Community feed
A focused stream of recent stories from the sources curated for this community. Latest: Preprint reports 20.5% fewer tokens for AI agent communication, Cross-Generation Optimization of YOLOv26, YOLOv11, and YOLOv8 for Fine-Grained Small-Object Detection and Instance Segmentation in Complex Orchards, and From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers. Page 256.
Planet AI Developer Filter
A preprint reports that RGA-Designer used 20.5% fewer tokens than ARG-Designer on average while maintaining similar benchmark accuracy across six datasets.
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23636: Cross-Generation Optimization of YOLOv26, YOLOv11, and YOLOv8 for Fine-Grained Small-Object Detection and Instance Segmentation in Complex Orchards
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23812: From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23806: Giga-Embeddings: Mixture-of-Experts Encoders for High-Throughput Text Embeddings
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23783: Inter-dimension Dependence for Multi-Dimensional Evaluation of Open-Ended Text
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23780: When Youth Enter The Chat: An Epistemic Shift in the Validation of LLM-Based Measures of Student Talk
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23719: ADE: Agentic Data Evolution Framework for Human-Centered Objectives
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23705: The Limits of Automatic Evaluation of Creativity in Large Language Models
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23645: Contextual Embedding Evidence for Main--Light Verb Distinctions in Urdu
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23570: Taming Visual Neglect: A Variational Information Bottleneck Framework for Adaptive Attention in Multimodal In-Context Learning
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23744: Calibration-Preserving Pruning: Compression as a Reliability Contract
Planet AI Developer Filter
Abstract page for arXiv paper 2608.23725: Response Renormalization for Critical Deep Equilibrium Models