Alexei A. Efros

Affiliations

UC Berkeley

papers

6,832

total citations

papers (29)

Share with Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

ECCV 2022arXiv

citations

Video Autoencoder: Self-Supervised Disentanglement of Static 3D Structure and Motion

ICCV 2021arXiv

citations

Hallucinating Pose-Compatible Scenes

ECCV 2022arXiv

citations

Prioritized Generative Replay

ICLR 2025arXiv

citations

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting

NEURIPS 2025arXiv

citations

IT$^3$: Idempotent Test-Time Training

ICML 2025arXiv

citations

GPS as a Control Signal for Image Generation

CVPR 2025arXiv

citations

Fast Data Attribution for Text-to-Image Models

NEURIPS 2025arXiv

citations

Scraping Textures from Natural Images for Synthesis and Editing

ECCV 2022

citations

Alexei A. Efros

Affiliations

papers (29)

InstructPix2Pix: Learning To Follow Image Editing Instructions

CNN-Generated Images Are Surprisingly Easy to Spot... for Now

Dataset Distillation by Matching Training Trajectories

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions

Few-Shot Image Generation via Cross-Domain Correspondence

Continuous 3D Perception Model with Persistent State

Sequential Modeling Enables Scalable Learning for Large Vision Models

COLMAP-Free 3D Gaussian Splatting

Interpreting CLIP's Image Representation via Text-Based Decomposition

Generalizing Dataset Distillation via Deep Generative Prior

RANSAC-Flow: Generic Two-stage Image Alignment

GAN-Supervised Dense Visual Alignment

Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes

Learning to Factorize and Relight a City

Evaluating Data Attribution for Text-to-Image Models

Studying Bias in GANs through the Lens of Race

Understanding Collapse in Non-Contrastive Siamese Representation Learning

Learning Pixel Trajectories With Multiscale Contrastive Random Walks

BlobGAN: Spatially Disentangled Scene Representations

Rosetta Neurons: Mining the Common Units in a Model Zoo

Share with Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

Video Autoencoder: Self-Supervised Disentanglement of Static 3D Structure and Motion

Hallucinating Pose-Compatible Scenes

Prioritized Generative Replay

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting

IT$^3$: Idempotent Test-Time Training

GPS as a Control Signal for Image Generation

Fast Data Attribution for Text-to-Image Models

Scraping Textures from Natural Images for Synthesis and Editing

papers (29)

InstructPix2Pix: Learning To Follow Image Editing Instructions

CNN-Generated Images Are Surprisingly Easy to Spot... for Now

Dataset Distillation by Matching Training Trajectories

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions

Few-Shot Image Generation via Cross-Domain Correspondence

Continuous 3D Perception Model with Persistent State

Sequential Modeling Enables Scalable Learning for Large Vision Models

COLMAP-Free 3D Gaussian Splatting

Interpreting CLIP's Image Representation via Text-Based Decomposition

Generalizing Dataset Distillation via Deep Generative Prior

RANSAC-Flow: Generic Two-stage Image Alignment

GAN-Supervised Dense Visual Alignment

Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes

Learning to Factorize and Relight a City

Evaluating Data Attribution for Text-to-Image Models

Studying Bias in GANs through the Lens of Race

Understanding Collapse in Non-Contrastive Siamese Representation Learning

Learning Pixel Trajectories With Multiscale Contrastive Random Walks

BlobGAN: Spatially Disentangled Scene Representations

Rosetta Neurons: Mining the Common Units in a Model Zoo

Share with Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency

Video Autoencoder: Self-Supervised Disentanglement of Static 3D Structure and Motion

Hallucinating Pose-Compatible Scenes

Prioritized Generative Replay

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting

IT$^3$: Idempotent Test-Time Training

GPS as a Control Signal for Image Generation

Fast Data Attribution for Text-to-Image Models

Scraping Textures from Natural Images for Synthesis and Editing