arXiv Artificial Intelligence

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

1 day ago 10.09.2026 07:00 👁 1 views
VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

Quick summary

arXiv:2609.07815v1 Announce Type: cross Abstract: Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise. Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals. In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs). Instead of treati

Key takeaways

  • arXiv:2609.07815v1 Announce Type: cross Abstract: Current text-to-image systems typically employ a "text encoder plus diffusion decoder" paradigm, in which text semantics directly modulate continuous latent noise.
  • Despite their success, these methods lack an explicit, interpretable intermediate representation that effectively bridges high-level linguistic semantics and low-level visual signals.
  • In this paper, we propose Vision-of-Thought (VoT), a framework that introduces a discrete visual-thinking layer between vision-language models (VLMs) and diffusion transformers (DiTs).

Why it matters

“VoT: Vision-of-Thought for Unified Multimodal Representation Alignment” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