SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.03326 · 2024

LLaVA-OneVision: Easy Visual Task Transfer

Bo Li, Chunyuan Li, Ziwei Liu, Yanwei Li, Hao Zhang, Hkust, Renrui Zhang, Feng Li, Peiyuan Zhang, Kaichen Zhang, Yuanhan Zhang, Dong Guo

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present LLaVA-OneVision, a family of open large multimodal models (LMMs) developed by consolidating our insights into data, models, and visual representations in the LLaVA-NeXT blog series. Our experimental results demonstrate that LLaVA-OneVision is the first single model that can simultaneously push the performance boundaries of open LMMs in three important computer vision scenarios: single-image, multi-image, and video scenarios. Importantly, the design of LLaVA-OneVision allows strong transfer learning across different modalities/scenarios, yielding new emerging capabilities. In particular, strong video understanding and cross-scenario capabilities are demonstrated through task transfer from images to videos.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.03326")
get_code_for_paper("2408.03326")
have("2408.03326")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2408.03326.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2408.03326.svg)](https://syntology.ai/paper/2408.03326)

Connect an agent — have() is free.