieving a staggering 61.4脳 simulation speedup while optimizing SRAM design without sacrificing fidelity could revolutionize how we approach memory architecture.
Achieving pose-controllable object insertion with high visual fidelity, DIRECT redefines the boundaries of 2D image synthesis by integrating 3D manipulation.
Robots can now better reason about their environment and plan actions by maintaining a persistent, action-updated belief state across control chunks, even when visual updates are infrequent.
Conditional risk calibration reveals a unique perspective on uncertainty quantification that could transform how we approach decision-making in machine learning.
Training-free change detection gets a serious boost: CoRegOVCD leverages posterior calibration and geometric consistency to identify semantic changes in remote sensing imagery with significantly improved accuracy.
HALyPO stabilizes human-robot collaboration by directly certifying the convergence of decentralized policy learning in parameter space, sidestepping the oscillations that plague standard MARL approaches.
By using optimal transport to guide cross-attention, SceneTransporter disentangles image patches and 3D latents, leading to more coherent and geometrically faithful 3D scene generation from single images.
