Akash Sharma
@akashsharma02.bsky.social
Ph.D. student at CMU Robotics Institute | Visiting Researcher at FAIR Meta
Opinions expressed are my own
📍Pittsburgh, USA 🔗 akashsharma02.github.io
Opinions expressed are my own
📍Pittsburgh, USA 🔗 akashsharma02.github.io
Pinned
Akash Sharma
@akashsharma02.bsky.social
· May 27
Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tactile sensing or use specific architectures per tactile task.
Can 1 model improve many tactile tasks?
🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c
1/6
Can 1 model improve many tactile tasks?
🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c
1/6
Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tactile sensing or use specific architectures per tactile task.
Can 1 model improve many tactile tasks?
🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c
1/6
Can 1 model improve many tactile tasks?
🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c
1/6
May 27, 2025 at 2:44 PM
Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tactile sensing or use specific architectures per tactile task.
Can 1 model improve many tactile tasks?
🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c
1/6
Can 1 model improve many tactile tasks?
🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c
1/6
Last week I passed my thesis proposal, and I'm now officially a Ph.D. candidate!
I'm grateful to my committee, and everyone who supported me.
My proposed thesis "Self supervised perception for tactile dexterity" will explore ways to improve dexterous manipulation using tactile reps.
I'm grateful to my committee, and everyone who supported me.
My proposed thesis "Self supervised perception for tactile dexterity" will explore ways to improve dexterous manipulation using tactile reps.
May 11, 2025 at 1:28 PM
Last week I passed my thesis proposal, and I'm now officially a Ph.D. candidate!
I'm grateful to my committee, and everyone who supported me.
My proposed thesis "Self supervised perception for tactile dexterity" will explore ways to improve dexterous manipulation using tactile reps.
I'm grateful to my committee, and everyone who supported me.
My proposed thesis "Self supervised perception for tactile dexterity" will explore ways to improve dexterous manipulation using tactile reps.
Reposted by Akash Sharma
I asked "on the other platform" what were the most important improvements to the original 2017 transformer.
That was quite popular and here is a synthesis of the responses:
That was quite popular and here is a synthesis of the responses:
April 28, 2025 at 6:47 AM
I asked "on the other platform" what were the most important improvements to the original 2017 transformer.
That was quite popular and here is a synthesis of the responses:
That was quite popular and here is a synthesis of the responses:
Reposted by Akash Sharma
⏰ Heads up! The deadline for two #CVPR2025 Autonomous Grand Challenge tracks is May 10th, 2025:
1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20...
2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...
1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20...
2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...
April 28, 2025 at 9:41 AM
⏰ Heads up! The deadline for two #CVPR2025 Autonomous Grand Challenge tracks is May 10th, 2025:
1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20...
2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...
1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20...
2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...
Reposted by Akash Sharma
I love situations like this: in the pre-deep era (and following classical learning theory), people would have stopped training the white model at the red arrow, as the validation error increases. But, no, the model first seems to learns unwanted short cuts (overfitting wildly) but finds a way out.
March 27, 2025 at 3:30 PM
I love situations like this: in the pre-deep era (and following classical learning theory), people would have stopped training the white model at the red arrow, as the validation error increases. But, no, the model first seems to learns unwanted short cuts (overfitting wildly) but finds a way out.
Some pictures of the Pittsburgh spring to reduce the spiciness of the bsky feed!
a6700 w/ 17-70mm Tamron lens
a6700 w/ 17-70mm Tamron lens
March 26, 2025 at 3:47 PM
Some pictures of the Pittsburgh spring to reduce the spiciness of the bsky feed!
a6700 w/ 17-70mm Tamron lens
a6700 w/ 17-70mm Tamron lens
Reposted by Akash Sharma
A new #CosmicDistanceLadder post on why lunar and solar eclipses tend to come in pairs (for instance, the solar eclipse next week is paired with the lunar eclipse from last week). www.instagram.com/p/DHkS3EcA40L
March 24, 2025 at 4:42 AM
A new #CosmicDistanceLadder post on why lunar and solar eclipses tend to come in pairs (for instance, the solar eclipse next week is paired with the lunar eclipse from last week). www.instagram.com/p/DHkS3EcA40L
Reposted by Akash Sharma
What would you love to know about #robot learning and decision making?
Later this season, I'll be chatting to Prof. Lerrel Pinto (@lerrelpinto.com) from NYU about using machine learning to train robots to adapt to new environments.
Send me your questions for Lerrel: robottalk.org/ask-a-question/
Later this season, I'll be chatting to Prof. Lerrel Pinto (@lerrelpinto.com) from NYU about using machine learning to train robots to adapt to new environments.
Send me your questions for Lerrel: robottalk.org/ask-a-question/
March 18, 2025 at 10:11 AM
What would you love to know about #robot learning and decision making?
Later this season, I'll be chatting to Prof. Lerrel Pinto (@lerrelpinto.com) from NYU about using machine learning to train robots to adapt to new environments.
Send me your questions for Lerrel: robottalk.org/ask-a-question/
Later this season, I'll be chatting to Prof. Lerrel Pinto (@lerrelpinto.com) from NYU about using machine learning to train robots to adapt to new environments.
