The HOLI Project

LOGO-ERC_negatif.jpg
LOGO-ERC_negatif.jpg

Machine learning has rapidly evolved in the last decade, significantly improving accuracy on tasks such as image classification. Much of this success can be attributed to the re-emergence of neural nets. However, learning algorithms are still far from achieving the capabilities of human cognition. In particular, humans can rapidly organize an input stream (e.g., textual or visual) into a set of entities, and understand the complex relations between those.

In this project our group aims to create a general methodology for semantic interpretation of input streams. In particular, we put emphasis on understanding of entities in input streams, building architectures for top-down inference, and a theoretical understanding of optimization and generalization in these problems.

Publications

On the Inductive Bias of Neural Networks for Learning Read-once DNFs 

Ido Bronstein, Alon Brutzkus, Amir Globerson

The Conference on Uncertainty in Artificial Intelligence (UAI) 2022.

Efficient Learning of CNNs using Patch Based Features 

Alon Brutzkus, Amir Globerson, Eran Malach, Alon Regev Netser ,Shai Shalev-Shwartz

 International Conference on Machine Learning (ICML), 2022.

Learning to Retrieve Passages without Supervision

Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson

The North American Chapter of the Association for Computational Linguistics (NAACL), 2022.

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

Edo Cohen-Karlik, Avichai Ben David, Nadav Cohen, Amir Globerson

Conference on Artificial Intelligence and Statistics (AISTATS), 2022.

Object-Region Video Transformers

Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson

Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

 

 

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Amir Bar, Xin Wang, Vadim Kantorov, Colorado J Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson

Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

Compositional Video Synthesis with Action Graphs

Amir Bar , Roei Herzig, Xiaolong Wang,Anna Rohrbach, Gal Chechik,Trevor Darrell, Amir Globerson

International Conference on Machine Learning (ICML), 2021.

 

Towards Understanding Learning in Neural Networks with Linear Teachers

Roy Sarussi, Alon Brutzkus, Amir Globerson

International Conference on Machine Learning (ICML), 2021.

 

On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent

Shahar Azulay, Edward Moroshko, Mor Shpigel Nacson, Blake Woodworth, Nathan Srebro, Amir Globerson, Daniel Soudry

International Conference on Machine Learning (ICML), 2021.

 

An Optimization and Generalization Analysis for Max-Pooling Networks

Alon Brutzkus, Amir Globerson

 Uncertainty in Artificial Intelligence (UAI) 2021

Few-Shot Question Answering by Pretraining Span Selection
Ori Ram, Yuval Kirstain, Jonathan Berant, Amir Globerson amd Omer Levy
Association for Computational Linguistics (ACL) 2021 (to appear)

 

BERTese: Learning to Speak to BERT
Adi Haviv, Jonathan Berant and Amir Globerson
European Chapter of the Association for Computational Linguistics (EACL) 2021

 

 

Differentiable scene graphs 

Moshiko Raboh, Roei Herzig, Gal Chechik, Jonathan Berant, Amir Globerson.

The IEEE Winter Conference on Applications of Computer Vision (WACV) 2020


 

Learning Canonical Representations for Scene Graph to Image Generation

Roei Herzig, Amir Bar, Huijuan Xu, Gal Chechik, Trevor Darrell, Amir Globerson.

ECCV 2020 (to appear)


 

Learning Object Permanence from Video

Aviv Shamsian, Ofri Kleinfeld, Amir Globerson, Gal Chechik.

ECCV 2020 (to appear)


 

Holdout SGD: Byzantine Tolerant Federated Learning

Shahar Azulay, Lior Raz, Amir Globerson, Tomer Koren, Yehuda Afek.

Arxiv. Submitted 2020

 

Regularizing Towards Permutation Invariance In Recurrent Models
Edo Cohen, Avichai Ben David and Amir Globerson
Advanced in Neural Information Processing Systems (NeurIPS) 2020

 

Pre-training Mention Representations in Coreference Models
Yuval Varkel and Amir Globerson
Empirical Mehtods in Natural Language Processing (EMNLP) 2020