Author name cluster

Lior Wolf

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

64 papers

2 author rows

AAAI Conference 2026 Conference Paper

AlignTree: Efficient Defense Against LLM Jailbreak Attacks

Gil Goren
Shahar Katz
Lior Wolf

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient. However, existing approaches either incur high computational costs or rely on lightweight defenses that can be easily circumvented, rendering them impractical for real-world LLM-based systems. In this work, we introduce the AlignTree defense, which enhances model alignment while maintaining minimal computational overhead. AlignTree monitors LLM activations during generation and detects misaligned behavior using an efficient random forest classifier. This classifier operates on two signals: (i) the refusal direction - a linear representation that activates on misaligned prompts, and (ii) an SVM-based signal that captures non-linear features associated with harmful content. Unlike previous methods, AlignTree does not require additional prompts or auxiliary guard models. Through extensive experiments, we demonstrate the efficiency and robustness of AlignTree across multiple LLMs and benchmarks.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models

Yoad Tewel
Rinon Gal
Dvir Samuel
Yuval Atzmon
Lior Wolf
Gal Chechik

Adding Object into images based on text instructions is a challenging task in semantic image editing, requiring a balance between preserving the original scene and seamlessly integrating the new object in a fitting location. Despite extensive efforts, existing models often struggle with this balance, particularly with finding a natural location for adding an object in complex scenes. We introduce Add-it, a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources: the scene image, the text prompt, and the generated image itself. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Without task-specific fine-tuning, Add-it achieves state-of-the-art results on both real and generated image insertion benchmarks, including our newly constructed "Additing Affordance Benchmark" for evaluating object placement plausibility, outperforming supervised methods. Human evaluations show that Add-it is preferred in over 80% of cases, and it also demonstrates improvements in various automated metrics.

Details

ICLR Conference 2025 Conference Paper

DeciMamba: Exploring the Length Extrapolation Potential of Mamba

Assaf Ben-Kish
Itamar Zimerman
Shady Abu-Hussein
Nadav Cohen 0001
Amir Globerson
Lior Wolf
Raja Giryes

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level capabilities while requiring substantially fewer computational resources. In this paper we explore the length-generalization capabilities of Mamba, which we find to be relatively limited. Through a series of visualizations and analyses we identify that the limitations arise from a restricted effective receptive field, dictated by the sequence length used during training. To address this constraint, we introduce DeciMamba, a context-extension method specifically designed for Mamba. This mechanism, built on top of a hidden filtering mechanism embedded within the S6 layer, enables the trained model to extrapolate well even without additional training. Empirical experiments over real-world long-range NLP tasks show that DeciMamba can extrapolate to context lengths that are significantly longer than the ones seen during training, while enjoying faster inference. We will release our code and models.

Details

NeurIPS Conference 2025 Conference Paper

Execution Guided Line-by-Line Code Generation

Boaz Lavon
Shahar Katz
Lior Wolf

We present a novel approach to neural code generation that incorporates real-time execution signals into the language model generation process. While large language models (LLMs) have demonstrated impressive code generation capabilities, they typically do not utilize execution feedback during inference, a critical signal that human programmers regularly leverage. Our method, Execution-Guided Classifier-Free Guidance EG-CFG, dynamically incorporates execution signals as the model generates code, providing line-by-line feedback that guides the generation process toward executable solutions. EG-CFG employs a multi-stage process: first, we conduct beam search to sample candidate program completions for each line; second, we extract execution signals by executing these candidates against test cases; and finally, we incorporate these signals into the prompt during generation. By maintaining consistent signals across tokens within the same line and refreshing signals at line boundaries, our approach provides coherent guidance while preserving syntactic structure. Moreover, the method naturally supports native parallelism at the task level in which multiple agents operate in parallel, exploring diverse reasoning paths and collectively generating a broad set of candidate solutions. Our experiments across diverse coding tasks demonstrate that EG-CFG significantly improves code generation performance compared to standard approaches, achieving state-of-the-art results across various levels of complexity, from foundational problems to challenging competitive programming and data science tasks.

PDF Details

ICLR Conference 2025 Conference Paper

Explaining Modern Gated-Linear RNNs via a Unified Implicit Attention Formulation

Itamar Zimerman
Ameen Ali
Lior Wolf

Recent advances in efficient sequence modeling have led to attention-free layers, such as Mamba, RWKV, and various gated RNNs, all featuring sub-quadratic complexity in sequence length and excellent scaling properties, enabling the construction of a new type of foundation models. In this paper, we present a unified view of these models, formulating such layers as implicit causal self-attention layers. The formulation includes most of their sub-components and is not limited to a specific part of the architecture. The framework compares the underlying mechanisms on similar grounds for different layers and provides a direct means for applying explainability methods. Our experiments show that our attention matrices and attribution method outperform an alternative and a more limited formulation that was recently proposed for Mamba. For the other architectures for which our method is the first to provide such a view, our method is effective and competitive in the relevant metrics compared to the results obtained by state-of-the-art Transformer explainability methods. Our code is publicly available.

Details

NeurIPS Conference 2025 Conference Paper

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

Ariel Shaulov
Itay Hazan
Lior Wolf
Hila Chefer

Text-to-video diffusion models are notoriously limited in their ability to model temporal aspects such as motion, physics, and dynamic interactions. Existing approaches address this limitation by retraining the model or introducing external conditioning signals to enforce temporal consistency. In this work, we explore whether a meaningful temporal representation can be extracted directly from the predictions of a pre-trained model without any additional training or auxiliary inputs. We introduce FlowMo, a novel training-free guidance method that enhances motion coherence using only the model's own predictions in each diffusion step. FlowMo first derives an appearance-debiased temporal representation by measuring the distance between latents corresponding to consecutive frames. This highlights the implicit temporal structure predicted by the model. It then estimates motion coherence by measuring the patch-wise variance across the temporal dimension, and guides the model to reduce this variance dynamically during sampling. Extensive experiments across multiple text-to-video models demonstrate that FlowMo significantly improves motion coherence without sacrificing visual quality or prompt alignment, offering an effective plug-and-play solution for enhancing the temporal fidelity of pre-trained video diffusion models.

PDF Details

NeurIPS Conference 2025 Conference Paper

Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability

Yarden Bakish
Itamar Zimerman
Hila Chefer
Lior Wolf

The development of effective explainability tools for Transformers is a crucial pursuit in deep learning research. One of the most promising approaches in this domain is Layer-wise Relevance Propagation (LRP), which propagates relevance scores backward through the network to the input space by redistributing activation values based on predefined rules. However, existing LRP-based methods for Transformer explainability entirely overlook a critical component of the Transformer architecture: its positional encoding (PE), resulting in violations of conservation, and the loss of an important and unique type of relevance, which is also associated with structural and positional features. To address this limitation, we reformulate the input space for Transformer explainability as a set of position-token pairs, rather than relying solely on the standard vocabulary space. This allows us to propose specialized theoretically-grounded LRP rules designed to propagate attributions across various positional encoding methods, including Rotary, Learned, and Absolute PE. Extensive experiments with both fine-tuned classifiers and zero-shot foundation models, such as LLaMA 3, demonstrate that our method significantly outperforms the SoTA in both vision and NLP explainability tasks. Our code is provided as a supplement.

