Deep Learning for Holistic Inference

Información del proyecto

HOLI

Identificador del acuerdo de subvención: 819080

DOI

10.3030/819080

Proyecto cerrado

Fecha de la firma de la CE 17 Enero 2019

Fecha de inicio 1 Febrero 2019

Fecha de finalización 31 Enero 2025

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 1 932 500,00

Aportación de la UE

€ 1 932 500,00

Coordinado por

TEL AVIV UNIVERSITY
Israel

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (30)

Finding Visual Task Vectors

Autores: Alberto Hojel, Yutong Bai, Trevor Darrell, Amir Globerson, Amir Bar
Publicado en: ECCV24, 2024
Editor: Springer

Provable Benefits of Complex Parameterizations for Structured State Space Models

Autores: Yuval Ran-Milo, Eden Lumbroso, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen
Publicado en: 2024
Editor: NeurIPS

Compositional Video Synthesis with Action Graphs

Autores: Bar, Amir; Herzig, Roei; Wang, Xiaolong; Chechik, Gal; Darrell, Trevor; Globerson, Amir
Publicado en: International Conference on Machine Learning (ICML, 2021), Edición 1, 2021
Editor: The International Machine Learning Society

What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary

Autores: Ori Ram, Liat Bezalel, Adi Zicher, Yonatan Belinkov, Jonathan Berant, Amir Globerson
Publicado en: 2023
Editor: n Chapter of the ACL About Calls Elections Conferences Minutes Officers Policies News RSS Feed The North American Chapter of the Association for Computational Linguistics

Regularizing Towards Permutation Invariance In Recurrent Models

Autores: Cohen, Edo; Ben David, Avichai; Globerson, Amir
Publicado en: Advanced in Neural Information Processing Systems (NeurIPS) 2020, 2020
Editor: NeurIPS

On the Inductive Bias of a CNN for Orthogonal Patterns Distributions

Autores: Brutzkus, Alon; Globerson, Amir
Publicado en: Uncertainty in Artificial Inteliigence 2021, Edición 1, 2021
Editor: UAI

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

Autores: Azulay, Shahar; Moroshko, Edward; Shpigel Nacson, Mor; Woodworth, Blake; Srebro, Nathan; Globerson, Amir; Soudry, Daniel
Publicado en: International Conference on Machine Learning 2021, 2021
Editor: ICML

Object-Region Video Transformers

Autores: Roei Herzig, Elad Ben-Avraham, Karttikeya Mangalam, Amir Bar, Gal Chechik, Anna Rohrbach, Trevor Darrell, Amir Globerson
Publicado en: 2022
Editor: Conference on Computer Vision and Pattern Recognition (CVPR), 2022
DOI: 10.48550/arxiv.2110.06915

Towards Understanding Learning in Neural Networks with Linear Teachers

Autores: Sarussi, Roy; Brutzkus, Alon; Globerson, Amir
Publicado en: International Conference on Machine Learning 2021, 2021
Editor: ICML

PromptonomyViT: Multi-Task Prompt Learning Improves Video Transformers using Synthetic Scene Data

Autores: Roei Herzig, Ofir Abramovich, Elad Ben-Avraham, Assaf Arbelle, Leonid Karlinsky, Ariel Shamir, Trevor Darrell, Amir Globerson
Publicado en: 2024
Editor: WACV

In-Context Learning Creates Task Vectors

Autores: Roee Hendel, Mor Geva, Amir Globerson
Publicado en: 2023
Editor: EMNLP

EgoPet: Egomotion and Interaction Data from an Animal's Perspective

Autores: Amir Bar, Arya Bakhtiar, Danny Tran, Antonio Loquercio, Jathushan Rajasegaran, Yann LeCun, Amir Globerson, Trevor Darrell
Publicado en: European Conference on Computer Vision (ECCV), 2024
Editor: Springer
DOI: 10.48550/arxiv.2404.09991

Stochastic positional embeddings improve masked image modeling

Autores: Amir Bar, Florian Bordes, Assaf Shocher, Mahmoud Assran, Pascal Vincent, Nicolas Ballas, Trevor Darrell, Amir Globerson, Yann LeCun
Publicado en: 2024
Editor: ICML

Learning Canonical Representations for Scene Graph to Image Generation

Autores: Herzig, Roei; Bar, Amir; Xu, Huijuan; Chechik, Gal; Darrell, Trevor; Globerson, Amir
Publicado en: European Conference on Computer Vision (ECCV, 2020), Edición 2, 2020
Editor: Springer

