We are starting in a couple of minutes!

Alexis Conneau Alexis Conneau on Conversational Speech Turing Test #audioimagination2024

Joon Son Chung on Giving Face and Voice to AI #audioimagination2024.

Yao Xie on Generative Models for Statistical Inference: Advancing Probabilistic Representations. #audioimagination2024 #NeurIPS2024

Vikas Chandra Vikas Chandra on Audio Generation for AR/VR/MR

It was exciting to see the amazing turnout at our Audio Imagination Workshop NeurIPS Conference #NeurIPS2024. Grateful to everyone, invited speakers, panelists, authors and participants for the interesting presentations, discussions, and engagement. audio-imagination.com

``SyncFlow: Toward Temporally Aligned Joint Audio-Video Generation from Text,'' Haohe Liu, Gael Le Lan, Xinhao Mei, Zhaoheng Ni, Anurag Kumar, Varun Nagaraja, Wenwu Wang, Mark D. Plumbley, Yangyang Shi, Vikas Chandra, ift.tt/sxluwgt

Excited to share our work at COLING 2025! While I couldn’t attend in person, Jad Kabbara will be presenting today at the 1:30 PM poster session. Come by to learn how we’re using LLMs to improve understanding in social conversations! #COLING2025 #NLProc

``Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment,'' Joanna Hong, Sanjeel Parekh, Honglie Chen, Jacob Donley, Ke Tan, Buye Xu, Anurag Kumar, ift.tt/5JkZ0Gp

So happy to share that our work has been accepted to SIGIR 2025. Thank you to my amazing collaborators! Negar Arabzadeh, Andrea Tupini, Yuxuan Sun, Alexey Skrynnik, Artem Zholus, Marc-Alexandre Côté and Julia Kiseleva Pre-print: arxiv.org/pdf/2407.08898

Career Update: Excited to join Google Deepmind Google DeepMind to continue working on audio/speech/multimodal AI. I left Meta Meta after more than 6 years and I will definitely miss working with some amazing friends and colleagues. Super thankful for all the fun collaborations.

RL is not all you need, nor attention nor Bayesianism nor free energy minimisation, nor an age of first person experience. Such statements are propaganda. You need thousands of people working hard on data pipelines, scaling infrastructure, HPC, apps with feedback to drive