Computer Vision Researcher.
Joined April 2022
- Tweets 44
- Following 133
- Followers 53
- Likes 243
9 Photos and videos
Pinned Tweet
29 Dec 2022
Super excited to share our work "NeRN" where we create neural representations for the weights of a specific neural network!
29 Dec 2022
Iโm very excited to share our new work titled โNeRN - Learning Neural Representations for Neural Networksโ. Preprint and code are available now๐๐งต
@ZoharRimon @ronvain @levishir667 @EladRichardson @PinkyMintz
Paper: arxiv.org/abs/2212.13554
Code: github.com/maorash/NeRN/
[1/9]
1
4
362
Ron Vainshtein retweeted
Mar 17
Animation ๐ค Robotics
ProtoMotions GTC 2026 release โ bridging the gap between digital humans and real humanoid robots.
Train in simulation. Deploy on hardware. One framework, one codebase.
nvlabs.github.io/ProtoMotionโฆ
6
35
130
8,255
Ron Vainshtein retweeted
2 Dec 2025
Just arrived at San Diego for #Neurips2025 โ๏ธ
If you're interested in
- Tactile sensing ๐ซฐ
- Uncertain decision making โ๏ธ
- Medical robotics ๐ฉบ
Reach out or come see if you process touch better than AI at our poster on Fri 16:30-19:30 #2206.
@NeurIPSConf
25 Nov 2025
Can we use tactile sensors for soft object imaging?๐ค
YES!
Toward Artificial Palpation: Representation Learning of Touch on Soft Bodies.
@shafer_eli , @talt80, @Efrat_Shimron, @AvivTamar1.
Paper, videos, data: zoharri.github.io/artificialโฆ
Check us out at @NeurIPSConf #neurips2025!
3
11
629
Ron Vainshtein retweeted
14 Apr 2025
1. Train a behavior foundation model with a rich token-based representation (eg, MaskedMimic).
2. Fine tune a state-based tokenizer using RL, leveraging the BFM for meaningful gradients.
=> Converge 6x faster, 50x less params, dramatically improved robustness.
14 Apr 2025
๐Using BFMs to learn a new task with less than 0.1% additional params while still enabling user input??๐
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
๐: arxiv.org/abs/2503.22886
๐ป: github.com/rvainshtein/task-โฆ
w/@ZoharRimon @shiemannor @ChenTessler
๐งต1/10
1
8
58
6,764
Ron Vainshtein retweeted
14 Apr 2025
Behavior models are great โ but getting them to do *exactly* what you want takes *tons* of prompt hacking (just like vision-language models) ๐ช
No more, with our new work ๐ฐ -
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
14 Apr 2025
๐Using BFMs to learn a new task with less than 0.1% additional params while still enabling user input??๐
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
๐: arxiv.org/abs/2503.22886
๐ป: github.com/rvainshtein/task-โฆ
w/@ZoharRimon @shiemannor @ChenTessler
๐งต1/10
1
1
6
312
14 Apr 2025
๐Using BFMs to learn a new task with less than 0.1% additional params while still enabling user input??๐
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
๐: arxiv.org/abs/2503.22886
๐ป: github.com/rvainshtein/task-โฆ
w/@ZoharRimon @shiemannor @ChenTessler
๐งต1/10
2
14
60
8,727
14 Apr 2025
As our base BFM we use the great work MaskedMimic by Tessler et al. x.com/ChenTessler/status/183โฆ, although our approach can be extended to other BFMs with a transformer-based architecture
9/10
22 Sep 2024
Excited to share our latest work! ๐คฉ
Masked Mimic ๐ฅท: Unified Physics-Based Character Control Through Masked Motion Inpainting
Project page: research.nvidia.com/labs/parโฆ
with: Yunrong (Kelly) Guo, @ofirnabati, @GalChechik and @xbpeng4.
@SIGGRAPHAsia (ACM TOG).
1/ Read along! ๐
1
184
14 Apr 2025
โจThe potential of Task Tokens is truly exciting! Imagine seamlessly adapting behavior models to various tasks with just a few learned params - 5 tasks using just ~1M vs standard HRL using ~125M.
This is a promising step towards more flexible and generalizable AI behavior๐
10/10
1
110
Parallels between AI and #LK99:
- Both are modern-day alchemy. Just try more recipes until eureka.
- The holy grail is simpler than we expected.
- Lots of hyperparameters to tune.
- Random seeds matter.
- Arxiv is the new battlefield.
- Scaling up is the key.
- Tend to break the internet with every update.
- Fastest growth in Twitter experts.
- Democratization: there will be GPT-4's from big corps, and Alpaca's from grassroots.
32
138
955
309,435
Ron Vainshtein retweeted
5 Jun 2023
ืืืืืืืื ืืืฉืืื ืฉื ืกืื ืืืืื ืืืื ' ืชื ืืืื.
ืื ืืืืื, ืื ืื ืืืืชื ืฉื.
ืจืืื ืืช ืืืงืืื ืืืืจืง ืืื ืืช ืื ืืืืฉืืืช ืฉืื ืคืืืก ืชืืืื.
ืื:
ืกื ืืืืื, ืื ื"ื OpenAI ืืืฉื ืฉืืืงืื ืคืืืช ืืืืจืื - ืืืืื ืกืืฆืงืืจ, ืืืืขื ืืจืืฉื ืฉื OpenAI ืฉืืื ืืฉืจืืื ืืฉืขืืจ ืฉืืื ืคื ืืืจืฅ. >>
youtube.com/watch?v=mC-0XqTAโฆ
9
4
98
25,848
Ron Vainshtein retweeted
20 Feb 2023
Nice, love the concept ๐ฆ
20 Feb 2023
Some of my early experiments with @runwayml GEN-1
Itโs still early days of AI video - this tech will only get better. A whole new generation of filmmakers is gonna be able to make whatever they want on zero budget
See below for my process
1
2
352
16 Feb 2023
Hands down the best way to handle configs in your python code.
Definitely give this a try, I'm a huge fan ๐
15 Feb 2023
"Pyrallis, a year has passed
And your library's made coding a blast
Configuring projects is now so swift
And it's all thanks to your magical gift"
- ChatGPT
Pyrallis is celebrating its first birthday with 20K installs ๐๐
Join the configvolution ๐github.com/eladrich/pyrallis
3
151
Ron Vainshtein retweeted
1 Feb 2023
Really excited to see this paper released! Great work by the authors!
Hoping to see it integrated into diffusers soon ๐คฉ @huggingface
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
abs: arxiv.org/abs/2301.13826
project page: attendandexcite.github.io/Atโฆ
github: github.com/AttendAndExcite/Aโฆ
1
3
34
13,354