Edge Cases #004 with Coleman Hooper @ UC Berkeley (BAIR)
Hosted by AGI, Inc. + Juliana C + C K + Div Garg + Steve Frey + Jordan Ruppert + Naman Garg + Adam Awale + AGI Inc.
Register with organizer
What to look forward to
AGI, Inc.’s invite-only Edge Cases research night will feature UC Berkeley postdoctoral scholar Coleman Hooper (BAIR and SLICE Lab), whose work spans efficient LLM inference and ML hardware-software co-design. He’ll explain how diffusion language models and looped transformers can make on-device inference faster, including combined techniques achieving over 10× speedups, followed by an off-the-record Q&A and dinner.
Inside the event
Edge Cases is AGI, Inc.'s invite-only research night on what it takes to run real intelligence on-device.
Speaker
Coleman Hooper, postdoctoral scholar at UC Berkeley (BAIR and SLICE Lab). PhD at Berkeley, advised by Kurt Keutzer and Sophia Shao. Works on AI systems, efficient LLM inference and hardware-software co-design for ML. LinkedIn
Talk
Efficient edge inference through parallel and looped generation
In the cloud, LLM inference batches across many users. On a device there is one user, so decoding runs at batch size one and most of the hardware's parallel compute goes unused. Coleman will cover two ways around this. Diffusion language models refine several tokens in parallel, and his work trains them to need fewer refinement steps. Looped transformers pass each token through the model multiple times, and self-speculative decoding uses the earlier loops for drafting and the later loops for verification. The talk ends with recent work that combines the two for speedups above 10x.
Papers: MLSys 2026 · Springer chapter · one more on arXiv by the talk
Details
- Thursday, November 19, 5:30 PM
- Our founders' house in San Francisco. Exact address shared on approval.
- 30 to 40 minute talk, off-the-record Q&A, then dinner with the group
- For AI researchers, PhD students and research engineers
- Seats are limited and registration is approval-based
More about the series: theagi.company/edge-cases
Want to present your on-device research at a future Edge Cases? Apply here
San Francisco, CA
Venue listed by the organizer · San Francisco, CA. Confirm the final address before traveling.
Open in Google Maps ↗Details come from the event listing and the organizer page; registration is managed by the organizer.
Last checked: Nov 13, 2026. Confirm current availability before making plans.
Organizer page checked: Nov 13, 2026. Check registration for the latest details.