Amir Globerson

research

∙ 09/08/2023

Graph Neural Networks Use Graphs When They Shouldn't

Predictions over graphs play a crucial role in various domains, includin...

0 Maya Bechler-Speicher, et al. ∙

research

∙ 07/31/2023

Predicting masked tokens in stochastic locations improves masked image modeling

Self-supervised learning is a promising paradigm in deep learning that e...

0 Amir Bar, et al. ∙

research

∙ 07/24/2023

Evaluating the Ripple Effects of Knowledge Editing in Language Models

Modern language models capture a large body of factual knowledge. Howeve...

0 Roi Cohen, et al. ∙

research

∙ 07/06/2023

Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment

Human communication often involves information gaps between the interloc...

0 Roni Rabin, et al. ∙

research

∙ 05/22/2023

LM vs LM: Detecting Factual Errors via Cross Examination

A prominent weakness of modern language models (LMs) is their tendency t...

0 Roi Cohen, et al. ∙

research

∙ 05/10/2023

Incorporating Structured Representations into Pretrained Vision Language Models Using Scene Graphs

Vision and Language (VL) models have demonstrated remarkable zero-shot p...

4 Roei Herzig, et al. ∙

research

∙ 04/28/2023

Dissecting Recall of Factual Associations in Auto-Regressive Language Models

Transformer-based language models (LMs) are known to capture factual kno...

0 Mor Geva, et al. ∙

research

∙ 01/30/2023

Crawling the Internal Knowledge-Base of Language Models

Language models are trained on large volumes of text, and as a result th...

0 Roi Cohen, et al. ∙

research

∙ 12/20/2022

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

Dual encoders are now the dominant architecture for dense retrieval. Yet...

0 Ori Ram, et al. ∙

research

∙ 12/08/2022

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

Action recognition models have achieved impressive results by incorporat...

7 Roei Herzig, et al. ∙

research

∙ 10/25/2022

Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Network

Overparameterization in deep learning typically refers to settings where...

0 Edo Cohen-Karlik, et al. ∙

research

∙ 09/01/2022

Visual Prompting via Image Inpainting

How does one adapt a pre-trained visual model to novel downstream tasks ...

10 Amir Bar, et al. ∙

research

∙ 07/06/2022

Graph Trees with Attention

When dealing with tabular data, models based on regression and decision ...

0 Maya Bechler-Speicher, et al. ∙

research

∙ 06/15/2022

Structured Video Tokens @ Ego4D PNR Temporal Localization Challenge 2022

This technical report describes the SViT approach for the Ego4D Point of...

9 Elad Ben-Avraham, et al. ∙

research

∙ 06/13/2022

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

Recent action recognition models have achieved impressive results by int...

15 Elad Ben-Avraham, et al. ∙

research

∙ 04/10/2022

Active Learning with Label Comparisons

Supervised learning typically relies on manual annotation of the true la...

0 Gal Yona, et al. ∙

research

∙ 02/09/2022

On the Implicit Bias of Gradient Descent for Temporal Extrapolation

Common practice when using recurrent neural networks (RNNs) is to apply ...

0 Edo Cohen-Karlik, et al. ∙

research

∙ 12/14/2021

Learning to Retrieve Passages without Supervision

Dense retrievers for open-domain question answering (ODQA) have been sho...

1 Ori Ram, et al. ∙

research

∙ 10/26/2021

On the Optimization Landscape of Maximum Mean Discrepancy

Generative models have been successfully used for generating realistic s...

0 Itai Alon, et al. ∙

research

∙ 10/13/2021

Object-Region Video Transformers

Evidence from cognitive psychology suggests that understanding spatio-te...

4 Roei Herzig, et al. ∙

research

∙ 07/04/2021

A Theoretical Analysis of Fine-tuning with Linear Teachers

Fine-tuning is a common practice in deep learning, achieving excellent g...

1 Gal Shachaf, et al. ∙

research

∙ 06/08/2021

DETReg: Unsupervised Pretraining with Region Priors for Object Detection

Unsupervised pretraining has recently proven beneficial for computer vis...

6 Amir Bar, et al. ∙

research

∙ 04/27/2021

Explaining in Style: Training a GAN to explain a classifier in StyleSpace

Image classification models can depend on multiple different semantic at...

12 Oran Lang, et al. ∙

research

∙ 03/09/2021

BERTese: Learning to Speak to BERT

Large pre-trained language models have been shown to encode large amount...

0 Adi Haviv, et al. ∙

research

∙ 02/19/2021

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

Recent work has highlighted the role of initialization scale in determin...

0 Shahar Azulay, et al. ∙

research

∙ 01/07/2021

Towards Understanding Learning in Neural Networks with Linear Teachers

Can a neural network minimizing cross-entropy learn linearly separable d...

