Search papers, labs, and topics across Lattice.
4
0
5
21
A single continuous flow model now unifies language and vision generation, outperforming hybrid and discrete models under matched budgets and achieving strong benchmarks with drastically less data.
StateFlow transforms previsualization by enabling creators to iteratively refine complex 3D scenes with a persistent state, rather than relying on one-shot generation.
Achieving up to 338x faster inference, EOVSAM redefines open-vocabulary segmentation without sacrificing accuracy.
Ditch the complex multimodal pre-training pipelines: GenLIP proves a simple language modeling objective can effectively align vision encoders with LLMs, achieving strong performance with less data.
