ΑΙhub.org
Watch the invited talks (and much more) from #NeurIPS2019
Couldn’t make it to NeurIPS this week in Vancouver? Or simply unable to make your way to every exciting talk through the maze of 16k participants? Luckily, many of the sessions are available online.
To get started, we’ve embedded the invited talks below.
How To Know – Celeste Kidd
Veridical Data Science – Bin Yu
Machine learning meets single-cell biology: insights and challenges – Dana Pe’er
Social Intelligence – Blaise Aguera y Arcas
From System 1 Deep Learning to System 2 Deep Learning – Yoshua Bengio
Agency + Automation: Designing Artificial Intelligence into Interactive Systems – Jeff Heer
We’ll be featuring paper awards in a future post, so stay tuned.
Did you want us to feature your research? Send me an email with your blog post.
tags: NeurIPS
Sabine Hauert
is Associate Professor at the University of Bristol, and Executive Trustee of AIhub.org
Sabine Hauert
is Associate Professor at the University of Bristol, and Executive Trustee of AIhub.org
AUAI is supported by:
Related posts :
Interactive World Simulator for Robot Policy Training and Evaluation
Yixuan Wang
17 Jul 2026
Yixuan Wang discusses his faithful world simulator that allows robots to learn how to push, pick up, and grasp objects.
#ICML2026 social media round-up
AIhub
17 Jul 2026
We take a look at what the participants got up to in Seoul.
François Pachet on music generation with AI
Liliane-Caroline Demers
16 Jul 2026
“The day I hear a song of the quality of the Beatles, I will say: ‘Okay, we are done’. And I’ve never heard anything like that. Never.”
AI for science – talk recordings now available to watch
Lucy Smith
15 Jul 2026
Watch the invited talks from the day on YouTube.
AAAI presidential panel – factuality and trustworthiness
Lucy Smith
14 Jul 2026
Watch the latest panel discussion in the series based on the Future of AI research report from AAAI.
The secret to human ‘brilliance’ that AI just can’t match
Stanford Report
13 Jul 2026
New research reveals how people learn social conventions with minimal data – and why that sets us apart from LLMs.
Pre-training isn’t bitter enough
ML@CMU
10 Jul 2026
Given an unlabeled data stream, and a small set of verifiable downstream examples, can we use those examples during continued pre-training?
Interview with Thi Kieu Khanh Ho: Time-series anomaly detection
Lucy Smith
09 Jul 2026
How can we teach AI systems to recognize when something unusual or abnormal is happening in complex, real-world data streams, without relying on large amounts of labeled examples?
