Lior Wolf

Safeguarding Language Models via Self-Destruct Trapdoor EACL 2026 Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models WACV 2026 AlignTree: Efficient Defense Against LLM Jailbreak Attacks AAAI 2026 TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors ACL 2026 Mitigating Copy Bias in In-Context Learning through Neuron Pruning EACL 2026 Faithful Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance ACL 2026 VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models ICML 2025 SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception CVPR 2025 Adapting to the Unknown: Training-Free Audio-Visual Event Perception with Dynamic Thresholds CVPR 2025 Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models ICLR 2025 The Hidden Attention of Mamba Models ACL 2025 Segment-Based Attention Masking for GPTs ACL 2025 Reversed Attention: On The Gradient Descent Of Attention Layers In GPT NAACL 2025 DeciMamba: Exploring the Length Extrapolation Potential of Mamba ICLR 2025 Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation ICLR 2025 Multi-Dimensional Hyena for Spatial Inductive Bias AISTATS 2024 Revisiting the Noise Model of Stochastic Gradient Descent AISTATS 2024 Video Polyp Segmentation using Implicit Networks MIDL 2024 Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation ICLR 2024 Anomaly Detection with Variance Stabilized Density Estimation UAI 2024 Zero-Shot Medical Image Segmentation Based on Sparse Prompt Using Finetuned SAM MIDL 2024 A Foundation Model for Error Correction Codes ICLR 2024 Dynamic Layer Tying for Parameter-Efficient Transformers ICLR 2024 Learning Linear Block Error Correction Codes ICML 2024 Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption ICML 2024 Viewing Transformers Through the Lens of Long Convolutions Layers ICML 2024 Knowledge Editing in Language Models via Adapted Direct Preference Optimization EMNLP 2024 LLM Questionnaire Completion for Automatic Psychiatric Assessment EMNLP 2024 Backward Lens: Projecting Language Model Gradients into the Vocabulary Space EMNLP 2024 PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation EACL 2024 Deep Quantum Error Correction AAAI 2024 Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation AAAI 2024 A 2-Dimensional State Space Layer for Spatial Inductive Bias ICLR 2024 The Hidden Language of Diffusion Models ICLR 2024 Cross-Domain Relation Adaptation ACML 2023 Degree-based stratification of nodes in Graph Neural Networks ACML 2023 Semi-supervised learning of partial differential operators and dynamical flows UAI 2023 Pre-Training Transformers for Fingerprinting to Improve Stress Prediction in fMRI MIDL 2023 Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding CVPR 2023 Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation INTERSPEECH 2023 Focus Your Attention (with Adaptive IIR Filters) EMNLP 2023 Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks ICCV 2023 Discriminative Class Tokens for Text-to-Image Diffusion Models ICCV 2023 OCD: Learning to Overfit with Conditional Diffusion Models ICML 2023 Decision S4: Efficient Sequence-Based RL via State Spaces Layers ICLR 2023 Denoising Diffusion Error Correction Codes ICLR 2023 Self-Supervised Transformers for fMRI representation MIDL 2022 XAI for Transformers: Better Explanations through Conservative Propagation ICML 2022 What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs NIPS 2022 Optimizing Relevance Maps of Vision Transformers Improves Robustness NIPS 2022 Neural Inverse Kinematic ICML 2022 Anomaly Detection for Tabular Data with Internal Contrastive Learning ICLR 2022 Explainability Guided COVID-19 Detection in CT Scans MIDL 2022 Video and Text Matching With Conditioned Embeddings WACV 2022 SepIt: Approaching a Single Channel Speech Separation Bound INTERSPEECH 2022 Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models INTERSPEECH 2022 No Token Left Behind: Explainability-Aided Image Classification and Generation ECCV 2022 Image-Based CLIP-Guided Essence Transfer ECCV 2022 Describing Sets of Images with Textual-PCA EMNLP 2022 ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic CVPR 2022 Geometric Transformer for End-to-End Molecule Properties Prediction IJCAI 2022 Error Correction Code Transformer NIPS 2022 Dynamic Dual-Output Diffusion Models CVPR 2022 Image Animation With Perturbed Masks CVPR 2022 Weakly Supervised Discovery of Semantic Attributes CLEAR 2022 Unsupervised Disentanglement with Tensor Product Representations on the Torus ICLR 2022 Many-Speakers Single Channel Speech Separation with Optimal Permutation Training INTERSPEECH 2021 Caption Enriched Samples for Improving Hateful Memes Detection EMNLP 2021 HyperHyperNetwork for the Design of Antenna Arrays ICML 2021 Computational Visual Ceramicology: Matching Image Outlines to Catalog Sketches AAAI 2021 MTAdam: Automatic Balancing of Multiple Training Loss Terms EMNLP 2021 Meta Internal Learning NIPS 2021 Fidelity-based Deep Adiabatic Scheduling ICLR 2021 Shuffling Recurrent Neural Networks AAAI 2021 On random kernels of residual