PDF Details

ICML Conference 2025 Conference Paper

VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models

Hila Chefer
Uriel Singer
Amit Zohar
Yuval Kirstain
Adam Polyak
Yaniv Taigman
Lior Wolf
Shelly Sheynin

Despite tremendous recent progress, generative video models still struggle to capture real-world motion, dynamics, and physics. We show that this limitation arises from the conventional pixel reconstruction objective, which biases models toward appearance fidelity at the expense of motion coherence. To address this, we introduce VideoJAM, a novel framework that instills an effective motion prior to video generators, by encouraging the model to learn a joint appearance-motion representation. VideoJAM is composed of two complementary units. During training, we extend the objective to predict both the generated pixels and their corresponding motion from a single learned representation. During inference, we introduce Inner-Guidance, a mechanism that steers the generation toward coherent motion by leveraging the model’s own evolving motion prediction as a dynamic guidance signal. Notably, our framework can be applied to any video model with minimal adaptations, requiring no modifications to the training data or scaling of the model. VideoJAM achieves state-of-the-art performance in motion coherence, surpassing highly competitive proprietary models while also enhancing the perceived visual quality of the generations. These findings emphasize that appearance and motion can be complementary and, when effectively integrated, enhance both the visual quality and the coherence of video generation.

Details

ICLR Conference 2024 Conference Paper

A 2-Dimensional State Space Layer for Spatial Inductive Bias

Ethan Baron 0002
Itamar Zimerman
Lior Wolf

A central objective in computer vision is to design models with appropriate 2-D inductive bias. Desiderata for 2-D inductive bias include two-dimensional position awareness, dynamic spatial locality, and translation and permutation invariance. To address these goals, we leverage an expressive variation of the multidimensional State Space Model (SSM). Our approach introduces efficient parameterization, accelerated computation, and a suitable normalization scheme. Empirically, we observe that incorporating our layer at the beginning of each transformer block of Vision Transformers (ViT), as well as when replacing the Conv2D filters of ConvNeXT with our proposed layers significantly enhances performance for multiple backbones and across multiple datasets. The new layer is effective even with a negligible amount of additional parameters and inference time. Ablation studies and visualizations demonstrate that the layer has a strong 2-D inductive bias. For example, vision transformers equipped with our layer exhibit effective performance even without positional encoding. Our code is attached as supplementary.

Details

ICLR Conference 2024 Conference Paper

A Foundation Model for Error Correction Codes

Yoni Choukroun
Lior Wolf

In recent years, Artificial Intelligence has undergone a paradigm shift with the rise of foundation models, which are trained on large amounts of data, typically in a self-supervised way, and can then be adapted to a wide range of downstream tasks. In this work, we propose the first foundation model for Error Correction Codes. This model is trained on multiple codes and can then be applied to an unseen code. To enable this, we extend the Transformer architecture in multiple ways: (1) a code-invariant initial embedding, which is also position- and length-invariant, (2) a learned modulation of the attention maps that is conditioned on the Tanner graph, and (3) a length-invariant code-aware noise prediction module that is based on the parity-check matrix. The proposed architecture is trained on multiple short- and medium-length codes and is able to generalize to unseen codes. Its performance on these codes matches and even outperforms the state of the art, despite having a smaller capacity than the leading code-specific transformers. The suggested framework therefore demonstrates, for the first time, the benefits of learning a universal decoder rather than a neural decoder optimized for a given code.

Details

UAI Conference 2024 Conference Paper

Anomaly Detection with Variance Stabilized Density Estimation

Amit Rozner
Barak Battash
Henry Li
Lior Wolf
Ofir Lindenbaum

We propose a modified density estimation problem that is highly effective for detecting anomalies in tabular data. Our approach assumes that the density function is relatively stable (with lower variance) around normal samples. We have verified this hypothesis empirically using a wide range of real-world data. Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples. To obtain a reliable anomaly detector, we introduce a spectral ensemble of autoregressive models for learning the variance-stabilized distribution. We have conducted an extensive benchmark with 52 datasets, demonstrating that our method leads to state-of-the-art results while alleviating the need for data-specific hyperparameter tuning. Finally, we have used an ablation study to demonstrate the importance of each of the proposed components, followed by a stability analysis evaluating the robustness of our model.

Details

ICML Conference 2024 Conference Paper

Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption

Itamar Zimerman
Moran Baruch
Nir Drucker
Gilad Ezov
Omri Soceanu
Lior Wolf

Designing privacy-preserving DL solutions is a major challenge within the AI community. Homomorphic Encryption (HE) has emerged as one of the most promising approaches in this realm, enabling the decoupling of knowledge between a model owner and a data owner. Despite extensive research and application of this technology, primarily in CNNs, applying HE on transformer models has been challenging because of the difficulties in converting these models into a polynomial form. We break new ground by introducing the first polynomial transformer, providing the first demonstration of secure inference over HE with full transformers. This includes a transformer architecture tailored for HE, alongside a novel method for converting operators to their polynomial equivalent. This innovation enables us to perform secure inference on LMs and ViTs with several datasts and tasks. Our techniques yield results comparable to traditional models, bridging the performance gap with transformers of similar scale and underscoring the viability of HE for state-of-the-art applications. Finally, we assess the stability of our models and conduct a series of ablations to quantify the contribution of each model component. Our code is publicly available.

Details

AAAI Conference 2024 Conference Paper

Deep Quantum Error Correction

Yoni Choukroun
Lior Wolf

Quantum error correction codes (QECC) are a key component for realizing the potential of quantum computing. QECC, as its classical counterpart (ECC), enables the reduction of error rates, by distributing quantum logical information across redundant physical qubits, such that errors can be detected and corrected. In this work, we efficiently train novel end-to-end deep quantum error decoders. We resolve the quantum measurement collapse by augmenting syndrome decoding to predict an initial estimate of the system noise, which is then refined iteratively through a deep neural network. The logical error rates calculated over finite fields are directly optimized via a differentiable objective, enabling efficient decoding under the constraints imposed by the code. Finally, our architecture is extended to support faulty syndrome measurement, by efficient decoding of repeated syndrome sampling. The proposed method demonstrates the power of neural decoders for QECC by achieving state-of-the-art accuracy, outperforming for small distance topological codes, the existing end-to-end neural and classical decoders, which are often computationally prohibitive.

