AI Papers - 2026-04-21

Today's papers: - MobileAgeNet: Lightweight Facial Age Estimation for Mobile Deployment: https://arxiv.org/abs/2604.17007v1 - Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale: https://arxiv.org/abs/2604.18572v1 - mEOL: Training-Free Instruction-Guided Multimodal Embedder for Vector Graphics and Image Retrieval: https://arxiv.org/abs/2604.17054v1 - Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval: https://arxiv.org/abs/2604.15951v2 - DGSSM: Diffusion guided state-space models for multimodal salient object detection: https://arxiv.org/abs/2604.17585v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.