More from #AnationalistWarrior_ A Proud Indian Hindu

I first met her in Coimbatore,when she was doing the film , ஆயிரத்தில் ஒருவன் with the late MGR. She had come down for a dance recital , & was put up in hotel Alankar which was supposedly the best , those times ; the meeting was brief and as I grew up the charm changed to others


2. she was on her way up as Star; it must've been nearly 4 to 5 years, the editor of our college magazine wanted me to do an article on her, (by that time she was known as s gutsy person, no holds barred); I was rather taken aback when she recollected our earlier meet and then

4. All went smooth. I was in touch with her on and off and I was never into the movies , as I disliked their debauchery and multi faceted life style , however I was in touch with late Nagesh, JaiShankar, and a couple of others. It was fun being with them and I was elevated from

3. my favourite E stand at chepauk to pavilion terrace as Nagesh was a member and one ticket was for me always. She went into politics and our contact was lesser, except when she took a daring stand on the subject of Lord Rama: quote " சிலரை போல், நான் இல்லை. எனக்கு ராமர் கடவுள்

5. அவர் எனக்கு எப்போதும் வேண்டும் ". This was a dig at BJP who had at that period were playing low key on RJB. I was just out of the leftist clutches and this took me by surprise. She was a member of the RS, by then. I wrote a letter , appreciating her and it was responded to

More from All

1. Mini Thread on Conflicts of Interest involving the authors of the Nature Toilet Paper:
https://t.co/VUYbsKGncx
Kristian G. Andersen
Andrew Rambaut
Ian Lipkin
Edward C. Holmes
Robert F. Garry

2. Thanks to @newboxer007 for forwarding the link to the research by an Australian in Taiwan (not on

3. K.Andersen didn't mention "competing interests"
Only Garry listed Zalgen Labs, which we will look at later.
In acknowledgements, Michael Farzan, Wellcome Trust, NIH, ERC & ARC are mentioned.
Author affiliations listed as usual.
Note the 328 Citations!
https://t.co/nmOeohM89Q


4. Kristian Andersen (1)
Andersen worked with USAMRIID & Fort Detrick scientists on research, with Robert Garry, Jens Kuhn & Sina Bavari among


5. Kristian Andersen (2)
Works at Scripps Research Institute, which WAS in serious financial trouble, haemorrhaging 20 million $ a year.
But just when the first virus cases were emerging, they received great news.
They issued a press release dated November 27, 2019:
How can we use language supervision to learn better visual representations for robotics?

Introducing Voltron: Language-Driven Representation Learning for Robotics!

Paper: https://t.co/gIsRPtSjKz
Models: https://t.co/NOB3cpATYG
Evaluation: https://t.co/aOzQu95J8z

🧵👇(1 / 12)


Videos of humans performing everyday tasks (Something-Something-v2, Ego4D) offer a rich and diverse resource for learning representations for robotic manipulation.

Yet, an underused part of these datasets are the rich, natural language annotations accompanying each video. (2/12)

The Voltron framework offers a simple way to use language supervision to shape representation learning, building off of prior work in representations for robotics like MVP (
https://t.co/Pb0mk9hb4i) and R3M (https://t.co/o2Fkc3fP0e).

The secret is *balance* (3/12)

Starting with a masked autoencoder over frames from these video clips, make a choice:

1) Condition on language and improve our ability to reconstruct the scene.

2) Generate language given the visual representation and improve our ability to describe what's happening. (4/12)

By trading off *conditioning* and *generation* we show that we can learn 1) better representations than prior methods, and 2) explicitly shape the balance of low and high-level features captured.

Why is the ability to shape this balance important? (5/12)

You May Also Like