pith. machine review for the scientific record. sign in

Generative pretraining from pixels

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 2

years

2025 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

MMaDA: Multimodal Large Diffusion Language Models

cs.CV · 2025-05-21 · unverdicted · novelty 6.0

MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.

Show-o2: Improved Native Unified Multimodal Models

cs.CV · 2025-06-18 · unverdicted · novelty 4.0

Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.

citing papers explorer

Showing 2 of 2 citing papers.

  • MMaDA: Multimodal Large Diffusion Language Models cs.CV · 2025-05-21 · unverdicted · none · ref 98

    MMaDA is a unified multimodal diffusion model using mixed chain-of-thought fine-tuning and a new UniGRPO reinforcement learning algorithm that outperforms specialized models in reasoning, understanding, and text-to-image tasks.

  • Show-o2: Improved Native Unified Multimodal Models cs.CV · 2025-06-18 · unverdicted · none · ref 22

    Show-o2 unifies text, image, and video understanding and generation in a single autoregressive-plus-flow-matching model built on 3D causal VAE representations.