Amir Globerson

25

Papers

20

Total Citations

Papers (25)

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

Optimal Tagging with Markov Chain Optimization

NeurIPS 2016arXiv

Robust Conditional Probabilities

NeurIPS 2017arXiv

TREE-G: Decision Trees Contesting Graph Neural Networks

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

Stochastic positional embeddings improve masked image modeling

Graph Neural Networks Use Graphs When They Shouldn't

DETReg: Unsupervised Pretraining With Region Priors for Object Detection

Object-Region Video Transformers

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

Learning Object Permanence from Video

Learning Canonical Representations for Scene Graph to Image Generation

Depth-Width Tradeoffs for Transformers on Graph Tasks

Teaching Models to Improve on Tape

Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction

Regularizing Towards Permutation Invariance In Recurrent Models

A Theoretical Analysis of Fine-tuning with Linear Teachers

Visual Prompting via Image Inpainting

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

How Hard is Inference for Structured Prediction?

Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs

Learning Infinite Layer Networks Without the Kernel Trick

Predict and Constrain: Modeling Cardinality in Deep Structured Prediction

Learning to Optimize Combinatorial Functions

Why do Larger Models Generalize Better? A Theoretical Perspective via the XOR Problem