PDF Details DOI

AAAI Conference 2024 Conference Paper

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

Guy Yariv
Itai Gat
Sagie Benaim
Lior Wolf
Idan Schwartz
Yossi Adi

We consider the task of generating diverse and realistic videos guided by natural audio samples from a wide variety of semantic classes. For this task, the videos are required to be aligned both globally and temporally with the input audio: globally, the input audio is semantically associated with the entire output video, and temporally, each segment of the input audio is associated with a corresponding segment of that video. We utilize an existing text-conditioned video generation model and a pre-trained audio encoder model. The proposed method is based on a lightweight adaptor network, which learns to map the audio-based representation to the input representation expected by the text-to-video generation model. As such, it also enables video generation conditioned on text, audio, and, for the first time as far as we can ascertain, on both text and audio. We validate our method extensively on three datasets demonstrating significant semantic diversity of audio-video samples and further propose a novel evaluation metric (AV-Align) to assess the alignment of generated videos with input audio samples. AV-Align is based on the detection and comparison of energy peaks in both modalities. In comparison to recent state-of-the-art approaches, our method generates videos that are better aligned with the input sound, both with respect to content and temporal axis. We also show that videos produced by our method present higher visual quality and are more diverse. Code and samples are available at: https://pages.cs.huji.ac.il/adiyoss-lab/TempoTokens/.

PDF Details DOI

TMLR Journal 2024 Journal Article

Domain-Generalizable Multiple-Domain Clustering

Amit Rozner
Barak Battash
Lior Wolf
Ofir Lindenbaum

This work generalizes the problem of unsupervised domain generalization to the case in which no labeled samples are available (completely unsupervised). We are given unlabeled samples from multiple source domains, and we aim to learn a shared predictor that assigns examples to semantically related clusters. Evaluation is done by predicting cluster assignments in previously unseen domains. Towards this goal, we propose a two-stage training framework: (1) self-supervised pre-training for extracting domain invariant semantic features. (2) multi-head cluster prediction with pseudo labels, which rely on both the feature space and cluster head prediction, further leveraging a novel prediction-based label smoothing scheme. We demonstrate empirically that our model is more accurate than baselines that require fine-tuning using samples from the target domain or some level of supervision. Our code is available at \url{https://github.com/AmitRozner/domain-generalizable-multiple-domain-clustering}.

PDF Details

ICLR Conference 2024 Conference Paper

Dynamic Layer Tying for Parameter-Efficient Transformers

Tamir David Hay
Lior Wolf

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked whether to train each layer $i$ independently or to copy the weights of a previous layer $j<i$. This facilitates weight sharing, reduces the number of trainable parameters, and also serves as an effective regularization technique. Experimental evaluations validate that our model modestly outperforms the baseline transformer model with regard to perplexity and drastically reduces the number of trainable parameters. In particular, the memory consumption during training is up to one order of magnitude less than the conventional training method.

Details

ICML Conference 2024 Conference Paper

Learning Linear Block Error Correction Codes

Yoni Choukroun
Lior Wolf

Error correction codes are a crucial part of the physical communication layer, ensuring the reliable transfer of data over noisy channels. The design of optimal linear block codes capable of being efficiently decoded is of major concern, especially for short block lengths. While neural decoders have recently demonstrated their advantage over classical decoding techniques, the neural design of the codes remains a challenge. In this work, we propose for the first time a unified encoder-decoder training of binary linear block codes. To this end, we adapt the coding setting to support efficient and differentiable training of the code for end-to-end optimization over the order two Galois field. We also propose a novel Transformer model in which the self-attention masking is performed in a differentiable fashion for the efficient backpropagation of the code gradient. Our results show that (i) the proposed decoder outperforms existing neural decoding on conventional codes, (ii) the suggested framework generates codes that outperform the analogous conventional codes, and (iii) the codes we developed not only excel with our decoder but also show enhanced performance with traditional decoding techniques.

Details

ICLR Conference 2024 Conference Paper

Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation

Shahar Lutati
Eliya Nachmani
Lior Wolf

The problem of speech separation, also known as the cocktail party problem, refers to the task of isolating a single speech signal from a mixture of speech signals. Previous work on source separation derived an upper bound for the source separation task in the domain of human speech. This bound is derived for deterministic models. Recent advancements in generative models challenge this bound. We show how the upper bound can be generalized to the case of random generative models. Applying a diffusion model Vocoder that was pretrained to model single-speaker voices on the output of a deterministic separation model leads to state-of-the-art separation results. It is shown that this requires one to combine the output of the separation model with that of the diffusion model. In our method, a linear combination is performed, in the frequency domain, using weights that are inferred by a learned model. We show state-of-the-art results on 2, 3, 5, 10, and 20 speakers on multiple benchmarks. In particular, for two speakers, our method is able to surpass what was previously considered the upper performance bound.

Details

ICLR Conference 2024 Conference Paper

The Hidden Language of Diffusion Models

Hila Chefer
Oran Lang
Mor Geva
Volodymyr Polosukhin
Assaf Shocher
Michal Irani
Inbar Mosseri
Lior Wolf

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we present Conceptor, a novel method to interpret the internal representation of a textual concept by a diffusion model. This interpretation is obtained by decomposing the concept into a small set of human-interpretable textual elements. Applied over the state-of-the-art Stable Diffusion model, Conceptor reveals non-trivial structures in the representations of concepts. For example, we find surprising visual connections between concepts, that transcend their textual semantics. We additionally discover concepts that rely on mixtures of exemplars, biases, renowned artistic styles, or a simultaneous fusion of multiple meanings of the concept. Through a large battery of experiments, we demonstrate Conceptor's ability to provide meaningful, robust, and faithful decompositions for a wide variety of abstract, concrete, and complex textual concepts, while allowing to naturally connect each decomposition element to its corresponding visual impact on the generated images.

Details

ICML Conference 2024 Conference Paper

Viewing Transformers Through the Lens of Long Convolutions Layers

Itamar Zimerman
Lior Wolf

Despite their dominance in modern DL and, especially, NLP domains, transformer architectures exhibit sub-optimal performance on long-range tasks compared to recent layers that are specifically designed for this purpose. In this work, drawing inspiration from key attributes of longrange layers, such as state-space layers, linear RNN layers, and global convolution layers, we demonstrate that minimal modifications to the transformer architecture can significantly enhance performance on the Long Range Arena (LRA) benchmark, thus narrowing the gap with these specialized layers. We identify that two key principles for long-range tasks are (i) incorporating an inductive bias towards smoothness, and (ii) locality. As we show, integrating these ideas into the attention mechanism improves results with a negligible amount of additional computation and without any additional trainable parameters. Our theory and experiments also shed light on the reasons for the inferior performance of transformers on long-range tasks and identify critical properties that are essential for successfully capturing long-range dependencies.