Send me your questions for Lerrel: robottalk.org/ask-a-question/
Reposted by Akash Sharma
We are looking for a student researcher to work on video understanding plus 3D, in Google DeepMind London. DM/Email me or pass it to someone if you feel it may be a good fit!
March 5, 2025 at 8:44 PM
We are looking for a student researcher to work on video understanding plus 3D, in Google DeepMind London. DM/Email me or pass it to someone if you feel it may be a good fit!
Reposted by Akash Sharma
The first measles death in the US in a decade -- the tragic, preventable death of a child whose parents chose not to protect them with vaccination -- should spark an immediate nation-wide campaign to ensure all children are protected against preventable diseases. Anything less is unconscionable.
February 26, 2025 at 7:36 PM
The first measles death in the US in a decade -- the tragic, preventable death of a child whose parents chose not to protect them with vaccination -- should spark an immediate nation-wide campaign to ensure all children are protected against preventable diseases. Anything less is unconscionable.
Reposted by Akash Sharma
Gearing up for our workshop on 4D Vision at @CVPR this June! Check out our line up of speakers and submit your work by Mar 28. Spread the word!
Really excited to put together this #CVPR2025 workshop on "4D Vision: Modeling the Dynamic World" -- one of the most fascinating areas in computer vision today!
We've invited incredible researchers who are leading fantastic work at various related fields.
4dvisionworkshop.github.io
We've invited incredible researchers who are leading fantastic work at various related fields.
4dvisionworkshop.github.io
February 12, 2025 at 1:35 PM
Gearing up for our workshop on 4D Vision at @CVPR this June! Check out our line up of speakers and submit your work by Mar 28. Spread the word!
Reposted by Akash Sharma
Last night I found out that the NSF math postdoctoral fellowship I applied for is being deleted because it does not comply with Trump’s executive orders on DEI in the federal government. I’m going to answer some FAQs and share some thoughts about this ordeal in this thread 1/n
February 8, 2025 at 6:42 PM
Last night I found out that the NSF math postdoctoral fellowship I applied for is being deleted because it does not comply with Trump’s executive orders on DEI in the federal government. I’m going to answer some FAQs and share some thoughts about this ordeal in this thread 1/n
Seeing some of the early results from DexterityGen were definitely a wow moment for me!
It doesn't take a lot to realize all the new opportunities a strong teleop system like this enables! 🚀
X thread: x.com/zhaohengyin/...
Link: zhaohengyin.github.io/dexteritygen/
It doesn't take a lot to realize all the new opportunities a strong teleop system like this enables! 🚀
X thread: x.com/zhaohengyin/...
Link: zhaohengyin.github.io/dexteritygen/
DexGen
zhaohengyin.github.io
February 8, 2025 at 3:02 AM
Seeing some of the early results from DexterityGen were definitely a wow moment for me!
It doesn't take a lot to realize all the new opportunities a strong teleop system like this enables! 🚀
X thread: x.com/zhaohengyin/...
Link: zhaohengyin.github.io/dexteritygen/
It doesn't take a lot to realize all the new opportunities a strong teleop system like this enables! 🚀
X thread: x.com/zhaohengyin/...
Link: zhaohengyin.github.io/dexteritygen/
Reposted by Akash Sharma
Not one VC would ever fund a startup to do the kind of hardcore optimization work that DeepSeek did.
Every VC firm should be asking themselves why.
Every VC firm should be asking themselves why.
January 28, 2025 at 5:00 AM
Not one VC would ever fund a startup to do the kind of hardcore optimization work that DeepSeek did.
Every VC firm should be asking themselves why.
Every VC firm should be asking themselves why.
Reposted by Akash Sharma
just warms my heart to see how they're citing my stuff --
"some people have done some thing [7]"
"most work is inadequate [8]"
"unlike prior work [7,8,9], we don't suck"
7. Bigham
8. Bigham
9. Bigham
them increasing my hindex is joke on them! 😂
"some people have done some thing [7]"
"most work is inadequate [8]"
"unlike prior work [7,8,9], we don't suck"
7. Bigham
8. Bigham
9. Bigham
them increasing my hindex is joke on them! 😂
January 17, 2025 at 8:32 PM
just warms my heart to see how they're citing my stuff --
"some people have done some thing [7]"
"most work is inadequate [8]"
"unlike prior work [7,8,9], we don't suck"
7. Bigham
8. Bigham
9. Bigham
them increasing my hindex is joke on them! 😂
"some people have done some thing [7]"
"most work is inadequate [8]"
"unlike prior work [7,8,9], we don't suck"
7. Bigham
8. Bigham
9. Bigham
them increasing my hindex is joke on them! 😂
Reposted by Akash Sharma
A new dawn, a golden era of boot licking before us. Unheralded, unimaginable forms of boot licking to be discovered
January 7, 2025 at 2:20 PM
A new dawn, a golden era of boot licking before us. Unheralded, unimaginable forms of boot licking to be discovered
Reposted by Akash Sharma
It’s kinda wild how much of ML is tradition. Not always in a bad way, just that there’s so damn much that you’re forced to rely on others’ recommendations for models, hyperparameters, training sets, loss metrics, architectures, and quirky practices.
