Episode Details

Today's papers: - Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning: https://arxiv.org/abs/2606.16118v1 - Scalable Circuit Learning for Interpreting Large Language Models: https://arxiv.org/abs/2606.16939v1 - Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering: https://arxiv.org/abs/2606.17257v1 - WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning: https://arxiv.org/abs/2606.18147v1 - Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selection: https://arxiv.org/abs/2606.16868v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.