Lior Wolf

66

Papers

71

Total Citations

1

Affiliations

Affiliations

Facebook AI Research and Tel Aviv University

Papers (66)

The Hidden Language of Diffusion Models

Deep Quantum Error Correction

Dynamic Layer Tying for Parameter-Efficient Transformers

FlowMo: Variance-Based Flow Guidance for Coherent Motion in Video Generation

SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception

Learning Linear Block Error Correction Codes

Web-Scale Training for Face Identification

Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vectors

A Dynamic Convolutional Layer for Short Range Weather Prediction

CNN-N-Gram for Handwriting Word Recognition

The Multiverse Loss for Robust Transfer Learning

PatchBatch: A Batch Augmented Loss for Optical Flow

Linking Image and Text With 2-Way Nets

Improved Stereo Matching With Constant Highway Networks and Reflective Confidence Learning

Optical Flow Requires Multiple Strategies (but Only One Network)

A Two-Step Disentanglement Method

Unsupervised Correlation Analysis

End-To-End Supervised Product Quantization for Image Search and Retrieval

Single Image Depth Estimation Trained via Depth From Defocus Cues

Wish You Were Here: Context-Aware Human Generation

ScopeFlow: Dynamic Scene Scoping for Optical Flow

Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification

HyperSeg: Patch-Wise Hypernetwork for Real-Time Semantic Segmentation

Transformer Interpretability Beyond Attention Visualization

Single-Shot Freestyle Dance Reenactment

Scale-Localized Abstract Reasoning

ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

Dynamic Dual-Output Diffusion Models

Image Animation With Perturbed Masks

Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding

Live Repetition Counting

Temporal Tessellation: A Unified Approach for Video Analysis

Unsupervised Creation of Parameterized Avatars

Bidirectional One-Shot Unsupervised Domain Mapping

Deep Meta Functionals for Shape Representation

Domain Intersection and Domain Difference

Specifying Object Attributes and Relations in Interactive Scene Generation

Live Face De-Identification in Video

Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network

A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

Generic Attention-Model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers

Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks

Discriminative Class Tokens for Text-to-Image Diffusion Models

OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering

No Token Left Behind: Explainability-Aided Image Classification and Generation

Image-Based CLIP-Guided Essence Transfer

One-Sided Unsupervised Domain Mapping

NeurIPS 2017arXiv

InterpoNet, a Brain Inspired Neural Network for Optical Flow Dense Interpolation

Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds

Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption

Viewing Transformers Through the Lens of Long Convolutions Layers

One-Shot Unsupervised Cross Domain Translation

Automatic Program Synthesis of Long Programs with a Learned Garbage Collector

Regularizing by the Variance of the Activations' Sample-Variances

Hyper-Graph-Network Decoders for Block Codes

Generating Correct Answers for Progressive Matrices Intelligence Tests

On the Modularity of Hypernetworks

On Infinite-Width Hypernetworks

Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample

Meta Internal Learning

What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs

Optimizing Relevance Maps of Vision Transformers Improves Robustness

Error Correction Code Transformer

Learning to Align the Source Code to the Compiled Object Code

Fitting New Speakers Based on a Short Untranscribed Sample