Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning

July 14, 2023

Abstract

We present CM3Leon (pronounced “Chameleon”), a retrieval-augmented, tokenbased, decoder-only multi-modal language model capable of generating and infilling both text and images. CM3Leon uses the CM3 multi-modal architecture but additionally shows the extreme benefits of scaling up and tuning on more diverse instruction-style data. It is the first multi-modal model trained with a recipe adapted from text-only language models, including a large-scale retrieval-augmented pretraining stage and a second multi-task supervised fine-tuning (SFT) stage. It is also a general purpose model that can do both text-to-image and image-to text generation, allowing us to introduce self-contained contrastive decoding methods that produce high-quality outputs. Extensive experiments demonstrate that this recipe is highly effective for multi-modal models. CM3Leon achieves state-of-theart performance in text-to-image generation with 5x less training compute than comparable methods (zero-shot MS-COCO FID of 4.88). After SFT, CM3Leon can also demonstrate unprecedented levels of controllability in tasks ranging from language-guided image editing to image-controlled generation and segmentation.

Download the Paper

AUTHORS

Written by

Lili Yu

Bowen Shi

Ram Pasunuru

Benjamin Miller

Olga Golovneva

Tianlu Wang

Arun Babu

Binh Tang

Brian Karrer

Shelly Sheynin

Candace Ross

Adam Polyak

Russ Howes

Vasu Sharma

Jacob Xu

Uriel Singer

Gargi Ghosh

Asli Celikyilmaz

Armen Aghajanyan

Publisher

Meta Research website

Research Topics

Natural Language Processing (NLP)

Computer Vision

Related Publications

July 02, 2025

REINFORCEMENT LEARNING

NLP

ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context

Joongwon (Daniel) Kim, Anirudh Goyal, Liang Tan, Hannaneh Hajishirzi, Srini Iyer, Tianlu Wang

July 02, 2025

Read the Paper

June 27, 2025

HUMAN & MACHINE INTELLIGENCE

CONVERSATIONAL AI

Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset

Vasu Agrawal, Akinniyi Akinyemi, Kathryn Alvero, Morteza Behrooz, Julia Buffalini, Fabio Maria Carlucci, Joy Chen, Junming Chen, Zhang Chen, Shiyang Cheng, Praveen Chowdary, Joe Chuang, Antony D'Avirro, Jon Daly, Ning Dong, Mark Duppenthaler, Cynthia Gao, Jeff Girard, Martin Gleize, Sahir Gomez, Hongyu Gong, Srivathsan Govindarajan, Brandon Han, Sen He, Denise Hernandez, Yordan Hristov, Rongjie Huang, Hirofumi Inaguma, Somya Jain, Raj Janardhan, Qingyao Jia, Christopher Klaiber, Dejan Kovachev, Moneish Kumar, Hang Li, Yilei Li, Pavel Litvin, Wei Liu, Guangyao Ma, Jing Ma, Martin Ma, Xutai Ma, Lucas Mantovani, Sagar Miglani, Sreyas Mohan, Louis-Philippe Morency, Evonne Ng, Kam-Woh Ng, Tu Anh Nguyen, Amia Oberai, Benjamin Peloquin, Juan Pino, Jovan Popovic, Omid Poursaeed, Fabian Prada, Alice Rakotoarison, Alexander Richard, Christophe Ropers, Safiyyah Saleem, Vasu Sharma, Alex Shcherbyna, Jie Shen, Anastasis Stathopoulos, Anna Sun, Paden Tomasello, Tuan Tran, Arina Turkatenko, Bo Wan, Chao Wang, Jeff Wang, Mary Williamson, Carleigh Wood, Tao Xiang, Yilin Yang, Zhiyuan Yao, Chen Zhang, Jiemin Zhang, Xinyue Zhang, Jason Zheng, Pavlo Zhyzheria, Jan Zikes, Michael Zollhoefer