Aviv Tamar
@aviv-tamar.bsky.social
AI and robotics researcher at Technion
avivt.github.io/avivt/
avivt.github.io/avivt/
This was a fantastic collaboration with W/
Zohar Rimon, Eli Shafer, Tal Tepper, and Efrat Shimron
Check it out, and come chat with us at #NeurIPS2025
Zohar Rimon, Eli Shafer, Tal Tepper, and Efrat Shimron
Check it out, and come chat with us at #NeurIPS2025
November 26, 2025 at 1:55 PM
This was a fantastic collaboration with W/
Zohar Rimon, Eli Shafer, Tal Tepper, and Efrat Shimron
Check it out, and come chat with us at #NeurIPS2025
Zohar Rimon, Eli Shafer, Tal Tepper, and Efrat Shimron
Check it out, and come chat with us at #NeurIPS2025
Want to learn more? Our project page has data, code, a simulator, manufacturing recipes, and all the information you need to engage
zoharri.github.io/artificial-p...
zoharri.github.io/artificial-p...
Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies
A proof of concept for artificial palpation.
zoharri.github.io
November 26, 2025 at 1:55 PM
Want to learn more? Our project page has data, code, a simulator, manufacturing recipes, and all the information you need to engage
zoharri.github.io/artificial-p...
zoharri.github.io/artificial-p...
What’s next?
Goal is a device that can visualize the internal structure of any soft object. This requires more data and more sophisticated models. Eventually, we’d like to see this work in clinical experiments - where we can use it to detect changes in a body’s shape over time.
Goal is a device that can visualize the internal structure of any soft object. This requires more data and more sophisticated models. Eventually, we’d like to see this work in clinical experiments - where we can use it to detect changes in a body’s shape over time.
November 26, 2025 at 1:55 PM
What’s next?
Goal is a device that can visualize the internal structure of any soft object. This requires more data and more sophisticated models. Eventually, we’d like to see this work in clinical experiments - where we can use it to detect changes in a body’s shape over time.
Goal is a device that can visualize the internal structure of any soft object. This requires more data and more sophisticated models. Eventually, we’d like to see this work in clinical experiments - where we can use it to detect changes in a body’s shape over time.
The result is a neural network that can process a sequence of tactile measurements and output an image of the soft object’s internal structure. Because it is learned - it can recover precise shapes that appeared in the data, like the round inclusions seen in the video.
November 26, 2025 at 1:55 PM
The result is a neural network that can process a sequence of tactile measurements and output an image of the soft object’s internal structure. Because it is learned - it can recover precise shapes that appeared in the data, like the round inclusions seen in the video.
Finally, for tactile imaging, we learn to map the representation to a GT image of the object structure. But how to obtain the GT internal structure?
We scanned our objects in an MRI!
We scanned our objects in an MRI!
November 26, 2025 at 1:55 PM
Finally, for tactile imaging, we learn to map the representation to a GT image of the object structure. But how to obtain the GT internal structure?
We scanned our objects in an MRI!
We scanned our objects in an MRI!
So, we started from the beginning - data. We manufactured modular soft objects that we can automatically palpate for hours with a robot.
Our key idea - self-supervised learning.
By predicting tactile sequence -> forces at a future position, we learn a tactile representation!
Our key idea - self-supervised learning.
By predicting tactile sequence -> forces at a future position, we learn a tactile representation!
November 26, 2025 at 1:55 PM
So, we started from the beginning - data. We manufactured modular soft objects that we can automatically palpate for hours with a robot.
Our key idea - self-supervised learning.
By predicting tactile sequence -> forces at a future position, we learn a tactile representation!
Our key idea - self-supervised learning.
By predicting tactile sequence -> forces at a future position, we learn a tactile representation!
There’s been progress with tactile-based policies, but there’s much more to tactile understanding - it’s part of our world model!
There's also progress with rigid objects, which are easy to simulate/visualize, but soft objects is still a mystery...
There's also progress with rigid objects, which are easy to simulate/visualize, but soft objects is still a mystery...
November 26, 2025 at 1:55 PM
There’s been progress with tactile-based policies, but there’s much more to tactile understanding - it’s part of our world model!
There's also progress with rigid objects, which are easy to simulate/visualize, but soft objects is still a mystery...
There's also progress with rigid objects, which are easy to simulate/visualize, but soft objects is still a mystery...
Think of the applications - artificial palpation, cooking robots, smart prosthesis, and many more domains are based on touch.
Our motivation in this work is breast tactile imaging.
But AI here is tricky - tactile data is hard to find!
Our motivation in this work is breast tactile imaging.
But AI here is tricky - tactile data is hard to find!
November 26, 2025 at 1:55 PM
Think of the applications - artificial palpation, cooking robots, smart prosthesis, and many more domains are based on touch.
Our motivation in this work is breast tactile imaging.
But AI here is tricky - tactile data is hard to find!
Our motivation in this work is breast tactile imaging.
But AI here is tricky - tactile data is hard to find!
They performed well enough to make us believe that we can seriously spend $$$ to train a model to generate images that look real.
StyleGAN was the first time "deep fakes" became a real thing.
