| |
|
| |
Edge Cases is AGI's invite-only research night on what it takes to run real intelligence on-device.
Speaker
Coleman Hooper, postdoctoral scholar at UC Berkeley (BAIR & SLICE Lab). PhD at Berkeley, advised by Kurt Keutzer & Sophia Shao. Works on AI systems, efficient LLM inference & hardware-software co-design for ML. LinkedIn
Talk
Efficient edge inference through parallel & 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 & most of the hardware's parallel compute goes unused. Coleman will cover two ways around this. Diffusion language models refine several tokens in parallel, & his work trains them to need fewer refinement steps. Looped transformers pass each token through the model multiple times, & self-speculative decoding uses the earlier loops for drafting & 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 & research engineers
Seats are limited & 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
|
|
|
|
|
|
|
|