Seminar "Why does musical AI generate music that sounds so convincing yet so often uninteresting?" by François Pachet

  • Research
  • Science and society
Published on May 21, 2026 Updated on May 21, 2026
Dates

on the May 27, 2026

11:00 am
Location
Centre Inria d'Université Côte d'Azur
"Euler violet" room

Asbtract

What does it really mean to "generate music" with AI? While current models produce impressive results, they face a fundamental challenge: in music, there is no obvious cost function, no stable quality criterion, and no reliable learning signal.
Drawing on examples from musical AI, Markov models, LSTMs, the Continuator, transformers, and diffusion models, I will show that the real challenge is not merely to produce musically plausible outputs, but to design systems that are controllable, interactive, and appropriable by musicians. This perspective connects with several research threads at I3S, including constraints, generative models, optimization, and interactive systems.
 

Short bio

François Pachet got his Ph.D. and Habilitation from Université Pierre et Marie Curie (UPMC), after an engineer’s degree from Ecole des Ponts et Chaussées. He has been assistant professor in artificial intelligence at UPMC until 1997 when he joined SONY Computer Science Laboratory Paris to conduct research on interactive music listening, composition and performance. He became its director in 2015. In 2017, he joined Spotify to create the Content Technology Research Lab. He left in 2023 to start Ynosound, specialized in AI-assisted music composition and Imagine All The People, dedicated to AI-assisted decision making.

During his research career, he developed several award winning technologies such as constraint-based spatialisation, intelligent music scheduling using metadata and systems: MusicSpace, Continuator for interactive music improvisation, and Flow Composer which paved the way for AI-based score composition.

François Pachet has published intensively in artificial intelligence and computer music. He was elected  EurAI Fellow in 2014 and doctor Honoris Causa of the University of Pernambuco (Brazil) in 2017.

He was Principal Investigator of the Flow Machines ERC-funded project, which produced (with the musician SKYGGE) Daddy’s Car, a song in the style of the Beatles, and Hello World, the first mainstream music album composed with AI.

He is also a musician and has published two music albums (jazz and pop) as composer and performer, as well as an augmented book about the ontogenesis of a musical ear, Histoire d’une Oreille.

François Pachet is invited by Jean-Charles Régin, 3IA Chairholder.