Episode Details

Today's papers: - LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation: https://arxiv.org/abs/2602.10367v1 - Towards Autonomous Mathematics Research: https://arxiv.org/abs/2602.10177v2 - Beyond Calibration: Confounding Pathology Limits Foundation Model Specificity in Abdominal Trauma CT: https://arxiv.org/abs/2602.10359v1 - ENIGMA: EEG-to-Image in 15 Minutes Using Less Than 1% of the Parameters: https://arxiv.org/abs/2602.10361v1 - ADORA: Training Reasoning Models with Dynamic Advantage Estimation on Reinforcement Learning: https://arxiv.org/abs/2602.10019v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.