Abstract We introduce Generative Infinite-Vocabulary Transformers (GIVT) which generate
vector sequences with real-valued entries, instead of discrete tokens from a finite …

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

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and
tones, marks a milestone for omni-modal foundation models. However, empowering Large …

Generalization capabilities, or rather a lack thereof, is one of the most important unsolved
problems in the field of robot learning, and while several large scale efforts have set out to …

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

The recent large-scale text-to-speech (TTS) systems are usually grouped as autoregressive
and non-autoregressive systems. The autoregressive systems implicitly model duration but …

Modern image generation (IG) models have been shown to capture rich semantics valuable
for image understanding (IU) tasks. However, the potential of IU models to improve IG …

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that
redefines the autoregressive learning on images as coarse-to-fine" next-scale prediction" or" …

Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o,
have captured significant attention in the speech domain. Compared to traditional three-tier …

Recent studies have demonstrated the effectiveness of token-based methods for visual
content generation. As a representative work, non-autoregressive Transformers (NATs) are …