Louis Rouillard
where else to find them
what they talk about
where they keep going back
no series more than once — all 1 in the filters
on a stage with
never shared a talk
who talks about the same things
one talk is not yet a subject
| title | conference | date |
|---|---|---|
| RLHF for finer alignment with Gemma 3 | Gemma Developer Day Paris 2025 | 2025-03-12 |
Gemma 3 uses two concrete fixes to reduce RLHF reward hacking: train the reward model from the same policy to keep RM judgments in-distribution and build an… | ||
| nothing matches | ||