IndabaX Rwanda @ ICLR 2023 – Kigali, May 4th Deep Learning Indaba is a great community. It is coming to Rwanda this May during ICLR. Applications to attend IndabaX Rwanda are open. Researchers who also want to present their works are welcome. Apply here: https://
docs.google.com/forms/d/e/1FAI
pQLSemBiT28abBTC9H_8Q_YoQzesZtMbrUcaZYAaPudiZHd21hew/viewform
…
@jeande_d
-
IndabaX Rwanda at ICLR 2023 – Applications Now Open
By
–
-
Multimodal Learning Research: Upcoming Resource Collection
By
–
Multimodal learning is one of my favorites areas of research. We've done a great job of designing systems that learn from single modalities but not so much about learning from multiple modalities. I am putting MML resources together and will share over the next couple of days.
-
Sam’s interviews reveal insights on AI risks and societal transformation
By
–
I've been enjoying watching Sam's interviews a lot these days. There is always a hint of what's ahead. This one is about the risks of AI and how it will reshape society. And tough questions! https://
youtube.com/watch?v=540vzM
lf-54
… -
Copilot et VS Code simplifient la programmation avec l’autocomplétion
By
–
Copilot and VS Code make things way easier. I like to pass instructions via a sequence of comments and I am always surprised by its code completion capability.
-
BLIP-2 and Visual ChatGPT: Two Advances in Computer Vision
By
–
BLIP-2:
https://arxiv.org/abs/2301.12597
Visual ChatGPT:
https://arxiv.org/abs/2303.04671 -
BLIP-2: Efficient AI Research Using Frozen Models and Low Compute
By
–
BLIP-2 is a great case study for people who want to do great works with less compute. Amazing how far using frozen models can get you! There are other similar studies such as Visual ChatGPT. VisualChatGPT indeed took it to another level.
-
Carnegie Mellon Multimodal Machine Learning Course Videos
By
–
So good to see courses that are dedicated to this new and vibrant area of AI research. Lecture videos of Multimodal Machine Learning (MML) offered at Carnegie Mellon: https://
youtube.com/playlist?list=
PL-Fhd_vrvisNM7pbbevXKAbT_Xmub37fA
… Follow @Jeande_d for more learning resources and trends in AI research. -
Multimodal Machine Learning: Fusing Vision, Audio, Text, and Actions
By
–
Multimodal machine learning is a hot area in AI research. Unimodal learning has developed massively in the last 5 years. The challenge now is how we fuse different modalities(vision, audio, text, robot actions) into a single agent. GPT-4 & similar models are the beginning.
-
Multimodal Machine Learning Course Carnegie Mellon 2022
By
–
Multimodal Machine Learning – Carnegie Mellon, 2022 A great series of lectures on multimodal machine learning(MML). The course covers fundamental concepts related to MML and recent state-of-the-art MML systems. Lectures: https://
youtube.com/playlist?list=
PL-Fhd_vrvisNM7pbbevXKAbT_Xmub37fA
… Webpage: https://
cmu-multicomp-lab.github.io/mmml-course/fa
ll2022/
… -
OpenAI GPT-4 Developer Livestream: Features and Capabilities Overview
By
–
One last thing: OpenAI just hosted GPT-4 Developer Livestream. This is a nice watch and a quick way to see a glimpse of all cool things you can do with GPT-4. https://
youtube.com/watch?v=outcGt
bnMuQ
…