Salut! There you go! Original tweet by @AnJamison: "@SethAbramson @buzz\_chronicles @buzz\\\_chronicles @buzz_chronicles save as cat...". Cheers! 👌
More from Buzz Chronicles
More from All
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)
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
A brief analysis and comparison of the CSS for Twitter's PWA vs Twitter's legacy desktop website. The difference is dramatic and I'll touch on some reasons why.
Legacy site *downloads* ~630 KB CSS per theme and writing direction.
6,769 rules
9,252 selectors
16.7k declarations
3,370 unique declarations
44 media queries
36 unique colors
50 unique background colors
46 unique font sizes
39 unique z-indices
https://t.co/qyl4Bt1i5x
PWA *incrementally generates* ~30 KB CSS that handles all themes and writing directions.
735 rules
740 selectors
757 declarations
730 unique declarations
0 media queries
11 unique colors
32 unique background colors
15 unique font sizes
7 unique z-indices
https://t.co/w7oNG5KUkJ
The legacy site's CSS is what happens when hundreds of people directly write CSS over many years. Specificity wars, redundancy, a house of cards that can't be fixed. The result is extremely inefficient and error-prone styling that punishes users and developers.
The PWA's CSS is generated on-demand by a JS framework that manages styles and outputs "atomic CSS". The framework can enforce strict constraints and perform optimisations, which is why the CSS is so much smaller and safer. Style conflicts and unbounded CSS growth are avoided.
Legacy site *downloads* ~630 KB CSS per theme and writing direction.
6,769 rules
9,252 selectors
16.7k declarations
3,370 unique declarations
44 media queries
36 unique colors
50 unique background colors
46 unique font sizes
39 unique z-indices
https://t.co/qyl4Bt1i5x

PWA *incrementally generates* ~30 KB CSS that handles all themes and writing directions.
735 rules
740 selectors
757 declarations
730 unique declarations
0 media queries
11 unique colors
32 unique background colors
15 unique font sizes
7 unique z-indices
https://t.co/w7oNG5KUkJ

The legacy site's CSS is what happens when hundreds of people directly write CSS over many years. Specificity wars, redundancy, a house of cards that can't be fixed. The result is extremely inefficient and error-prone styling that punishes users and developers.
The PWA's CSS is generated on-demand by a JS framework that manages styles and outputs "atomic CSS". The framework can enforce strict constraints and perform optimisations, which is why the CSS is so much smaller and safer. Style conflicts and unbounded CSS growth are avoided.
Keep dwelling on this:
Further Examination of the Motif near PRRA Reveals Close Structural Similarity to the SEB Superantigen as well as Sequence Similarities to Neurotoxins and a Viral SAg.
The insertion PRRA together with 7 sequentially preceding residues & succeeding R685 (conserved in β-CoVs) form a motif, Y674QTQTNSPRRAR685, homologous to those of neurotoxins from Ophiophagus (cobra) and Bungarus genera, as well as neurotoxin-like regions from three RABV strains
(20) (Fig. 2D). We further noticed that the same segment bears close similarity to the HIV-1 glycoprotein gp120 SAg motif F164 to V174.
https://t.co/EwwJOSa8RK
In (B), the segment S680PPRAR685 including the PRRA insert and highly conserved cleavage site *R685* is shown in van der Waals representation (black labels) and nearby CDR residues of the TCRVβ domain are labeled in blue/white
https://t.co/BsY8BAIzDa
Sequence Identity %
https://t.co/BsY8BAIzDa
Y674 - QTQTNSPRRA - R685
Similar to neurotoxins from Ophiophagus (cobra) & Bungarus genera & neurotoxin-like regions from three RABV strains
T678 - NSPRRA- R685
Superantigenic core, consistently aligned against bacterial or viral SAgs
Further Examination of the Motif near PRRA Reveals Close Structural Similarity to the SEB Superantigen as well as Sequence Similarities to Neurotoxins and a Viral SAg.
The insertion PRRA together with 7 sequentially preceding residues & succeeding R685 (conserved in β-CoVs) form a motif, Y674QTQTNSPRRAR685, homologous to those of neurotoxins from Ophiophagus (cobra) and Bungarus genera, as well as neurotoxin-like regions from three RABV strains
(20) (Fig. 2D). We further noticed that the same segment bears close similarity to the HIV-1 glycoprotein gp120 SAg motif F164 to V174.
https://t.co/EwwJOSa8RK

In (B), the segment S680PPRAR685 including the PRRA insert and highly conserved cleavage site *R685* is shown in van der Waals representation (black labels) and nearby CDR residues of the TCRVβ domain are labeled in blue/white
https://t.co/BsY8BAIzDa

Sequence Identity %
https://t.co/BsY8BAIzDa
Y674 - QTQTNSPRRA - R685
Similar to neurotoxins from Ophiophagus (cobra) & Bungarus genera & neurotoxin-like regions from three RABV strains
T678 - NSPRRA- R685
Superantigenic core, consistently aligned against bacterial or viral SAgs
