Search papers, labs, and topics across Lattice.
6
0
6
2
Achieving a 2dB PSNR improvement, EmbodiedVAE transforms how robots learn and execute manipulation tasks by providing compact and controllable latent representations.
TRA achieves up to 2.05x faster video generation by intelligently mapping query entropy to token-specific attention budgets, revolutionizing efficiency in VDiTs.
Achieve SOTA zero-shot anomaly detection by dynamically routing image patches based on structural entropy, adapting to heterogeneous anomaly patterns without target-domain fine-tuning.
Scaling up robot data and closing the loop with state decoding and automated reward scoring allows a 2B parameter video world simulator to outperform larger, dedicated robotic world models in real-world policy transfer.
Ditch the training: SVOO achieves up to 1.93x speedup in video generation with sparse attention by exploiting the intrinsic, layer-specific sparsity patterns of attention without any fine-tuning.
Achieve more physically realistic video generation by explicitly modeling 3D geometry and physical attributes across multiple viewpoints.
