Episode Details

Today's papers: - QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing: https://arxiv.org/abs/2610.17829v2 - Hybrid Reasoning Agents: https://arxiv.org/abs/2610.18861v1 - Seeing, Maintaining, and Learning: The Evolution of Multimodal Agent Memory: https://arxiv.org/abs/2610.19366v1 - Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off: https://arxiv.org/abs/2610.19405v1 - Whose turn is it? Context-guided model routing for stateful agents: https://arxiv.org/abs/2610.19292v1 This podcast is from Colin Davis (colin-davis.com) using Claude & Elevenlabs.