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

Autores: Cohen-Karlik, Edo; David, Avichai Ben; Cohen, Nadav; Globerson, Amir
Publicado en: International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
Editor: PMLR
DOI: 10.48550/arxiv.2202.04302

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States

Autores: Noam Razin, Yotam Alexander, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen
Publicado en: 2024
Editor: ICML

Efficient Learning of CNNs using Patch Based Features

Autores: Alon Brutzkus, Amir Globerson, Eran Malach, Alon Regev Netser, Shai Shalev-Schwartz Proceedings
Publicado en: 2022
Editor: of the 39th International Conference on Machine Learning, PMLR

Learning to Retrieve Passages without Supervision

Autores: Ori Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson
Publicado en: 2021
Editor: arxiv
DOI: 10.48550/arxiv.2112.07708

Bringing Image Structure to Video via Frame-Clip Consistency of Object Tokens

Autores: Elad Ben Avraham, Roei Herzig, Karttikeya Mangalam, Amir Bar, Anna Rohrbach, Leonid Karlinsky , Trevor Darrell, Amir Globerson
Publicado en: 2022
Editor: Advanced in Neural Information Processing Systems (NeurIPS)

Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs

Autores: Roei Herzig, Alon Mendelson, Leonid Karlinsky, Assaf Arbelle, Rogerio Feris, Trevor Darrell, Amir Globerson
Publicado en: 2023
Editor: EMNLP

Few-Shot question answering by pretraining span selection

Autores: Ram, Ori; Kirstain, Yuval; Berant, Jonathan; Globerson, Amir; Levy, Omer
Publicado en: Association for Computational Linguistics (ACL), 2021, 2021
Editor: ACL-IJCNLP

Differentiable Scene Graphs

Autores: Moshiko Raboh, Roei Herzig, Jonathan Berant, Gal Chechik, Amir Globerson
Publicado en: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, Página(s) 1477-1486, ISBN 978-1-7281-6553-0
Editor: IEEE
DOI: 10.1109/wacv45572.2020.9093297

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

Autores: Ido Bronstein, Alon Brutzkus, Amir Globerson
Publicado en: 2022
Editor: The Conference on Uncertainty in Artificial Intelligence (UAI)

Pre-training Mention Representations in Coreference Models

Autores: Yuval Varkel, Amir Globerson
Publicado en: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Página(s) 8534-8540
Editor: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.687

BERTese: Learning to Speak to BERT

Autores: Haviv, Adi; Berant, Jonathan; Globerson, Amir
Publicado en: European Chapter of the Association for Computational Linguistics (EACL) 2021, 2021
Editor: EACL

Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets

Autores: Edo Cohen-Karlik, Itamar Menuhin-Gruman, Raja Giryes, Nadav Cohen, Amir Globerson
Publicado en: 2023
Editor: The Eleventh International Conference on Learning Representations

Visual Prompting via Image Inpainting

Autores: Amir Bar, Yossi Gandelsman, Trevor Darrell , Amir Globerson, Alexei Efros
Publicado en: 2022
Editor: Advanced in Neural Information Processing Systems (NeurIPS)

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Autores: Bar, Amir; Wang, Xin; Kantorov, Vadim; Reed, Colorado J; Herzig, Roei; Chechik, Gal; Rohrbach, Anna; Darrell, Trevor; Globerson, Amir
Publicado en: 2022
Editor: Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Learning Object Permanence from Video

Autores: Shamsian, Aviv; Kleinfeld, Ofri; Globerson, Amir; Chechik, Gal
Publicado en: European Conference on Computer Vision (ECCV, 2020), Edición 2, 2020
Editor: Computing Research Repository (CoRR)

Teaching Models to Improve on Tape

Autores: Liat Bezalel, Eyal Orgad, Amir Globerson
Publicado en: Proceedings of the AAAI Conference on Artificial Intelligence, Edición 39, 2025, Página(s) 15550-15558, ISSN 2374-3468
Editor: Association for the Advancement of Artificial Intelligence (AAAI)
DOI: 10.1609/aaai.v39i15.33707

Other (2)

Holdout SGD: Byzantine Tolerant Federated Learning

Autores: Shahar Azulay, Lior Raz, Amir Globerson, Tomer Koren, Yehuda Afek
Publicado en: 2020
Editor: arxiv

On the Expressivity of Selective State-Space Layers:A Multivariate Polynomial Approach

Autores: Edo Cohen-Karlik, Itamar Zimerman, Liane Galanti, Ido Atad, Amir Globerson, Lior Wolf
Publicado en: 2025
Editor: arxiv
DOI: 10.48550/arxiv.2502.02209