Search papers, labs, and topics across Lattice.
Northeastern University
3
0
8
Flash-WAM achieves real-time inference for world-action models by reducing latency from 8.1 seconds to 348 milliseconds without sacrificing performance.
Ditch the clunky tool-use pipelines: STORM teaches video-language models to reason about space and time using *internalized* latent trajectories, slashing inference costs while boosting accuracy.
By explicitly modeling physical scales within a Transformer architecture, DynFormer slashes PDE solution error by 95% and dramatically reduces memory consumption.
