PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

## Episode Summary In this episode, we cover: - **PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception** (arXiv) - [Read more](http://arxiv.org/abs/2606.28322v1) - **Agent-Native Immune System: Architecture, Taxonomy, and Engineering** (arXiv) - [Read more](http://arxiv.org/abs/2606.28270v1) - **RSICCLLM: A Multimodal Large Language Model for Remote Sensing Image Change Captioning** (arXiv) - [Read more](http://arxiv.org/abs/2606.28266v1) - **The Tatoxa System for Text Detoxification in Low-Resource Languages: The Case of Tatar** (Hugging Face Daily) - [Read more](https://huggingface.co/papers/2606.26015) - **How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring** (Hugging Face Daily) - [Read more](https://huggingface.co/papers/2606.26979) --- *Sponsored by LimitLess AI*