Maybe it's because videos data contain a moderate amount of intermediate reasoning steps. For a natural/unedited video, everything is raw, live, and corrections are versioned while texts(on the web) tends to be the final version people publishes.
@jeande_d
-
Smooth search interface for 4000 NeurIPS accepted papers
By
–
A smooth way to search over 4k papers accepted to NeurIPS. Love the interface and responses' accuracy!! https://
neurips.exa.ai -
Research Visit at CMU: Multilingual Multimodal AI Focus
By
–
Some life updates: starting a research visit at @LTIatCMU
, working with truly amazing @gneubig and the team on range of topics in multimodal AI, most notably multilingual multimodal LLMs and multimodal evaluation. Excited for the journey and the opportunity to work along -
History of Attention Mechanism and Transformer Paper Development
By
–
History of "attention"(the idea that was popularized/packaged nicely by Transformer paper) and how everything came together, piece by piece.
-
Concise Machine Learning Paper from UC Berkeley
By
–
Concise Machine Learning – UC Berkeley https://
people.eecs.berkeley.edu/~jrs/papers/ma
chlearn.pdf
… -
Congratulations to François on Keras Legacy and New Journey
By
–
Congrats, François! Keras inspired thousands if not millions of people to begin their deep learning journey and through its design simplicity, it inspired the ecosystem of deep learning tools as whole. Wishing you the best in the new adventure!
-
Book covers deep fundamentals with math introduction for deep learning
By
–
The book is mostly for deep fundamentals, some of which might require some level of maths but there is a good introduction to maths for DL too right in Part I.
-
Deep Learning by Goodfellow Parts I and II Remain Valuable Resources
By
–
Part I and Part II of Deep Learning by Ian Goodfellow et al. are still golds!!!
-
Cornell CS5785 Applied Machine Learning Course with 80 Video Tutorials
By
–
Applied Machine Learning – Cornell CS5785 "Starting from the very basics, covering all of the most important ML algorithms and how to apply them in practice. Executable Jupyter notebooks (and as slides)". 80 videos!! Videos: https://
youtube.com/playlist?list=
PL2UML_KCiC0UlY7iCQDSiGDMovaupqc83
…
Code: https://
github.com/kuleshov/corne
ll-cs5785-2020-applied-ml
… -
Appreciation for New Multimodal LLM Articles
By
–
Great to see your new articles on multimodal LLMs:-)