architectures UAI 2021 HyperSeg: Patch-Wise Hypernetwork for Real-Time Semantic Segmentation CVPR 2021 Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models EACL 2021 Sample Selection for Universal Domain Adaptation AAAI 2021 Single-Shot Freestyle Dance Reenactment CVPR 2021 Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs JMLR 2021 Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization AAAI 2021 Scale-Localized Abstract Reasoning CVPR 2021 A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection ICCV 2021 Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification CVPR 2021 Transformer Interpretability Beyond Attention Visualization CVPR 2021 Generic Attention-Model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers ICCV 2021 Recovering AES Keys with a Deep Cold Boot Attack ICML 2021 Wish You Were Here: Context-Aware Human Generation CVPR 2020 Masked Based Unsupervised Content Transfer ICLR 2020 Vid2Game: Controllable Characters Extracted from Real-World Videos ICLR 2020 OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering ECCV 2020 Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks AAAI 2020 Unsupervised Cross-Domain Singing Voice Conversion INTERSPEECH 2020 TTS Skins: Speaker Conversion via ASR INTERSPEECH 2020 Generating Correct Answers for Progressive Matrices Intelligence Tests NIPS 2020 On the Modularity of Hypernetworks NIPS 2020 On Infinite-Width Hypernetworks NIPS 2020 Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample NIPS 2020 Voice Separation with an Unknown Number of Multiple Speakers ICML 2020 End to End Lip Synchronization with a Temporal AutoEncoder WACV 2020 End to End Trainable Active Contours via Differentiable Rendering ICLR 2020 Supervised and Unsupervised Learning of Parameterized Color Enhancement WACV 2020 ScopeFlow: Dynamic Scene Scoping for Optical Flow CVPR 2020 A Universal Music Translation Network ICLR 2019 Hyper-Graph-Network Decoders for Block Codes NIPS 2019 End-To-End Supervised Product Quantization for Image Search and Retrieval CVPR 2019 Single Image Depth Estimation Trained via Depth From Defocus Cues CVPR 2019 Bidirectional One-Shot Unsupervised Domain Mapping ICCV 2019 Deep Meta Functionals for Shape Representation ICCV 2019 Domain Intersection and Domain Difference ICCV 2019 Specifying Object Attributes and Relations in Interactive Scene Generation ICCV 2019 Live Face De-Identification in Video ICCV 2019 Unsupervised Microvascular Image Segmentation Using an Active Contours Mimicking Neural Network ICCV 2019 Unsupervised Learning of the Set of Local Maxima ICLR 2019 Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer ICLR 2019 Unsupervised Singing Voice Conversion INTERSPEECH 2019 Fitting New Speakers Based on a Short Untranscribed Sample ICML 2018 VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop ICLR 2018 The Role of Minimal Complexity Functions in Unsupervised Learning of Semantic Mappings ICLR 2018 Identifying Analogies Across Domains ICLR 2018 One-Shot Unsupervised Cross Domain Translation NIPS 2018 Non-Adversarial Unsupervised Word Translation EMNLP 2018 NAM: Non-Adversarial Unsupervised Domain Mapping ECCV 2018 Estimating the Success of Unsupervised Image to Image Translation ECCV 2018 Unsupervised Correlation Analysis CVPR 2018 A Two-Step Disentanglement Method CVPR 2018 Regularizing by the Variance of the Activations' Sample-Variances NIPS 2018 Automatic Program Synthesis of Long Programs with a Learned Garbage Collector NIPS 2018 Unsupervised Creation of Parameterized Avatars ICCV 2017 Using the Output Embedding to Improve Language Models EACL 2017 Temporal Tessellation: A Unified Approach for Video Analysis ICCV 2017 Learning to Align the Source Code to the Compiled Object Code ICML 2017 Optical Flow Requires Multiple Strategies (but Only One Network) CVPR 2017 Improved Stereo Matching With Constant Highway Networks and Reflective Confidence Learning CVPR 2017 Linking Image and Text With 2-Way Nets CVPR 2017 InterpoNet, a Brain Inspired Neural Network for Optical Flow Dense Interpolation CVPR 2017 One-Sided Unsupervised Domain Mapping NIPS 2017 PatchBatch: A Batch Augmented Loss for Optical Flow CVPR 2016 The Multiverse Loss for Robust Transfer Learning CVPR 2016 CNN-N-Gram for Handwriting Word Recognition CVPR 2016 Live Repetition Counting ICCV 2015 Associating Neural Word Embeddings With Deep Image Representations Using Fisher Vectors CVPR 2015 Web-Scale Training for Face Identification CVPR 2015 A Dynamic Convolutional Layer for Short Range Weather Prediction CVPR 2015 DeepFace: Closing the Gap to Human-Level Performance in Face Verification CVPR 2014 Congruency-Based Reranking CVPR 2014 Fast High Dimensional Vector Multiplication Face Recognition ICCV 2013 The SVM-Minus Similarity Score for Video Face Recognition CVPR 2013 Variational Relevance Vector Machine for Tabular Data ACML 2010 Feature Selection for Unsupervised and Supervised Inference: The Emergence of Sparsity in a Weight-Based Approach JMLR 2005 Learning over Sets using Kernel Principal Angles JMLR 2003