Episode Details

Today's papers: - Beyond Uniform Forgetting: A Study of Sequential Direct Preference Optimization Across Preference Settings: https://arxiv.org/abs/2606.19744v1 - Co-policy: Responsive Human-Robot Co-Creation for Musical Performances: https://arxiv.org/abs/2606.19914v1 - How Transparent is DiffusionGemma?: https://arxiv.org/abs/2606.20560v1 - See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View: https://arxiv.org/abs/2606.20045v1 - Evaluating and Enhancing Negation Comprehension in Remote Sensing MLLMs: https://arxiv.org/abs/2606.20177v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.