Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
## Episode Summary In this episode, we cover: - **Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning** (Hugging Face Daily) - [Read more](https://huggingface.co/papers/2610.09450) - **AutoResearch at Production Scale: Failure Modes and a Multi-Agent Framework** (Hugging Face Daily) - [Read more](https://huggingface.co/papers/2609.30541) - **EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory** (arXiv) - [Read more](http://arxiv.org/abs/2610.10533v1) - **GRACE: Generation-aware latent compression for efficient video…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.