All sessions
Generative MediaSession
Generative Video at the Speed of Light
Keegan McCallum
- When
- Thursday, July 22:25 PM – 2:45 PM · 20 min
- Where
- Track 1San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
Discussing recent breakthroughs in realtime generative video models, and the new architectural problems and bottlenecks involved in creating immersive, interactive experiences on top of these models.
Speaker
Keegan McCallum
Founder, uRun
Founder of uRun, build the inference cloud for the interactive era of AI. Formerly Head of ML Infrastructure at Luma, built Video model serving for Dream Machine from scratch after pivot to generative video. Obsessed with the intersection of creativity and technology.
More in Generative Media
- Training Krea 2 - What matters in generative model training.Thursday, July 2 · 10:45 AM – 11:05 AM · Track 1
- HTML Is All Agents NeedThursday, July 2 · 11:10 AM – 11:30 AM · Track 1
- Building an Agentic Video Editor for Mass ConsumerThursday, July 2 · 11:40 AM – 12:00 PM · Track 1
- The Next Game Engine Won't Have a ManualThursday, July 2 · 12:05 PM – 12:25 PM · Track 1
- While my guitar gently speaksThursday, July 2 · 1:30 PM – 1:50 PM · Track 1
For developers: this programme is open data — JSON, iCal, schedule XML and an MCP endpoint.Show endpointsHide
- JSONEvery published session and speaker, in one request./aie-worldsfair-2026-import/feed.json
- iCalSubscribe in Google, Apple or Outlook Calendar./aie-worldsfair-2026-import/feed.ics
- Schedule XMLfrab / pentabarf — the format conference apps import./aie-worldsfair-2026-import/feed.xml
- MCP + RESTPoint Claude at the programme. OpenAPI 3.1 included./agents
No key, no signup, CORS open. Everything here is generated from the same data the organisers edit.