Search papers, labs, and topics across Lattice.
5
0
13
Text-only foundation models can perform surprisingly well on complex 3D spatial reasoning tasks, rivaling multimodal models, when equipped with a structured spatial representation derived from 3D reconstruction.
Achieve significant speedups in diffusion model inference, without training, by adaptively selecting the best predictor for each token at each step based on a low-cost probe of the first layer.
Context matters: SQL injection detection accuracy jumps by over 40% when models are trained on request-response pairs versus payload-only data.
MiroFlow leapfrogs existing LLM agent frameworks with its agent graph architecture, delivering state-of-the-art performance and robust execution across a diverse range of benchmarks.
LLMs can now more accurately answer questions on complex documents thanks to a new system that understands layout and hierarchical relationships between document components.
