Amir Globerson

papers

939

total citations

papers (17)

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

ICML 2024arXiv

citations

Teaching Models to Improve on Tape

AAAI 2025arXiv

citations

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

NEURIPS 2022arXiv

citations

Depth-Width Tradeoffs for Transformers on Graph Tasks

NEURIPS 2025

citations

Amir Globerson

papers (17)

Visual Prompting via Image Inpainting

Explaining in Style: Training a GAN To Explain a Classifier in StyleSpace

DETReg: Unsupervised Pretraining With Region Priors for Object Detection

Learning Canonical Representations for Scene Graph to Image Generation

Object-Region Video Transformers

Learning Object Permanence from Video

Graph Neural Networks Use Graphs When They Shouldn't

Regularizing Towards Permutation Invariance In Recurrent Models

A Theoretical Analysis of Fine-tuning with Linear Teachers

Finding Visual Task Vectors

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

Stochastic positional embeddings improve masked image modeling

TREE-G: Decision Trees Contesting Graph Neural Networks

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

Teaching Models to Improve on Tape

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

Depth-Width Tradeoffs for Transformers on Graph Tasks

papers (17)

Visual Prompting via Image Inpainting

Explaining in Style: Training a GAN To Explain a Classifier in StyleSpace

DETReg: Unsupervised Pretraining With Region Priors for Object Detection

Learning Canonical Representations for Scene Graph to Image Generation

Object-Region Video Transformers

Learning Object Permanence from Video

Graph Neural Networks Use Graphs When They Shouldn't

Regularizing Towards Permutation Invariance In Recurrent Models

A Theoretical Analysis of Fine-tuning with Linear Teachers

Finding Visual Task Vectors

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

Stochastic positional embeddings improve masked image modeling

TREE-G: Decision Trees Contesting Graph Neural Networks

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

Teaching Models to Improve on Tape

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

Depth-Width Tradeoffs for Transformers on Graph Tasks