Ming-Yu Liu, Nvidia · Practical AI · Open models and the future of Physical AI with NVIDIA
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
Build open-source models on Nvidia hardware to test and iterate quickly, then let customers fine-tune those models for their own sensor setups
“We trained for 90 steps, with three seeds for each fine-tuned character model, nine runs in total… using Impossible Bench… broken tests… model could only get the reward if it tampered with the tests.”
“We asked inkling to fine tune itself using tinker. The model wrote its own fine tuning job, ran it and evaluated the result.”
“We can quickly make the robot… with a very minimal amount of fine tuning… very few amount of demonstrations and the model can readily do a bunch of the tasks”
“You may need a bit of fine-tuning of your probes so that they work on each person's particular fine-tuned model”
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.