Why Large? Tiny LMs & Agents on Edge/Robotics
Cormac Brick
- When
- Wednesday, July 12:50 PM – 3:10 PM · 20 min
- Where
- Track 2San Francisco, CA · imported from ai.engineer's public schedule feed
About this session
big models get a lot of press. small model scale much better. RAM is expensive. The real world needs tiny models for scale on the edge. This workshop will cover how to combine both for mobile and robotics deployment. specifically covering: - skills are different on mobile - tiny LLMs <1B scale much further on mobile/web - how to fine tune and train tiny models. - skills on robotics / edge/ mobile - latest open models for edge (including gemma, qwen, and anything else that happens in next 10 weeks) This talk will focus on open models, including some gemma variants that will be shortly announced.
Speaker
Principal Engineer, Google AI Edge, Google
Principal Engineer at Google working on edge AI. Lead on the Google AI Edge team and contributes to Gemma Model development. An early pioneer in Edge AI, his industry background includes leading Intel’s first laptop NPUs, as well as demonstrating edge AI on a USB key way back in NeurIPS 2016. These days he is technical lead for a team that drives multiple open source projects (Google AI Edge Gallery, LiteRT-LM, LiterRT, Xnnpack, Mediapipe) that enable Edge AI for billions of users.
More in Robotics & World Models
- Building the simulation infrastructure for practical world model useWednesday, July 1 · 10:45 AM – 11:05 AM · Track 2
- Building the simulation infrastructure for practical world model use (Part 2)Wednesday, July 1 · 11:10 AM – 11:30 AM · Track 2
- Commercial Grade-Robots for Real World UsageWednesday, July 1 · 11:40 AM – 12:00 PM · Track 2
- Unitree: Building Mass Produced HumanoidsWednesday, July 1 · 1:30 PM – 1:50 PM · Track 2
- Frontier Robotics ResearchWednesday, July 1 · 1:55 PM – 2:15 PM · Track 2
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.