Episode Details

Today's papers: - Multi-Agent Egocentric World Model with Fine-Grained Embodied Interaction: https://arxiv.org/abs/2610.12299v1 - Mid-Training Language Models on Raw Video: https://arxiv.org/abs/2610.11019v1 - Unifying Policy Learning and State Prediction through Spatial Language Modeling: https://arxiv.org/abs/2610.12172v1 - Zatom-2: Multitask Pretraining on Atomistic Data for Generative Modeling across Domains: https://arxiv.org/abs/2610.11454v1 - Looking Inside LLMs: Small-World Connectivity as a Signature of Reasoning Performance: https://arxiv.org/abs/2610.12304v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.