paper-with-me

Papers

Jointly Training Large Autoregressive Multimodal Models

2023-09-27 · Emanuele Aiello, Lili Yu, Yixin Nie, Armen Aghajanyan, Barlas Oguz

In recent years, advances in the large-scale pretraining of language and text-to-image models have revolutionized the field of machine learning. Yet, integrating these two modalities into a single, robust model capable of generating seamless multimodal outputs remains a significant challenge. To address this gap, we present the Joint Autoregressive Mixture (JAM) framework, a modular approach that systematically fuses existing text and image generation models. We also introduce a specialized, data-efficient instruction-tuning strategy, tailored for mixed-modal generation tasks. Our final instruct-tuned model demonstrates unparalleled performance in generating high-quality multimodal outputs and represents the first model explicitly designed for this purpose.

📄 PDF Abstract BibTeX arXiv:2309.15564

Code (0)

등록된 구현이 없습니다.

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

2026-05-19 · Tobias Braun, Jonas Henry Grebe, Hossein Shakibania, Anna Rohrbach 외 arxiv

Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and…

multimodal generationImage Generation

Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities

2023-11-09 · CVPR 2024 1 · AJ Piergiovanni, Isaac Noble, Dahun Kim, Michael S. Ryoo 외

One of the main challenges of multimodal learning is the need to combine heterogeneous modalities (e.g., video, audio, text). For example, video and audio are obtained at much higher rates than text and are roughly align…

Action ClassificationAudio ClassificationVideo Question Answering

Unified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification

2026-06-16 · Wujian Peng, Lingchen Meng, Yuxuan Cai, Xianwei Zhuang 외 arxiv

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation sp…

Reinforcement LearningImage GenerationImage Editing

Multimodal Autoregressive Pre-training of Large Vision Encoders

2024-11-21 · CVPR 2025 1 · Enrico Fini, Mustafa Shukor, Xiujun Li, Philipp Dufter 외

We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images…

DecoderImage Classification

JetFormer: An Autoregressive Generative Model of Raw Images and Text

2024-11-29 · Michael Tschannen, André Susano Pinto, Alexander Kolesnikov

Removing modeling constraints and unifying architectures across domains has been a key driver of the recent progress in training large multimodal models. However, most of these models still rely on many separately traine…

DecoderImage GenerationText to Image GenerationText-to-Image Generation