Geoffrey Cideron

@CdrGeo

Research Engineer at Google DeepMind. Spent time at FAIR London, INRIA Lille, and Instadeep.

Joined March 2019

415

Geoffrey Cideron
@CdrGeo
Oct 10, 2024
Happy to introduce our new paper "Diversity-Rewarded CFG Distillation". We combine distillation, a novel diversity reward, and model merging to improve the quality-diversity tradeoff of MusicLM. arxiv: arxiv.org/abs/2410.06084 More info:
Alexandre Ramé
@ramealexandre
Oct 10, 2024
An AI will win a Nobel price someday✨. Yet currently, alignment reduces creativity. Our new @GoogleDeepMind paper "diversity-rewarded CFG distillation" improves quality AND diversity for music, via distillation of test-time compute, RL with a diversity reward, and model merging.
Geoffrey Cideron
@CdrGeo
Feb 7, 2024
Happy to introduce our paper MusicRL, the first music generation system finetuned with human preferences. Paper link:
arxiv.org
MusicRL: Aligning Music Generation to Human Preferences
We propose MusicRL, the first music generation system finetuned from human feedback. Appreciation of text-to-music models is particularly subjective since the concept of musicality as well as the...
Geoffrey Cideron
@CdrGeo
Dec 30, 2020
It was great to work with @AmartyaSanyal, @_rockt, and @egrefen at FAIR London. This line of research is fascinating! Thank you for the opportunity! Additional gratitude to @RCalandra for the support and advice.
Edward Grefenstette
@egrefen
Dec 29, 2020
Replying to @egrefen
I've been thinking a lot about this work recently, esp. the fascinating ML problems that emerge when you want to solve it without generating doc/env variants. Ongoing work on this with @AmartyaSanyal+@CdrGeo who I had the pleasure of remotely hosting as interns this year. [3/14]