SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.06212 · 2024

OmniFusion Technical Report

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

Last year, multimodal architectures served up a revolution in AI-based approaches and solutions, extending the capabilities of large language models (LLM). We propose an \textit{OmniFusion} model based on a pretrained LLM and adapters for visual modality. We evaluated and compared several architecture design principles for better text and visual data coupling: MLP and transformer adapters, various CLIP ViT-based encoders (SigLIP, InternVIT, etc.), and their fusing approach, image encoding method (whole image or tiles encoding) and two 7B LLMs (the proprietary one and open-source Mistral). Experiments on 8 visual-language benchmarks show the top score for the best OmniFusion setup in terms of different VQA tasks in comparison with open-source LLaVA-like solutions: VizWiz, Pope, MM-Vet, ScienceQA, MMBench, TextVQA, VQAv2, MMMU. We also propose a variety of situations, where OmniFusion provides highly-detailed answers in different domains: housekeeping, sightseeing, culture, medicine, handwritten and scanned equations recognition, etc. Mistral-based OmniFusion model is an open-source solution with weights, training and inference scripts available at https://github.com/AIRI-Institute/OmniFusion.

For agents

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

get_harvested_code_for_paper("2404.06212")
get_code_for_paper("2404.06212")
have("2404.06212")

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

curl https://syntology.ai/api/ran/2404.06212.json

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

[![Syntology run record](https://syntology.ai/api/ran/2404.06212.svg)](https://syntology.ai/paper/2404.06212)

Connect an agent — have() is free.