While next-token prediction is considered a promising path towards artificial general
intelligence, it has struggled to excel in multimodal tasks, which are still dominated by …

We present a unified transformer, ie, Show-o, that unifies multimodal understanding and
generation. Unlike fully autoregressive models, Show-o unifies autoregressive and …

We present Lumina-mGPT, a family of multimodal autoregressive models capable of various
vision and language tasks, particularly excelling in generating flexible photorealistic images …

In this paper, we introduce Janus, an autoregressive framework that unifies multimodal
understanding and generation. Prior research often relies on a single visual encoder for …

It is desirable but challenging to generate content-rich long videos in the scale of minutes.
Autoregressive large language models (LLMs) have achieved great success in generating …

We present Open-MAGVIT2, a family of auto-regressive image generation models ranging
from 300M to 1.5 B. The Open-MAGVIT2 project produces an open-source replication of …

Masked transformer models for class-conditional image generation have become a
compelling alternative to diffusion models. Typically comprising two stages-an initial VQGAN …

Building on the foundations of language modeling in natural language processing, Next
Token Prediction (NTP) has evolved into a versatile training objective for machine learning …

Diffusion models have become the dominant approach for visual generation. They are
trained by denoising a Markovian process which gradually adds noise to the input. We …

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation,
which sets a new state-of-the-art performance on the image generation task while …