A 17B-parameter sparse MoE diffusion transformer activates 2B parameters per pass and reaches competitive quality on image generation benchmarks without post-training.
Janusflow: Harmonizing autoregression and rectified flow for unified multimodal understanding and generation
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 4roles
baseline 1polarities
baseline 1representative citing papers
Kling-Omni is a unified multimodal generative system that produces cinematic videos from diverse inputs by integrating generation, editing, and intelligent reasoning in a single end-to-end model.
HunyuanImage 3.0 is an open 80B-parameter multimodal autoregressive image generator that reportedly matches leading closed models on in-house benchmarks.
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
citing papers explorer
-
Nucleus-Image: Sparse MoE for Image Generation
A 17B-parameter sparse MoE diffusion transformer activates 2B parameters per pass and reaches competitive quality on image generation benchmarks without post-training.
-
Kling-Omni Technical Report
Kling-Omni is a unified multimodal generative system that produces cinematic videos from diverse inputs by integrating generation, editing, and intelligent reasoning in a single end-to-end model.
-
HunyuanImage 3.0 Technical Report
HunyuanImage 3.0 is an open 80B-parameter multimodal autoregressive image generator that reportedly matches leading closed models on in-house benchmarks.
-
Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.