StyleGAN was the first time "deep fakes" became a real thing.
November 28, 2024 at 1:17 PM
They performed well enough to make us believe that we can seriously spend $$$ to train a model to generate images that look real.
StyleGAN was the first time "deep fakes" became a real thing.
StyleGAN was the first time "deep fakes" became a real thing.
I could never remember the git commands beyond commit/push/pull, but I find that chatGPT is very good at helping me with it whenever I need
November 27, 2024 at 4:07 PM
I could never remember the git commands beyond commit/push/pull, but I find that chatGPT is very good at helping me with it whenever I need
Thanks. At a high level, I see search heuristics to be quite similar to value functions. In the book, we prove A* optimality by "reward shaping" Dijkstra's algorithm, which is another connection between search heuristics and values.
November 26, 2024 at 3:01 PM
Thanks. At a high level, I see search heuristics to be quite similar to value functions. In the book, we prove A* optimality by "reward shaping" Dijkstra's algorithm, which is another connection between search heuristics and values.
There's a fairly large RL Theory community.
November 26, 2024 at 1:28 PM
There's a fairly large RL Theory community.
Completely agree.
Recently I got a review (for a journal) that was from a relevant expert who also signed his name at the end (he didn't need to). Made us take the review very very seriously, even though it was negative.
Recently I got a review (for a journal) that was from a relevant expert who also signed his name at the end (he didn't need to). Made us take the review very very seriously, even though it was negative.
November 26, 2024 at 6:53 AM
Completely agree.
Recently I got a review (for a journal) that was from a relevant expert who also signed his name at the end (he didn't need to). Made us take the review very very seriously, even though it was negative.
Recently I got a review (for a journal) that was from a relevant expert who also signed his name at the end (he didn't need to). Made us take the review very very seriously, even though it was negative.
ahm ahm... we just posted this today :)
bsky.app/profile/aviv...
bsky.app/profile/aviv...
Want to learn / teach RL?
Check out new book draft:
Reinforcement Learning - Foundations sites.google.com/view/rlfound...
W/ Shie Mannor & Yishay Mansour
This is a rigorous first course in RL, based on our teaching at TAU CS and Technion ECE.
Check out new book draft:
Reinforcement Learning - Foundations sites.google.com/view/rlfound...
W/ Shie Mannor & Yishay Mansour
This is a rigorous first course in RL, based on our teaching at TAU CS and Technion ECE.
November 25, 2024 at 6:48 PM
ahm ahm... we just posted this today :)
bsky.app/profile/aviv...
bsky.app/profile/aviv...
Yes, when I teach I also have a final "hand waving" class on deep RL where I show how to go from the textbook material to DQN, PPO, Alpha Go. Adding such comments is a good idea, thanks!
November 25, 2024 at 6:44 PM
Yes, when I teach I also have a final "hand waving" class on deep RL where I show how to go from the textbook material to DQN, PPO, Alpha Go. Adding such comments is a good idea, thanks!
We don't really cover deep RL algorithms. There's a lot on Q learning, and the distance from what we cover to DQN is very small. Actually, it would be a good idea to add a remark on that, thanks!
November 25, 2024 at 3:44 PM
We don't really cover deep RL algorithms. There's a lot on Q learning, and the distance from what we cover to DQN is very small. Actually, it would be a good idea to add a remark on that, thanks!
We hope you find it useful!
The book is still work in progress - we’d be grateful for comments, suggestions, omissions, and errors of any kind, at [email protected]
The book is still work in progress - we’d be grateful for comments, suggestions, omissions, and errors of any kind, at [email protected]
November 25, 2024 at 12:08 PM
We hope you find it useful!
The book is still work in progress - we’d be grateful for comments, suggestions, omissions, and errors of any kind, at [email protected]
The book is still work in progress - we’d be grateful for comments, suggestions, omissions, and errors of any kind, at [email protected]
But for teaching RL, we wanted a book that is both rigorous (full proofs and analytical examples), covers what we feel is most relevant, and is easy enough for undergrad teaching.
The book is a focused one semester course for advanced undergrad/early grad that covers key topics in depth.
The book is a focused one semester course for advanced undergrad/early grad that covers key topics in depth.
November 25, 2024 at 12:08 PM
But for teaching RL, we wanted a book that is both rigorous (full proofs and analytical examples), covers what we feel is most relevant, and is easy enough for undergrad teaching.
The book is a focused one semester course for advanced undergrad/early grad that covers key topics in depth.
The book is a focused one semester course for advanced undergrad/early grad that covers key topics in depth.
For teachers, we also have a 40+ page exam booklet on our website.
Why this book?
There are several other excellent textbooks, including Sutton and Barto and Bertsekas and Tsitsiklis.
Why this book?
There are several other excellent textbooks, including Sutton and Barto and Bertsekas and Tsitsiklis.
November 25, 2024 at 12:08 PM
For teachers, we also have a 40+ page exam booklet on our website.
Why this book?
There are several other excellent textbooks, including Sutton and Barto and Bertsekas and Tsitsiklis.
Why this book?
There are several other excellent textbooks, including Sutton and Barto and Bertsekas and Tsitsiklis.