Pinned Tweet
🎉 Excited to share that our paper "Towards Croppable Implicit Neural Representations" has been accepted to #NeurIPS2024! 🧵
Paper: arxiv.org/abs/2409.19472
Code: github.com/maorash/Local-Glo…
Additional Results: sites.google.com/view/local-…
#NeurIPS2024 #NeurIPS
[1/8]
Maor Ashkenazi retweeted
🚀Using BFMs to learn a new task with less than 0.1% additional params while still enabling user input??🚀
Task Tokens: A Flexible Approach to Adapting Behavior Foundation Models
📄: arxiv.org/abs/2503.22886
💻: github.com/rvainshtein/task-…
w/@ZoharRimon @shiemannor @ChenTessler
🧵1/10
Excited to present my paper now at NeurIPS 2024! 🥳
Stop by the first poster session to chat about improving Implicit Neural Representations 🤩
Looking forward to sharing insights and meeting fellow AI enthusiasts!
@ East Exhibit Hall, poster 1502
#NeurIPS2024 #NeurIPS #inrs
🎉 Excited to share that our paper "Towards Croppable Implicit Neural Representations" has been accepted to #NeurIPS2024! 🧵
Paper: arxiv.org/abs/2409.19472
Code: github.com/maorash/Local-Glo…
Additional Results: sites.google.com/view/local-…
#NeurIPS2024 #NeurIPS
[1/8]
✂️After training, Local-Global SIRENs allow cropping without retraining.
Here’s an example with video - cropping both spatial and temporal dimensions
[7/8]
1
45
Maor Ashkenazi retweeted
Text-to-image models revolutionized computer vision, but what do they learn about the world?🤔
We present Conceptor 🧐 a method to inspect the inner representation of a concept by decomposing it into a set of interpretable tokens, which reveals surprising semantic structures🧵
Maor Ashkenazi retweeted
Breaking Common Sense: WHOOPS! A Vision-and-Language Benchmark of Synthetic and Compositional Images
abs: arxiv.org/abs/2303.07274
project page: whoops-benchmark.github.io/
@huggingface dataset: huggingface.co/datasets/nlph…
@gradio demo: huggingface.co/spaces/nlphuj…
Maor Ashkenazi retweeted
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
abs: arxiv.org/abs/2301.13826
project page: attendandexcite.github.io/At…
github: github.com/AttendAndExcite/A…
Delighted to share that #NeRN was accepted as a notable-top-25% (spotlight) paper to #ICLR2023 #ICLR 🥳🤩
I’m very excited to share our new work titled “NeRN - Learning Neural Representations for Neural Networks”. Preprint and code are available now😊🧵
@ZoharRimon @ronvain @levishir667 @EladRichardson @PinkyMintz
Paper: arxiv.org/abs/2212.13554
Code: github.com/maorash/NeRN/
[1/9]
I’m very excited to share our new work titled “NeRN - Learning Neural Representations for Neural Networks”. Preprint and code are available now😊🧵
@ZoharRimon @ronvain @levishir667 @EladRichardson @PinkyMintz
Paper: arxiv.org/abs/2212.13554
Code: github.com/maorash/NeRN/
[1/9]
For example, a limited capacity NeRN will most likely prioritize the weights during training. The reconstruction error can be explored to study the importance of different weights.
[8/9]
1
2
246