Details

ICLR Conference 2023 Conference Paper

Decision S4: Efficient Sequence-Based RL via State Spaces Layers

Shmuel Bar-David
Itamar Zimerman
Eliya Nachmani
Lior Wolf

Recently, sequence learning methods have been applied to the problem of off-policy Reinforcement Learning, including the seminal work on Decision Transformers, which employs transformers for this task. Since transformers are parameter-heavy, cannot benefit from history longer than a fixed window size, and are not computed using recurrence, we set out to investigate the suitability of the S4 family of models, which are based on state-space layers and have been shown to outperform transformers, especially in modeling long-range dependencies. In this work, we present two main algorithms: (i) an off-policy training procedure that works with trajectories, while still maintaining the training efficiency of the S4 model. (ii) An on-policy training procedure that is trained in a recurrent manner, benefits from long-range dependencies, and is based on a novel stable actor-critic mechanism. Our results indicate that our method outperforms multiple variants of decision transformers, as well as the other baseline methods on most tasks, while reducing the latency, number of parameters, and training time by several orders of magnitude, making our approach more suitable for real-world RL

Details

ICLR Conference 2023 Conference Paper

Denoising Diffusion Error Correction Codes

Yoni Choukroun
Lior Wolf

Error correction code (ECC) is an integral part of the physical communication layer, ensuring reliable data transfer over noisy channels. Recently, neural decoders have demonstrated their advantage over classical decoding techniques. However, recent state-of-the-art neural decoders suffer from high complexity and lack the important iterative scheme characteristic of many legacy decoders. In this work, we propose to employ denoising diffusion models for the soft decoding of linear codes at arbitrary block lengths. Our framework models the forward channel corruption as a series of diffusion steps that can be reversed iteratively. Three contributions are made: (i) a diffusion process suitable for the decoding setting is introduced, (ii) the neural diffusion decoder is conditioned on the number of parity errors, which indicates the level of corruption at a given step, (iii) a line search procedure based on the code's syndrome obtains the optimal reverse diffusion step size. The proposed approach demonstrates the power of diffusion models for ECC and is able to achieve state-of-the-art accuracy, outperforming the other neural decoders by sizable margins, even for a single reverse diffusion step.

Details

ICML Conference 2023 Conference Paper

OCD: Learning to Overfit with Conditional Diffusion Models

Shahar Lutati
Lior Wolf

We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y. This mapping between an input sample and network weights is approximated by a denoising diffusion model. The diffusion model we employ focuses on modifying a single layer of the base model and is conditioned on the input, activations, and output of this layer. Since the diffusion model is stochastic in nature, multiple initializations generate different networks, forming an ensemble, which leads to further improvements. Our experiments demonstrate the wide applicability of the method for image classification, 3D reconstruction, tabular data, speech separation, and natural language processing.

Details

UAI Conference 2023 Conference Paper

Semi-supervised learning of partial differential operators and dynamical flows

Michael Rotman
Amit Dekel
Ran Ilan Ber
Lior Wolf
Yaron Oz

The evolution of many dynamical systems is generically governed by nonlinear partial differential equations (PDEs), whose solution, in a simulation framework, requires vast amounts of computational resources. In this work, we present a novel method that combines a hyper-network solver with a Fourier Neural Operator architecture. Our method treats time and space separately and as a result, it successfully propagates initial conditions in continuous time steps by employing the general composition properties of the partial differential operators. Following previous works, supervision is provided at a specific time point. We test our method on various time evolution PDEs, including nonlinear fluid flows in one, two, or three spatial dimensions. The results show that the new method improves the learning accuracy at the time of the supervision point, and can interpolate the solutions to any intermediate time.

Details

ICLR Conference 2022 Conference Paper

Anomaly Detection for Tabular Data with Internal Contrastive Learning

Tom Shenkar
Lior Wolf

We consider the task of finding out-of-class samples in tabular data, where little can be assumed on the structure of the data. In order to capture the structure of the samples of the single training class, we learn mappings that maximize the mutual information between each sample and the part that is masked out. The mappings are learned by employing a contrastive loss, which considers only one sample at a time. Once learned, we can score a test sample by measuring whether the learned mappings lead to a small contrastive loss using the masked parts of this sample. Our experiments show that our method leads by a sizable accuracy gap in comparison to the literature and that the same default set of hyperparameters provides state-of-the-art results across benchmarks.

Details

NeurIPS Conference 2022 Conference Paper

Error Correction Code Transformer

Yoni Choukroun
Lior Wolf

Error correction code is a major part of the physical communication layer, ensuring the reliable transfer of data over noisy channels. Recently, neural decoders were shown to outperform classical decoding techniques. However, the existing neural approaches present strong overfitting, due to the exponential training complexity, or a restrictive inductive bias, due to reliance on Belief Propagation. Recently, Transformers have become methods of choice in many applications, thanks to their ability to represent complex interactions between elements. In this work, we propose to extend for the first time the Transformer architecture to the soft decoding of linear codes at arbitrary block lengths. We encode each channel's output dimension to a high dimension for a better representation of the bits' information to be processed separately. The element-wise processing allows the analysis of channel output reliability, while the algebraic code and the interaction between the bits are inserted into the model via an adapted masked self-attention module. The proposed approach demonstrates the power and flexibility of Transformers and outperforms existing state-of-the-art neural decoders by large margins, at a fraction of their time complexity.

PDF Details

IJCAI Conference 2022 Conference Paper

Geometric Transformer for End-to-End Molecule Properties Prediction

Yoni Choukroun
Lior Wolf

Transformers have become methods of choice in many applications thanks to their ability to represent complex interactions between elements. However, extending the Transformer architecture to non-sequential data such as molecules and enabling its training on small datasets remains a challenge. In this work, we introduce a Transformer-based architecture for molecule property prediction, which is able to capture the geometry of the molecule. We modify the classical positional encoder by an initial encoding of the molecule geometry, as well as a learned gated self-attention mechanism. We further suggest an augmentation scheme for molecular data capable of avoiding the overfitting induced by the overparameterized architecture. The proposed framework outperforms the state-of-the-art methods while being based on pure machine learning solely, i. e. the method does not incorporate domain knowledge from quantum chemistry and does not use extended geometric inputs besides the pairwise atomic distances.

PDF Details DOI

ICML Conference 2022 Conference Paper

Neural Inverse Kinematic

Raphael Bensadoun
Shir Gur
Nitsan Blau
Lior Wolf

Inverse kinematic (IK) methods recover the parameters of the joints, given the desired position of selected elements in the kinematic chain. While the problem is well-defined and low-dimensional, it has to be solved rapidly, accounting for multiple possible solutions. In this work, we propose a neural IK method that employs the hierarchical structure of the problem to sequentially sample valid joint angles conditioned on the desired position and on the preceding joints along the chain. In our solution, a hypernetwork $f$ recovers the parameters of multiple primary networks {$g_1, g_2, …, g_N$, where $N$ is the number of joints}, such that each $g_i$ outputs a distribution of possible joint angles, and is conditioned on the sampled values obtained from the previous primary networks $g_j, j<i$. The hypernetwork can be trained on readily available pairs of matching joint angles and positions, without observing multiple solutions. At test time, a high-variance joint distribution is presented, by sampling sequentially from the primary networks. We demonstrate the advantage of the proposed method both in comparison to other IK methods for isolated instances of IK and with regard to following the path of the end effector in Cartesian space.

