Home
LMMs-LabResearch journal

LMMs-Lab Blog

Research notes, engineering stories, and open-source updates—feeling and building multimodal intelligence.

Publication index

Latest notes

2 entries
  1. 2026-08-04

    A Multimodal Hello World

    A compact smoke test for Markdown, equations, code highlighting, tables, and local images.

  2. 2026-01-15

    OneVision Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

    Codec Patchification processes only the 3.1%-25% of visual regions rich in signal entropy, improving video understanding while using substantially fewer patches.

LMMs-Lab · Building multimodal intelligence

Built with Angular · Deployed on Cloudflare Workers

Authoring Docs · Source Code: