Search papers, labs, and topics across Lattice.
5
0
6
11
Latent reasoning can beat explicit Chain-of-Thought – but only if you force it to learn causal dynamics via a visual world model, not just language.
Forget pixel-aligned Gaussians: TokenGS uses learnable tokens to directly regress 3D Gaussians, unlocking robustness to pose noise and emergent scene understanding.
Forget generating static 3D scenes – Lyra 2.0 lets you create entire explorable 3D worlds by cleverly routing information from past frames and training the model to correct its own mistakes.
Achieve state-of-the-art results in high-resolution video geometry estimation by disentangling global coherence and fine detail using a dual-stream transformer architecture.
Achieve state-of-the-art depth completion by adapting 3D foundation models at test time with minimal parameter updates, outperforming task-specific encoders that often overfit.
