EVERYTHING AIAI engineering, made visual
Visual edition planned
Phase 12 · Lesson 08Build3 h25 lessons in phase

LLaVA-OneVision: Single-Image, Multi-Image, Video in One Model

Before LLaVA-OneVision (Li et al., August 2024) the open-VLM world had separate lineages: LLaVA-1.5 for single images, multi-image models like Mantis and VILA, video models like Video-LLaVA and Video-LLaMA. Each won its benchmark and failed at the others. LLaVA-OneVision argued a single curriculum could train one model to dominate all three scenarios, and that the emergent task-transfer effects (single-image skills exported to video, multi-image reasoning exported to single-image) beat the sum of specialists. The recipe is deceptively simple: a visual-token budget that stays constant across scenarios, plus an explicit curriculum that moves from single-image to OneVision (multi-image) to video. This lesson reads the budget, the curriculum, and the emergent behaviors.

Visual edition planned

This lesson isn’t interactive yet.

It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:

Part of Phase 12Multimodal AI. Use the previous / next cards below to keep browsing the phase.