Jointly Training Large Autoregressive Multimodal Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models
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 GenerationMirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities
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 AnsweringUnified Multimodal Autoregressive Modeling with Shared Context-Visual Tokenizer is Key to Unification
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 EditingMultimodal Autoregressive Pre-training of Large Vision Encoders
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 ClassificationJetFormer: An Autoregressive Generative Model of Raw Images and Text
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