Papers
arxiv:2506.10395

Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation

Published on Jun 12
Authors:
,
,
,
,
,
,
,
,
,
,
,
,

Abstract

Pisces, a unified multimodal model with decoupled visual encoders and tailored training techniques, achieves competitive performance in both image understanding and image generation.

AI-generated summary

Recent advances in large language models (LLMs) have enabled multimodal foundation models to tackle both image understanding and generation within a unified framework. Despite these gains, unified models often underperform compared to specialized models in either task. A key challenge in developing unified models lies in the inherent differences between the visual features needed for image understanding versus generation, as well as the distinct training processes required for each modality. In this work, we introduce Pisces, an auto-regressive multimodal foundation model that addresses this challenge through a novel decoupled visual encoding architecture and tailored training techniques optimized for multimodal generation. Combined with meticulous data curation, pretraining, and finetuning, Pisces achieves competitive performance in both image understanding and image generation. We evaluate Pisces on over 20 public benchmarks for image understanding, where it demonstrates strong performance across a wide range of tasks. Additionally, on GenEval, a widely adopted benchmark for image generation, Pisces exhibits robust generative capabilities. Our extensive analysis reveals the synergistic relationship between image understanding and generation, and the benefits of using separate visual encoders, advancing the field of unified multimodal models.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2506.10395 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2506.10395 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2506.10395 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.