16 Roei Sarussi, et al. ∙

research

∙ 01/02/2021

Few-Shot Question Answering by Pretraining Span Selection

In a number of question answering (QA) benchmarks, pretrained models hav...

0 Ori Ram, et al. ∙

research

∙ 10/25/2020

Regularizing Towards Permutation Invariance in Recurrent Models

In many machine learning problems the output should not depend on the or...

0 Edo Cohen-Karlik, et al. ∙

research

∙ 10/10/2020

Maximin Optimization for Binary Regression

We consider regression problems with binary weights. Such optimization p...

6 Nisan Chiprut, et al. ∙

research

∙ 09/30/2020

Learning Object Detection from Captions via Textual Scene Attributes

Object detection is a fundamental task in computer vision, requiring lar...

9 Achiya Jerbi, et al. ∙

research

∙ 08/11/2020

Holdout SGD: Byzantine Tolerant Federated Learning

This work presents a new distributed Byzantine tolerant federated learni...

0 Shahar Azulay, et al. ∙

research

∙ 06/27/2020

Compositional Video Synthesis with Action Graphs

Videos of actions are complex spatio-temporal signals, containing rich c...

3 Amir Bar, et al. ∙

research

∙ 03/23/2020

Learning Object Permanence from Video

Object Permanence allows people to reason about the location of non-visi...

11 Aviv Shamsian, et al. ∙

research

∙ 02/22/2020

On the Inductive Bias of a CNN for Orthogonal Patterns Distributions

Training overparameterized convolutional neural networks with gradient b...

0 Alon Brutzkus, et al. ∙

research

∙ 12/16/2019

Learning Canonical Representations for Scene Graph to Image Generation

Generating realistic images of complex visual scenes becomes very challe...

15 Roei Herzig, et al. ∙

research

∙ 02/26/2019

Learning Latent Scene-Graph Representations for Referring Relationships

Understanding the semantics of complex visual scenes often requires anal...

6 Moshiko Raboh, et al. ∙

research

∙ 02/25/2019

Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing

We introduce a novel method for multilingual transfer that utilizes deep...

0 Tal Schuster, et al. ∙

research

∙ 12/04/2018

Classifying Collisions with Spatio-Temporal Action Graph Networks

Events defined by the interaction of objects in a scene often are of cri...

0 Roei Herzig, et al. ∙

research

∙ 10/06/2018

Over-parameterization Improves Generalization in the XOR Detection Problem

Empirical evidence suggests that neural networks with ReLU activations g...

0 Alon Brutzkus, et al. ∙

research

∙ 08/14/2018

Explaining Queries over Web Tables to Non-Experts

Designing a reliable natural language (NL) interface for querying tables...

4 Jonathan Berant, et al. ∙

research

∙ 03/08/2018

Learning with Rules

Complex classifiers may exhibit "embarassing" failures in cases that wou...

0 Deborah Cohen, et al. ∙

research

∙ 02/15/2018

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Structured prediction is concerned with predicting multiple inter-depend...

0 Roei Herzig, et al. ∙

research

∙ 02/13/2018

Predict and Constrain: Modeling Cardinality in Deep Structured Prediction

Many machine learning problems require the prediction of multi-dimension...

0 Nataly Brukhim, et al. ∙

research

∙ 11/14/2017

Weakly-supervised Semantic Parsing with Abstract Examples

Semantic parsers translate language utterances to programs, but are ofte...

0 Omer Goldman, et al. ∙

research

∙ 02/26/2017

Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs

Deep learning models are often successfully trained using gradient desce...

0 Alon Brutzkus, et al. ∙

research

∙ 08/27/2016

Learning to generalize to new compositions in image understanding

Recurrent neural networks have recently been used for learning to descri...

0 Yuval Atzmon, et al. ∙

research

∙ 09/19/2014

Tight Error Bounds for Structured Prediction

Structured prediction tasks in machine learning involve the simultaneous...

0 Amir Globerson, et al. ∙

research

∙ 09/26/2013

Tighter Linear Program Relaxations for High Order Graphical Models

Graphical models with High Order Potentials (HOPs) have received conside...

0 Elad Mezuman, et al. ∙

research

∙ 09/26/2013

Learning Max-Margin Tree Predictors

Structured prediction is a powerful framework for coping with joint pred...

0 Ofer Meshi, et al. ∙

research

∙ 10/19/2012

Sufficient Dimensionality Reduction with Irrelevant Statistics

The problem of finding a reduced dimensionality representation of catego...

0 Amir Globerson, et al. ∙

Amir Globerson

Featured Co-authors