Aviv Netanyahu

AI Researcher | PhD @MIT_CSAIL | formerly @WeizmannScience @HebrewU

[Aviv Netanyahu @avivnet]

Extrapolation in materials science
🗣️ Spotlight presentation at AI4Mat
🕝 Saturday, 2:42-2:54pm PT
📍 West Meeting Room 211-214

https://t.co/yDwsJTbQdE

[Nofit @NofitSegal]

Zero-shot extrapolation for out-of-distribution (OOD) chemical property prediction is an important step towards high-performance materials discovery. Check out our spotlight at the #NeurIPS AI for Accelerated Materials Design Workshop! https://t.co/wHxezk4zD7

[Aviv Netanyahu @avivnet]

I'm at #NeurIPS2024 presenting our work on:
🤖 Few-shot robot task learning via generative modeling
⚛️ Extrapolation in materials science

I’m also on the job market this year! Let’s chat about industry research opportunities, distribution shift in ML, and AI4Science. 🧵

[Aviv Netanyahu @avivnet]

Few-shot robot task learning via generative modeling
🪧 Poster #6602
🕟 Thursday, 4:30-7:30pm PT
📍 West Ballroom A-D

https://t.co/0qK0yatVfT

[Aviv Netanyahu @avivnet]

Learning new tasks with imitation learning often requires hundreds of demos. Check out our #NeurIPS paper in which we learn new tasks from few demos by inverting them into the latent space of a generative model pre-trained on a set of base tasks.

https://t.co/TKso152ziO

[Aviv Netanyahu @avivnet]

Joint work with awesome collaborators @du_yilun, @BronarsToni, @jyo_pari, Josh Tenenbaum @MITCoCoSci, @tianminshu and @pulkitology.

Drop by our poster Thu, 4:30-7:30pm PT, West Ballroom A-D #6602! https://t.co/57JihLUQdH

[Aviv Netanyahu @avivnet]

Tasks are often defined by a policy, reward, or trajectory, requiring retraining for new tasks. Inspired by few-shot visual concept learning via inverting generative models, we infer tasks represented as latent vectors without retraining.

[Aviv Netanyahu @avivnet]

We evaluate our approach extensively and demonstrate that we successfully learn novel tasks and generate corresponding agent plans and motion in (1) unseen configurations and (2) in composition with training tasks.

[Aviv Netanyahu @avivnet]

Learning new tasks with imitation learning often requires hundreds of demos. Check out our #NeurIPS paper in which we learn new tasks from few demos by inverting them into the latent space of a generative model pre-trained on a set of base tasks.

https://t.co/TKso152ziO

[Aviv Netanyahu @avivnet]

Join us tomorrow to learn more about the role of LLMs in robot social intelligence!

[Social Intelligence in Humans and Robots @SIHRworkshop]

Join us at the #RSS2024 Workshop on Social Intelligence in Humans and Robots on July 19 (1:45 - 6 pm, Netherland time). We have exciting talks covering diverse topics in robotics, AI, & cog sci. Schedule & Zoom available at: https://t.co/EqCw5gA4iG

[Aviv Netanyahu @avivnet]

Excited that this amazing project I was fortunate to be part of during my time at @WeizmannScience is now published!
Led by Shimon Ullman, Liav Assif, and Alona Strugatski, and in collaboration with Ben-Zion Vatashsky, Hila Levi, and @AdamYaari.

[Aviv Netanyahu @avivnet]

Visual scene analysis is challenging due to the complexity of objects, properties, and relations in natural scenes. Our PNAS paper https://t.co/QX2uxrXRjH proposes a goal-directed model for scene analysis that focuses on partial scene structures of interest.

[Aviv Netanyahu @avivnet]

We further show across several tasks that TD guidance is crucial for noncombinatorial and combinatorial generalization in the low and high data regimes.

[Andi Peng @TheAndiPenguin]

I'm excited to share our #ICML2023 paper: we develop a user-informed framework for eliciting feedback to diagnose and fix policy failures.

Project page: https://t.co/6vlwE3vDE6. [1/8]

[Aviv Netanyahu @avivnet]

Joint work with @abhishekunique7, Max Simchowitz, @KaiqingZhang and @pulkitology

Drop by our poster on Tue 11:30am - 1:30pm CAT!
https://t.co/FeEyAxTA2L

[Aviv Netanyahu @avivnet]

Machine learning systems often fail to make predictions on out-of-support data, even when it has significant structure. Our #ICLR23 paper proposes a method for learning predictors that extrapolate without making domain-specific assumptions.
https://t.co/iOgiF2yW7h

[Aviv Netanyahu @avivnet]

We demonstrate our method's capabilities on various regression tasks and robotics imitation learning tasks, such as action prediction for picking and placing an object at a target with a robotic arm.