Details

NeurIPS Conference 2022 Conference Paper

Optimizing Relevance Maps of Vision Transformers Improves Robustness

Hila Chefer
Idan Schwartz
Lior Wolf

It has been observed that visual classification models often rely mostly on spurious cues such as the image background, which hurts their robustness to distribution changes. To alleviate this shortcoming, we propose to monitor the model's relevancy signal and direct the model to base its prediction on the foreground object. This is done as a finetuning step, involving relatively few samples consisting of pairs of images and their associated foreground masks. Specifically, we encourage the model's relevancy map (i) to assign lower relevance to background regions, (ii) to consider as much information as possible from the foreground, and (iii) we encourage the decisions to have high confidence. When applied to Vision Transformer (ViT) models, a marked improvement in robustness to domain-shifts is observed. Moreover, the foreground masks can be obtained automatically, from a self-supervised variant of the ViT model itself; therefore no additional supervision is required. Our code is available at: https: //github. com/hila-chefer/RobustViT.

PDF Details

ICLR Conference 2022 Conference Paper

Unsupervised Disentanglement with Tensor Product Representations on the Torus

Michael Rotman
Amit Dekel
Shir Gur
Yaron Oz
Lior Wolf

The current methods for learning representations with auto-encoders almost exclusively employ vectors as the latent representations. In this work, we propose to employ a tensor product structure for this purpose. This way, the obtained representations are naturally disentangled. In contrast to the conventional variations methods, which are targeted toward normally distributed features, the latent space in our representation is distributed uniformly over a set of unit circles. We argue that the torus structure of the latent space captures the generative factors effectively. We employ recent tools for measuring unsupervised disentanglement, and in an extensive set of experiments demonstrate the advantage of our method in terms of disentanglement, completeness, and informativeness. The code for our proposed method is available at https://github.com/rotmanmi/Unsupervised-Disentanglement-Torus.

Details

CLeaR Conference 2022 Conference Paper

Weakly Supervised Discovery of Semantic Attributes

Ameen Ali Ali
Tomer Galanti
Evgenii Zheltonozhskii
Chaim Baskin
Lior Wolf

We consider the problem of extracting semantic attributes, using only classification labels for supervision. For example, when learning to classify images of birds into species, we would like to observe the emergence of features used by zoologists to classify birds. To tackle this problem, we propose training a neural network with discrete features in the last layer, followed by two heads: a multi-layered perceptron (MLP) and a decision tree. The decision tree utilizes simple binary decision stumps, thus encouraging features to have semantic meaning. We present theoretical analysis, as well as a practical method for learning in the intersection of two hypothesis classes. Compared with various benchmarks, our results show an improved ability to extract a set of features highly correlated with a ground truth set of unseen attributes.

PDF Details

NeurIPS Conference 2022 Conference Paper

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

Tal Shaharabany
Yoad Tewel
Lior Wolf

Given an input image, and nothing else, our method returns the bounding boxes of objects in the image and phrases that describe the objects. This is achieved within an open world paradigm, in which the objects in the input image may not have been encountered during the training of the localization mechanism. Moreover, training takes place in a weakly supervised setting, where no bounding boxes are provided. To achieve this, our method combines two pre-trained networks: the CLIP image-to-text matching score and the BLIP image captioning tool. Training takes place on COCO images and their captions and is based on CLIP. Then, during inference, BLIP is used to generate a hypothesis regarding various regions of the current image. Our work generalizes weakly supervised segmentation and phrase grounding and is shown empirically to outperform the state of the art in both domains. It also shows very convincing results in the novel task of weakly-supervised open-world purely visual phrase-grounding presented in our work. For example, on the datasets used for benchmarking phrase-grounding, our method results in a very modest degradation in comparison to methods that employ human captions as an additional input.

PDF Details

ICML Conference 2022 Conference Paper

XAI for Transformers: Better Explanations through Conservative Propagation

Ameen Ali
Thomas Schnake
Oliver Eberle
Grégoire Montavon
Klaus-Robert Müller
Lior Wolf

Transformers have become an important workhorse of machine learning, with numerous applications. This necessitates the development of reliable methods for increasing their transparency. Multiple interpretability methods, often based on gradient information, have been proposed. We show that the gradient in a Transformer reflects the function only locally, and thus fails to reliably identify the contribution of input features to the prediction. We identify Attention Heads and LayerNorm as main reasons for such unreliable explanations and propose a more stable way for propagation through these layers. Our proposal, which can be seen as a proper extension of the well-established LRP method to Transformers, is shown both theoretically and empirically to overcome the deficiency of a simple gradient-based approach, and achieves state-of-the-art explanation performance on a broad range of Transformer models and datasets.

Details

AAAI Conference 2021 Conference Paper

Computational Visual Ceramicology: Matching Image Outlines to Catalog Sketches

Barak Itkin
Lior Wolf
Nachum Dershowitz

Field archeologists are called upon to identify potsherds, for which they rely on their professional experience and on reference works. We have developed a recognition method starting from images captured on site, which relies on the shape of the sherd’s fracture outline. The method sets up a new target for deep-learning, integrating information from points along inner and outer surfaces to learn about shapes. Training the classifiers required tackling multiple challenges that arose on account of our working with real-world archeological data: paucity of labeled data; extreme imbalance between instances of different categories; and the need to avoid neglecting rare classes and to take note of minute distinguishing features of some classes. The scarcity of training data was overcome by using synthetically-produced virtual potsherds and by employing multiple data-augmentation techniques. A novel form of training loss allowed us to overcome classification problems caused by under-populated classes and inhomogeneous distribution of discriminative features.

PDF Details

YNIMG Journal 2021 Journal Article

Deep learning model of fMRI connectivity predicts PTSD symptom trajectories in recent trauma survivors

Shelly Sheynin
Lior Wolf
Ziv Ben-Zion
Jony Sheynin
Shira Reznik
Jackob Nimrod Keynan
Roee Admon
Arieh Shalev

Early intervention following exposure to a traumatic life event could change the clinical path from the development of post traumatic stress disorder (PTSD) to recovery, hence the interest in early detection and underlying biological mechanisms involved in the development of post traumatic sequelae. We introduce a novel end-to-end neural network that employs resting-state and task-based functional MRI (fMRI) datasets, obtained one month after trauma exposure, to predict PTSD symptoms at one-, six- and fourteen-months after the exposure. FMRI data, as well as PTSD status and symptoms, were collected from adults at risk for PTSD development, after admission to emergency room following a traumatic event. Our computational method utilized a per-region encoder to extract brain regions embedding, which were subsequently updated by applying the algorithmic technique of pairwise attention. The affinities obtained between each pair of regions were combined to create a pairwise co-activation map used to perform multi-label classification. The results demonstrate that the novel method's performance in predicting PTSD symptoms, in a prospective manner, outperforms previous analytical techniques reported in the fMRI literature, all trained on the same dataset. We further show a high predictive ability for predicting PTSD symptom clusters and PTSD persistence. To the best of our knowledge, this is the first deep learning method applied on fMRI data with respect to prospective clinical outcomes, to predict PTSD status, severity and symptom clusters. Future work could further delineate the mechanisms that underlie such a prediction, and potentially improve single patient characterization.

