Search papers, labs, and topics across Lattice.
5
0
6
23
A real-time generative world model can synthesize complex driving scenarios that traditional simulators struggle to capture, enabling safer and more effective evaluation of autonomous vehicle policies.
Forget scaling laws: a single looped transformer block, iterated explicitly, crushes billion-parameter feed-forward networks at multi-view 3D reconstruction.
Forget pixel-aligned Gaussians: TokenGS uses learnable tokens to directly regress 3D Gaussians, unlocking robustness to pose noise and emergent scene understanding.
Ditch quadratic scaling in 3D reconstruction: VGG-T$^3$ achieves linear scaling and a 11.6x speed-up by distilling scene geometry into a fixed-size MLP.
Test-time training with KV binding isn't memorization, it's secretly a learned linear attention mechanism, unlocking architectural simplifications and parallelization.
