Computer Vision podcasts

John Platt discusses how Google’s applied-science team chooses problems where AI can make a useful contribution. Topics include satellite-based detection and prediction of aircraft contrails, evaluation of rerouting trials, limitations of physical simulation, and the role of AI agents in scientific modelling and data work. The conversation also examines overfitting, action incentives, gradient-free optimisation, SMO and support-vector machines, the physical constraints on scaling, and opportunities for robotics and manufacturing to support climate technology. It concludes with FireSat’s approach to detecting small wildfires from orbit and the practical issues of coverage, cost and false positives.

Hosted by Ravid Shwartz Ziv, Allen Roush

Andrew Dai joins The Information Bottleneck to discuss language-model pre-training, next-token prediction, training-data quality and visual reasoning. The conversation examines counting and image understanding, world models and JEPA. Hosted by Ravid Shwartz-Ziv and Allen Roush.

Alex Smola discusses the development of voice agents, audiovisual systems and AI avatars. Topics include audio tokenization, inference cost, conversational latency, visual context and how artificial systems might learn from interaction while responding appropriately to human emotion.

Hosted by Sam Charrington

Justin Johnson joins Sam Charrington to discuss world models and spatial artificial intelligence. Topics include representations of three-dimensional environments, simulation and the role of such models in enabling systems to reason about and act within the physical world.

Hosted by Sam Charrington

Fatih Porikli examines why scaling image models alone does not guarantee visually correct results. He discusses separating scene planning from rendering, improving controllability and editing, and bringing high-resolution generation to edge devices, including the role of training objectives and reinforcement learning.

Hosted by Sam Charrington

Dhruv Batra connects embodied AI research with browser agents at Yutori. He explains why navigation from pixels to actions links virtual robots and web interaction, then discusses reinforcement learning on live websites, simulation-to-reality gaps and teleoperation. The conversation also examines competing views of intelligence, claims about scaling and the implications of agent-mediated browsing for the web. Hosted by Ravid Shwartz Ziv and Allen Roush. Watch the full conversation on the publisher’s YouTube channel.

Hosted by Ravid Shwartz Ziv, Allen Roush

Dustin Podell discusses developments in image generation at Black Forest Labs, from diffusion models to flow matching and FLUX. The conversation considers image editing, local inference and the transition from producing pictures to supporting more capable visual workflows.

Hosted by Chris Benson, Daniel Whitenack

Munawar Hayat discusses visual grounding and object hallucination in vision-language models. Topics include attention-guided alignment, contrastive learning for combined image-and-text retrieval, and evaluating images containing multiple people. The conversation connects identity leakage and attribute blending with the constraints of efficient on-device deployment.

Hosted by Sam Charrington

Devi Parikh discusses browser agents that act through visually grounded models. The conversation examines screenshots as an interface, training with supervised learning, rejection sampling and reinforcement learning, and coordinating tools and sub-agents. It considers reliability and the progression from background monitoring to autonomous web tasks.

Hosted by Sam Charrington

Hung Bui examines efficient diffusion models for image generation and editing on devices. The discussion covers SwiftBrush and SwiftEdit, distillation from iterative teachers into single-step students, and a coach network that aligns denoising behaviour. It also considers personalised agents and reasoning under fixed compute budgets.

Hosted by Sam Charrington

Jack Parker-Holder and Shlomi Fruchter explain Genie 3's interactive world-generation capabilities. They discuss architecture, real-time environments, visual memory and promptable events, trace the project's development, and consider how generated worlds could train embodied agents and guide future research on world models.

Hosted by Sam Charrington

Fatih Porikli discusses distillation techniques for efficient multimodal systems, including autonomous-driving scene understanding and planning, and sharper monocular depth estimation. The episode also reviews on-device demonstrations of 3D and video generation and visual question answering, connecting transformer and diffusion research with resource-constrained deployment.

Hosted by Sam Charrington

Paul Middlebrooks and Patryk Laurent examine how principles drawn from brains could help artificial intelligence learn from the real world. Laurent connects experience in neuroscience and AI with questions about perception, action, prediction and generalization. The conversation considers learning from continuous video, what embodied robotic systems reveal about intelligence, the relationship between language models and other forms of learning, and which biological details may matter when developing more capable AI.

Hosted by Paul Middlebrooks