Details DOI

ICLR Conference 2021 Conference Paper

Fidelity-based Deep Adiabatic Scheduling

Eli Ovits
Lior Wolf

Adiabatic quantum computation is a form of computation that acts by slowly interpolating a quantum system between an easy to prepare initial state and a final state that represents a solution to a given computational problem. The choice of the interpolation schedule is critical to the performance: if at a certain time point, the evolution is too rapid, the system has a high probability to transfer to a higher energy state, which does not represent a solution to the problem. On the other hand, an evolution that is too slow leads to a loss of computation time and increases the probability of failure due to decoherence. In this work, we train deep neural models to produce optimal schedules that are conditioned on the problem at hand. We consider two types of problem representation: the Hamiltonian form, and the Quadratic Unconstrained Binary Optimization (QUBO) form. A novel loss function that scores schedules according to their approximated success probability is introduced. We benchmark our approach on random QUBO problems, Grover search, 3-SAT, and MAX-CUT problems and show that our approach outperforms, by a sizable margin, the linear schedules as well as alternative approaches that were very recently proposed.

Details

ICML Conference 2021 Conference Paper

HyperHyperNetwork for the Design of Antenna Arrays

Shahar Lutati
Lior Wolf

We present deep learning methods for the design of arrays and single instances of small antennas. Each design instance is conditioned on a target radiation pattern and is required to conform to specific spatial dimensions and to include, as part of its metallic structure, a set of predetermined locations. The solution, in the case of a single antenna, is based on a composite neural network that combines a simulation network, a hypernetwork, and a refinement network. In the design of the antenna array, we add an additional design level and employ a hypernetwork within a hypernetwork. The learning objective is based on measuring the similarity of the obtained radiation pattern to the desired one. Our experiments demonstrate that our approach is able to design novel antennas and antenna arrays that are compliant with the design requirements, considerably better than the baseline methods. We compare the solutions obtained by our method to existing designs and demonstrate a high level of overlap. When designing the antenna array of a cellular phone, the obtained solution displays improved properties over the existing one.

Details

NeurIPS Conference 2021 Conference Paper

Meta Internal Learning

Raphael Bensadoun
Shir Gur
Tomer Galanti
Lior Wolf

Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image. Since these models are trained on a single image, they are limited in their scale and application. To overcome these issues, we propose a meta-learning approach that enables training over a collection of images, in order to model the internal statistics of the sample image more effectively. In the presented meta-learning approach, a single-image GAN model is generated given an input image, via a convolutional feedforward hypernetwork $f$. This network is trained over a dataset of images, allowing for feature sharing among different models, and for interpolation in the space of generative models. The generated single-image model contains a hierarchy of multiple generators and discriminators. It is therefore required to train the meta-learner in an adversarial manner, which requires careful design choices that we justify by a theoretical analysis. Our results show that the models obtained are as suitable as single-image GANs for many common image applications, {significantly reduce the training time per image without loss in performance}, and introduce novel capabilities, such as interpolation and feedforward modeling of novel images.

PDF Details

UAI Conference 2021 Conference Paper

On random kernels of residual architectures

Etai Littwin
Tomer Galanti
Lior Wolf

We analyze the finite corrections to the neural tangent kernel (NTK) of residual and densely connected networks, as a function of both depth and width. Surprisingly, our analysis reveals that given a fixed depth, residual networks provide the best tradeoff between the parameter complexity and the coefficient of variation (normalized variance), followed by densely connected networks and vanilla MLPs. While in networks that do not use skip connections, convergence to the NTK requires one to fix the depth, while increasing the layers’ width. Our findings show that in ResNets, convergence to the NTK may occur when depth and width simultaneously tend to infinity, provided with a proper initialization. In DenseNets, however, the convergence of the NTK to its limit as the width tends to infinity is guaranteed, at a rate that is independent of both the depth and scale of the weights. Our experiments validate the theoretical results and demonstrate the advantage of deep ResNets and DenseNets for kernel regression with random gradient features.

Details

ICML Conference 2021 Conference Paper

Recovering AES Keys with a Deep Cold Boot Attack

Itamar Zimerman
Eliya Nachmani
Lior Wolf

Cold boot attacks inspect the corrupted random access memory soon after the power has been shut down. While most of the bits have been corrupted, many bits, at random locations, have not. Since the keys in many encryption schemes are being expanded in memory into longer keys with fixed redundancies, the keys can often be restored. In this work we combine a deep error correcting code technique together with a modified SAT solver scheme in order to apply the attack to AES keys. Even though AES consists Rijndael SBOX elements, that are specifically designed to be resistant to linear and differential cryptanalysis, our method provides a novel formalization of the AES key scheduling as a computational graph, which is implemented by neural message passing network. Our results show that our methods outperform the state of the art attack methods by a very large gap.

Details

JMLR Journal 2021 Journal Article

Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs

Tomer Galanti
Sagie Benaim
Lior Wolf

The recent empirical success of unsupervised cross-domain mapping algorithms, in mapping between two domains that share common characteristics, is not well-supported by theoretical justifications. This lacuna is especially troubling, given the clear ambiguity in such mappings. We work with adversarial training methods based on integral probability metrics (IPMs) and derive a novel risk bound, which upper bounds the risk between the learned mapping $h$ and the target mapping $y$, by a sum of three terms: (i) the risk between $h$ and the most distant alternative mapping that was learned by the same cross-domain mapping algorithm, (ii) the minimal discrepancy between the target domain and the domain obtained by applying a hypothesis $h^*$ on the samples of the source domain, where $h^*$ is a hypothesis selectable by the same algorithm, and (iii) an approximation error term that decreases as the capacity of the class of discriminators increases and is empirically shown to be small. The bound is directly related to Occam's razor and encourages the selection of the minimal architecture that supports a small mapping discrepancy. The bound leads to multiple algorithmic consequences, including a method for hyperparameter selection and early stopping in cross-domain mapping. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

PDF Details

AAAI Conference 2021 Conference Paper

Sample Selection for Universal Domain Adaptation

Omri Lifshitz
Lior Wolf

This paper studies the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains. We present a scoring scheme that is effective in identifying the samples of the shared classes. The score is used to select samples in the target domain for which to apply specific losses during training; pseudo-labels for high scoring samples and confidence regularization for low scoring samples. Taken together, our method is shown to outperform, by a sizeable margin, the current state of the art on the literature benchmarks.

PDF Details

AAAI Conference 2021 Conference Paper

Shuffling Recurrent Neural Networks

Michael Rotman
Lior Wolf

We propose a novel recurrent neural network model, where the hidden state ht is obtained by permuting the vector elements of the previous hidden state ht−1 and adding the output of a learned function β (xt) of the input xt at time t. In our model, the prediction is given by a second learned function, which is applied to the hidden state s (ht). The method is easy to implement, extremely efficient, and does not suffer from vanishing nor exploding gradients. In an extensive set of experiments, the method shows competitive results, in comparison to the leading literature baselines. We share our implementation at https: //github. com/rotmanmi/SRNN.

