Paris NeurIPS 2026 Workshop

Invited Speakers

Paris, France

Keynote talks will provide great insights on the current trends in Real-Time Multimodal Conversational AI from renowned and impactful scientists within the community. The workshop will feature four keynote talks.

Alexandre Défossez - Gradium / Kyutai

Title to be announced

Abstract: TBA

Biography: Alexandre is a co-founder of Kyutai, a non profit lab for research in artificial intelligence based in Paris committed to open science. His work covers generative speech and multimodal AI (Moshi, Hibiki, DSM) with a strong focus on handling multiple streams jointly across modalities in a streaming and low latency fashion. He is also a co-founder and Chief Science Officer at Gradium, a startup launched in 2025 whose mission is to commercialize the best possible voice AI experience. Before that, Alexandre was a scientist for 3 years at Facebook AI Research in Paris, where he led the development of models for audio compression and modeling (AudioCraft, MusicGen, EnCodec).

Tara Sainath - Google DeepMind

Title to be announced

Abstract: Large Language Models (LLMs) have recently introduced a paradigm shift in Machine Learning, including in audio processing tasks. In automatic speech recognition, we have improved understanding quality across a large number of languages, trained within one universal model. In generation, prompt-based capabilities and naturalness have opened up new paradigm shifts. In translation, we can translate numerous language pairs in real time. Finally, in dialogue, we can build single end-to-end systems that understand and reply to user queries. These capabilities are transforming audio products across the industry. In this talk, I will detail the research and product impact of audio LLMs at Google.

Biography: Dr. Tara Sainath holds an S.B., M.Eng, and PhD in Electrical Engineering and Computer Science from MIT. Her expertise in speech recognition and deep neural networks led to a 5 year stint at IBM T.J. Watson Research Center, and currently fuels her work as a Tech Lead in Google DeepMind's Audio Pillar. There, she focuses on the integration of audio capabilities with large language models (LLMs).
Her technical prowess is recognized through her IEEE Fellowship and awards such as the 2021 IEEE SPS Industrial Innovation Award and co-recipient of the 2022 IEEE SPS Signal Processing Magazine Best Paper Award. She has served as a member of the IEEE Speech and Language Processing Technical Committee (SLTC) as well as the Associate Editor for IEEE/ACM Transactions on Audio, Speech, and Language Processing. Dr. Sainath's leadership is exemplified by her roles as Program Chair for ICLR (2017, 2018) and her extensive work co-organizing influential conferences and workshops, including: Interspeech (2010, 2016, 2019), ICML (2013, 2017), and NeurIPS 2020. Her primary research interests are in deep neural networks for speech recognition.

Mohamed Chetouani - Sorbonne University

Title to be announced

Abstract: TBA

Biography: Prof. Mohamed Chetouani is currently a Full Professor in signal processing and machine learning for human-machine interaction. He is the Deputy Director the Institute of Intelligent Systems and Robotics (CNRS UMR 7222), Sorbonne University (formerly Pierre and Marie Curie University). His activities cover social signal processing, social robotics and interactive machine learning with applications in psychiatry, psychology, social neuroscience and education. He was the coordinator of the ANIMATAS H2020 Marie Sklodowska Curie European Training Network (2018-2022). He was the President of the Sorbonne University Ethics Committee from 2019 to 2023. He was involved in several educational activities including organization of summer schools. He was member of the EU Networks of Human-Centered AI (HumanE AI NET) and Robotics (euROBIN). He was General Chair of ACM ICMI 2023 and VIHAR 2021. He served as Associate Editor of IEEE Transactions on Affective Computing. He co-published several books and proceedings, including the Human-Centered Artificial Intelligence (Springer, 2023) and the Handbook of Human-AI Collaboration (2026). He was in charge of the inclusion of Students with Disabilities for the Faculty of Science and Engineering of Sorbonne University.

Rachel McDonnell - Trinity College Dublin

Title to be announced

Abstract: TBA

Biography: Rachel McDonnell is Professor in Creative Technologies and a Fellow of Trinity College Dublin, where she heads the Graphics and Vision discipline. She is also a Principal Investigator in the ADAPT Research Centre. Her research combines computer graphics, AI and human perception to develop believable and expressive virtual humans. Her work on speech-driven gesture synthesis explores how character movements can be generated from speech, alongside perceptual research investigating how characters’ appearance, gestures and voice influence their perceived personality, realism and social appeal. She is an Associate Editor for ACM Transactions on Applied Perception and regularly publishes at leading graphics and immersive technology venues, including ACM SIGGRAPH, IEEE VR and IEEE ISMAR. Her research has received best paper awards at venues such as IEEE VR and the ACM International Conference on Intelligent Virtual Agents (IVA).

Page updated

Google Sites

Report abuse