Search papers, labs, and topics across Lattice.
3
196
6
4
CoSA achieves nearly 5脳 faster attention computation without sacrificing accuracy, revolutionizing long-context processing in LLMs.
PIVOT achieves up to 4x faster indexing for token-level sparse attention without sacrificing accuracy, transforming how we handle query processing in large models.
Open-source 3D asset generation just leveled up: Hunyuan3D 2.0 delivers high-resolution, textured 3D models that outperform both open and closed-source alternatives.
