ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation

Ethan Chern, Jiadi Su, Yan Ma, Pengfei Liu
7/8/2024
cs.CLcs.AIcs.CV

No official code found. Best implementation: GAIR-NLP/anole (840 stars, last commit 2025-06-16).

Abstract

Previous open-source large multimodal models (LMMs) have faced several limitations: (1) they often lack native integration, requiring adapters to align visual representations with pre-trained large language models (LLMs); (2) many are restricted to single-modal generation; (3) while some support multimodal generation, they rely on separate diffusion models for visual modeling and generation. To mitigate these limitations, we present Anole, an open, autoregressive, native large multimodal model for interleaved image-text generation. We build Anole from Meta AI's Chameleon, adopting an innovative fine-tuning strategy that is both data-efficient and parameter-efficient. Anole demonstrates high-quality, coherent multimodal generation capabilities. We have open-sourced our model, training framework, and instruction tuning data.

View on arXivView PDF

Code Implementations(1)

GAIR-NLP/anoleCommunity100%

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

84050C, C++Jul 1, 20241 years ago

Similar Papers

ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability

89% match1 repo72025

LMFusion: Adapting Pretrained Language Models for Multimodal Generation

86% match1 repo32024

MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer

86% match2025

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

86% match1 repo6482024

Generating Images with Multimodal Language Models

86% match1 repo4722023

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

86% match1 repo3262025

Cite this paper

@article{chern2024anole,
  title  = {ANOLE: An Open, Autoregressive, Native Large Multimodal Models for Interleaved Image-Text Generation},
  author = {Ethan Chern and Jiadi Su and Yan Ma and Pengfei Liu},
  year   = {2024},
  eprint = {2407.06135},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.06135v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.06135.svg)](https://codeofpaper.com/paper/2407.06135)

Discussion