PDF Details

AAAI Conference 2021 Conference Paper

Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization

Shir Gur
Ameen Ali
Lior Wolf

Neural network visualization techniques mark image locations by their relevancy to the network’s classification. Existing methods are effective in highlighting the regions that affect the resulting classification the most. However, as we show, these methods are limited in their ability to identify the support for alternative classifications, an effect we name the saliency bias hypothesis. In this work, we integrate two lines of research: gradient-based methods and attributionbased methods, and develop an algorithm that provides perclass explainability. The algorithm back-projects the per pixel local influence, in a manner that is guided by the local attributions, while correcting for salient features that would otherwise bias the explanation. In an extensive battery of experiments, we demonstrate the ability of our methods to classspecific visualization, and not just the predicted label. Remarkably, the method obtains state of the art results in benchmarks that are commonly applied to gradient-based methods as well as in those that are employed mostly for evaluating attribution methods. Using a new unsupervised procedure, our method is also successful in demonstrating that selfsupervised methods learn semantic information. Our code is available at: https: //github. com/shirgur/AGFVisualization.

PDF Details

ICLR Conference 2020 Conference Paper

End to End Trainable Active Contours via Differentiable Rendering

Shir Gur
Tal Shaharabany
Lior Wolf

We present an image segmentation method that iteratively evolves a polygon. At each iteration, the vertices of the polygon are displaced based on the local value of a 2D shift map that is inferred from the input image via an encoder-decoder architecture. The main training loss that is used is the difference between the polygon shape and the ground truth segmentation mask. The network employs a neural renderer to create the polygon from its vertices, making the process fully differentiable. We demonstrate that our method outperforms the state of the art segmentation networks and deep active contour solutions in a variety of benchmarks, including medical imaging and aerial images.

Details

NeurIPS Conference 2020 Conference Paper

Generating Correct Answers for Progressive Matrices Intelligence Tests

Niv Pekar
Yaniv Benny
Lior Wolf

Raven’s Progressive Matrices are multiple-choice intelligence tests, where one tries to complete the missing location in a 3x3 grid of abstract images. Previous attempts to address this test have focused solely on selecting the right answer out of the multiple choices. In this work, we focus, instead, on generating a correct answer given the grid, which is a harder task, by definition. The proposed neural model combines multiple advances in generative models, including employing multiple pathways through the same network, using the reparameterization trick along two pathways to make their encoding compatible, a selective application of variational losses, and a complex perceptual loss that is coupled with a selective backpropagation procedure. Our algorithm is able not only to generate a set of plausible answers but also to be competitive to the state of the art methods in multiple-choice tests.

PDF Details

NeurIPS Conference 2020 Conference Paper

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

Shir Gur
Sagie Benaim
Lior Wolf

We consider the task of generating diverse and novel videos from a single video sample. Recently, new hierarchical patch-GAN based approaches were proposed for generating diverse images, given only a single sample at training time. Moving to videos, these approaches fail to generate diverse samples, and often collapse into generating samples similar to the training video. We introduce a novel patch-based variational autoencoder (VAE) which allows for a much greater diversity in generation. Using this tool, a new hierarchical video generation scheme is constructed: at coarse scales, our patch-VAE is employed, ensuring samples are of high diversity. Subsequently, at finer scales, a patch-GAN renders the fine details, resulting in high quality videos. Our experiments show that the proposed method produces diverse samples in both the image domain, and the more challenging video domain. Our code and supplementary material (SM) with additional samples are available at https: //shirgur. github. io/hp-vae-gan

PDF Details

AAAI Conference 2020 Conference Paper

Interactive Scene Generation via Scene Graphs with Attributes

Oron Ashual
Lior Wolf

We introduce a simple yet expressive image generation method. On the one hand, it does not require the user to paint the masks or deﬁne a bounding box of the various objects, since the model does it by itself. On the other hand, it supports deﬁning a coarse location and size of each object. Based on this, we offer a simple, interactive GUI, that allows a layman user to generate diverse images effortlessly. From a technical perspective, we introduce a dual embedding of layout and appearance. In this scheme, the location, size, and appearance of an object can change independently of each other. This way, the model is able to generate innumerable images per scene graph, to better express the intention of the user. In comparison to previous work, we also offer better quality and higher resolution outputs. This is due to a superior architecture, which is based on a novel set of discriminators. Those discriminators better constrain the shape of the generated mask, as well as capturing the appearance encoding in a counterfactual way. Our code is publicly available at https: //www. github. com/ ashual/scene generation.

PDF Details

ICLR Conference 2020 Conference Paper

Masked Based Unsupervised Content Transfer

Ron Mokady
Sagie Benaim
Lior Wolf
Amit H. Bermano

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other. The proposed method disentangles the common and separate parts of these domains and, through the generation of a mask, focuses the attention of the underlying network to the desired augmentation alone, without wastefully reconstructing the entire target. This enables state-of-the-art quality and variety of content translation, as demonstrated through extensive quantitative and qualitative evaluation. Our method is also capable of adding the separate content of different guide images and domains as well as remove existing separate content. Furthermore, our method enables weakly-supervised semantic segmentation of the separate part of each domain, where only class labels are provided. Our code is available at https://github.com/rmokady/mbu-content-tansfer.

Details

NeurIPS Conference 2020 Conference Paper

On Infinite-Width Hypernetworks

Etai Littwin
Tomer Galanti
Lior Wolf
Greg Yang

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}. A notable application of hypernetworks in the recent literature involves learning to output functional representations. In these scenarios, the hypernetwork learns a representation corresponding to the weights of a shallow MLP, which typically encodes shape or image information. While such representations have seen considerable success in practice, they remain lacking in the theoretical guarantees in the wide regime of the standard architectures. In this work, we study wide over-parameterized hypernetworks. We show that unlike typical architectures, infinitely wide hypernetworks do not guarantee convergence to a global minima under gradient descent. We further show that convexity can be achieved by increasing the dimensionality of the hypernetwork's output, to represent wide MLPs. In the dually infinite-width regime, we identify the functional priors of these architectures by deriving their corresponding GP and NTK kernels, the latter of which we refer to as the {\em hyperkernel}. As part of this study, we make a mathematical contribution by deriving tight bounds on high order Taylor expansion terms of standard fully connected ReLU networks.

PDF Details

NeurIPS Conference 2020 Conference Paper

On the Modularity of Hypernetworks

Tomer Galanti
Lior Wolf

In the context of learning to map an input $I$ to a function $h_I: \mathcal{X}\to \mathbb{R}$, two alternative methods are compared: (i) an embedding-based method, which learns a fixed function in which $I$ is encoded as a conditioning signal $e(I)$ and the learned function takes the form $h_I(x) = q(x, e(I))$, and (ii) hypernetworks, in which the weights $\theta_I$ of the function $h_I(x) = g(x; \theta_I)$ are given by a hypernetwork $f$ as $\theta_I=f(I)$. In this paper, we define the property of modularity as the ability to effectively learn a different function for each input instance $I$. For this purpose, we adopt an expressivity perspective of this property and extend the theory of~\cite{devore} and provide a lower bound on the complexity (number of trainable parameters) of neural networks as function approximators, by eliminating the requirements for the approximation method to be robust. Our results are then used to compare the complexities of $q$ and $g$, showing that under certain conditions and when letting the functions $e$ and $f$ be as large as we wish, $g$ can be smaller than $q$ by orders of magnitude. This sheds light on the modularity of hypernetworks in comparison with the embedding-based method. Besides, we show that for a structured target function, the overall number of trainable parameters in a hypernetwork is smaller by orders of magnitude than the number of trainable parameters of a standard neural network and an embedding method.

