JanusFlow: Unified Multimodal Understanding and Generation via Autoregressive Flow
Suraj Khanal
About JanusFlow: Unified Multimodal Understanding and Generation via Autoregressive Flow
JanusFlow unifies image understanding/generation using rectified flow and an autoregressive model. It decouples encoders for tasks, aligning representations during training. Training occurs in 3 stages: adaptation, pre-training, and fine-tuning. This achieves strong performance in both areas with 1.3B parameters
- Publisher
- Suraj Khanal
- Category
- technology
- Language
- en
- Explicit
- No
- First episode
- 27 Feb 2025
- Latest episode
- 27 Feb 2025
Pod Engine is an independent podcast discovery and analytics service and is not affiliated with or endorsed by this podcast. Artwork and show content belong to their owners. Full legal notice.