December 18, 2024 at 5:27 PM
It’s kinda wild how much of ML is tradition. Not always in a bad way, just that there’s so damn much that you’re forced to rely on others’ recommendations for models, hyperparameters, training sets, loss metrics, architectures, and quirky practices.
Reposted by Akash Sharma
Brilliant talk by Ilya, but he's wrong on one point.
We are NOT running out of data. We are running out of human-written text.
We have more videos than we know what to do with. We just haven't solved pre-training in vision.
Just go out and sense the world. Data is easy.
December 14, 2024 at 7:15 PM
Brilliant talk by Ilya, but he's wrong on one point.
We are NOT running out of data. We are running out of human-written text.
We have more videos than we know what to do with. We just haven't solved pre-training in vision.
Just go out and sense the world. Data is easy.
This piece of hardware is exciting!
@remicadene.bsky.social is the hand able to apply sufficient per joint torques for dexterous tasks such as bottle cap opening?
@remicadene.bsky.social is the hand able to apply sufficient per joint torques for dexterous tasks such as bottle cap opening?
HOT 🔥 fastest, most precise, and most capable hand control setup ever...
Less than $450 and fully open-source 🤯
by @huggingface, @therobotstudio, @NepYope
This tendon-driven technology will disrupt robotics! Retweet to accelerate its democratization 🚀
A thread 🧵
Less than $450 and fully open-source 🤯
by @huggingface, @therobotstudio, @NepYope
This tendon-driven technology will disrupt robotics! Retweet to accelerate its democratization 🚀
A thread 🧵
December 15, 2024 at 4:44 PM
This piece of hardware is exciting!
@remicadene.bsky.social is the hand able to apply sufficient per joint torques for dexterous tasks such as bottle cap opening?
@remicadene.bsky.social is the hand able to apply sufficient per joint torques for dexterous tasks such as bottle cap opening?
My anecdote for when entropy clicked for me, was when I understood that the uniform distribution has the highest entropy, and any other distribution is more surprising than that!
Prof. Keenan's visualizations are impeccable and a gift!
Prof. Keenan's visualizations are impeccable and a gift!
Entropy is one of those formulas that many of us learn, swallow whole, and even use regularly without really understanding.
(E.g., where does that “log” come from? Are there other possible formulas?)
Yet there's an intuitive & almost inevitable way to arrive at this expression.
(E.g., where does that “log” come from? Are there other possible formulas?)
Yet there's an intuitive & almost inevitable way to arrive at this expression.
December 10, 2024 at 1:31 PM
My anecdote for when entropy clicked for me, was when I understood that the uniform distribution has the highest entropy, and any other distribution is more surprising than that!
Prof. Keenan's visualizations are impeccable and a gift!
Prof. Keenan's visualizations are impeccable and a gift!
Reposted by Akash Sharma
Excited to present new work on using diffusion priors for video amodal segmentation and content completion!
with Deva Ramanan and @tarashakhurana.bsky.social
arXiv: arxiv.org/abs/2412.04623
project page: diffusion-vas.github.io
with Deva Ramanan and @tarashakhurana.bsky.social
arXiv: arxiv.org/abs/2412.04623
project page: diffusion-vas.github.io
December 9, 2024 at 6:12 PM
Excited to present new work on using diffusion priors for video amodal segmentation and content completion!
with Deva Ramanan and @tarashakhurana.bsky.social
arXiv: arxiv.org/abs/2412.04623
project page: diffusion-vas.github.io
with Deva Ramanan and @tarashakhurana.bsky.social
arXiv: arxiv.org/abs/2412.04623
project page: diffusion-vas.github.io
Reposted by Akash Sharma
IMO VQGAN is why GANs deserve the NeurIPS test of time award. Suddenly our image representations were an order of magnitude more compact. Absolute game changer for generative modelling at scale, and the basis for latent diffusion models.
Taming Transformers for High-Resolution Image Synthesis
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias tha...
arxiv.org
November 28, 2024 at 12:09 AM
IMO VQGAN is why GANs deserve the NeurIPS test of time award. Suddenly our image representations were an order of magnitude more compact. Absolute game changer for generative modelling at scale, and the basis for latent diffusion models.
Threads banking on Insta's network has turned into baggage. Finding folks I'm interested in, like ML researchers, was incredibly easy on bsky. Starter packs, felt cringe, but were actually useful in discovering accounts.
Friction in finding people on Threads, made it very passive for me atleast
Friction in finding people on Threads, made it very passive for me atleast
November 25, 2024 at 3:58 PM
Threads banking on Insta's network has turned into baggage. Finding folks I'm interested in, like ML researchers, was incredibly easy on bsky. Starter packs, felt cringe, but were actually useful in discovering accounts.
Friction in finding people on Threads, made it very passive for me atleast
Friction in finding people on Threads, made it very passive for me atleast