Episode Details

Today's papers: - Verifiable Social Reasoning for LLM Assistants: https://arxiv.org/abs/2609.17496v1 - MUMINS: Metadata-conditioned Uncertainty-aware Medical Image Next-state Synthesis: https://arxiv.org/abs/2609.17169v1 - VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs: https://arxiv.org/abs/2609.16722v1 - Vision And Text Transformer For Predicting Answerability On Visual Question Answering: https://arxiv.org/abs/2609.16565v1 - PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control: https://arxiv.org/abs/2609.17521v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.