Search papers, labs, and topics across Lattice.
7
0
8
RainDancer achieves superior deraining performance by intelligently separating rain and background components before fusion, addressing the challenges of dynamic rainy scenes.
TuringViT outperforms leading ViT models with just 10% of the training data, making state-of-the-art vision technology accessible to a wider audience.
Achieve 2.6x faster autoregressive world model inference without retraining by caching and selectively reusing block-level residuals across generation chunks.
Ditch the expensive 3D annotations: Reliev3R trains high-quality 3D reconstruction models from scratch using only monocular relative depths and sparse image correspondences.
Autonomous driving planners can now explicitly self-correct unsafe actions by generating motion-token traces conditioned on a learned collision critic, leading to significant safety improvements.
Autonomous driving gets a boost: EvoDriveVLA's collaborative perception-planning distillation framework significantly enhances VLA model performance by tackling perception degradation and planning instability.
Achieve state-of-the-art surgical attention tracking with a new method that leverages temporal coherence and a large-scale benchmark dataset, enabling more robust and interpretable FoV guidance.
