Search papers, labs, and topics across Lattice.
Meituan
4
0
8
Omni-Flow revolutionizes multimodal inference by integrating flexible orchestration, efficient data sharing, and KV cache reuse into a single cohesive framework.
Mobile spatial data can now be analyzed for distribution statistics with 100% accuracy while reducing computation overhead by 1.2x and communication overhead by 20x, all without compromising privacy.
You can train a surprisingly effective AI-generated image detector with just 320 images by adversarially unlearning biases towards specific generative models.
LongCat-Next shatters the language-centric paradigm by unifying text, vision, and audio into a single autoregressive model with minimal modality-specific design, finally reconciling understanding and generation in discrete vision modeling.