PDF Details

AAAI Conference 2020 Conference Paper

Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks

Woo-Jeoung Nam
Shir Gur
Jaesik Choi
Lior Wolf
Seong-Whan Lee

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of ﬁelds, there is an increasing interest in understanding the complex internal mechanisms of DNNs. In this paper, we propose Relative Attributing Propagation (RAP), which decomposes the output predictions of DNNs with a new perspective of separating the relevant (positive) and irrelevant (negative) attributions according to the relative inﬂuence between the layers. The relevance of each neuron is identiﬁed with respect to its degree of contribution, separated into positive and negative, while preserving the conservation rule. Considering the relevance assigned to neurons in terms of relative priority, RAP allows each neuron to be assigned with a bi-polar importance score concerning the output: from highly relevant to highly irrelevant. Therefore, our method makes it possible to interpret DNNs with much clearer and attentive visualizations of the separated attributions than the conventional explaining methods. To verify that the attributions propagated by RAP correctly account for each meaning, we utilize the evaluation metrics: (i) Outside-inside relevance ratio, (ii) Segmentation mIOU and (iii) Region perturbation. In all experiments and metrics, we present a sizable gap in comparison to the existing literature.

PDF Details

ICLR Conference 2020 Conference Paper

Vid2Game: Controllable Characters Extracted from Real-World Videos

Oran Gafni
Lior Wolf
Yaniv Taigman

We extract a controllable model from a video of a person performing a certain activity. The model generates novel image sequences of that person, according to user-defined control signals, typically marking the displacement of the moving body. The generated video can have an arbitrary background, and effectively capture both the dynamics and appearance of the person. The method is based on two networks. The first maps a current pose, and a single-instance control signal to the next pose. The second maps the current pose, the new pose, and a given background, to an output frame. Both networks include multiple novelties that enable high-quality performance. This is demonstrated on multiple characters extracted from various videos of dancers and athletes.

Details

ICML Conference 2020 Conference Paper

Voice Separation with an Unknown Number of Multiple Speakers

Eliya Nachmani
Yossi Adi
Lior Wolf

We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.

Details

NeurIPS Conference 2019 Conference Paper

Hyper-Graph-Network Decoders for Block Codes

Eliya Nachmani
Lior Wolf

Neural decoders were shown to outperform classical message passing techniques for short BCH codes. In this work, we extend these results to much larger families of algebraic block codes, by performing message passing with graph neural networks. The parameters of the sub-network at each variable-node in the Tanner graph are obtained from a hypernetwork that receives the absolute values of the current message as input. To add stability, we employ a simplified version of the arctanh activation that is based on a high order Taylor approximation of this activation function. Our results show that for a large number of algebraic block codes, from diverse families of codes (BCH, LDPC, Polar), the decoding obtained with our method outperforms the vanilla belief propagation method as well as other learning techniques from the literature.

PDF Details

NeurIPS Conference 2018 Conference Paper

Automatic Program Synthesis of Long Programs with a Learned Garbage Collector

Amit Zohar
Lior Wolf

We consider the problem of generating automatic code given sample input-output pairs. We train a neural network to map from the current state and the outputs to the program's next statement. The neural network optimizes multiple tasks concurrently: the next operation out of a set of high level commands, the operands of the next statement, and which variables can be dropped from memory. Using our method we are able to create programs that are more than twice as long as existing state-of-the-art solutions, while improving the success rate for comparable lengths, and cutting the run-time by two orders of magnitude. Our code, including an implementation of various literature baselines, is publicly available at https: //github. com/amitz25/PCCoder

PDF Details

ICML Conference 2018 Conference Paper

Fitting New Speakers Based on a Short Untranscribed Sample

Eliya Nachmani
Adam Polyak
Yaniv Taigman
Lior Wolf

Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promise is currently largely unrealized. We present a method that is designed to capture a new speaker from a short untranscribed audio sample. This is done by employing an additional network that given an audio sample, places the speaker in the embedding space. This network is trained as part of the speech synthesis system using various consistency losses. Our results demonstrate a greatly improved performance on both the dataset speakers, and, more importantly, when fitting new voices, even from very short samples.

Details

NeurIPS Conference 2018 Conference Paper

One-Shot Unsupervised Cross Domain Translation

Sagie Benaim
Lior Wolf

Given a single image $x$ from domain $A$ and a set of images from domain $B$, our task is to generate the analogous of $x$ in $B$. We argue that this task could be a key AI capability that underlines the ability of cognitive agents to act in the world and present empirical evidence that the existing unsupervised domain translation methods fail on this task. Our method follows a two step process. First, a variational autoencoder for domain $B$ is trained. Then, given the new sample $x$, we create a variational autoencoder for domain $A$ by adapting the layers that are close to the image in order to directly fit $x$, and only indirectly adapt the other layers. Our experiments indicate that the new method does as well, when trained on one sample $x$, as the existing domain transfer methods, when these enjoy a multitude of training samples from domain $A$. Our code is made publicly available at https: //github. com/sagiebenaim/OneShotTranslation

PDF Details

NeurIPS Conference 2018 Conference Paper

Regularizing by the Variance of the Activations' Sample-Variances

Etai Littwin
Lior Wolf

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This new loss term encourages the variance of the activations to be stable and not vary from one random mini-batch to the next. As we prove, this encourages the activations to be distributed around a few distinct modes. We also show that if the inputs are from a mixture of two Gaussians, the new loss would either join the two together, or separate between them optimally in the LDA sense, depending on the prior probabilities. Finally, we are able to link the new regularization term to the batchnorm method, which provides it with a regularization perspective. Our experiments demonstrate an improvement in accuracy over the batchnorm technique for both CNNs and fully connected networks.

PDF Details

ICML Conference 2017 Conference Paper

Learning to Align the Source Code to the Compiled Object Code

Dor Levy
Lior Wolf

We propose a new neural network architecture and use it for the task of statement-by-statement alignment of source code and its compiled object code. Our architecture learns the alignment between the two sequences – one being the translation of the other – by mapping each statement to a context-dependent representation vector and aligning such vectors using a grid of the two sequence domains. Our experiments include short C functions, both artificial and human-written, and show that our neural network architecture is able to predict the alignment with high accuracy, outperforming known baselines. We also demonstrate that our model is general and can learn to solve graph problems such as the Traveling Salesman Problem.

Details

NeurIPS Conference 2017 Conference Paper

One-Sided Unsupervised Domain Mapping

Sagie Benaim
Lior Wolf

In unsupervised domain mapping, the learner is given two unmatched datasets $A$ and $B$. The goal is to learn a mapping $G_{AB}$ that translates a sample in $A$ to the analog sample in $B$. Recent approaches have shown that when learning simultaneously both $G_{AB}$ and the inverse mapping $G_{BA}$, convincing mappings are obtained. In this work, we present a method of learning $G_{AB}$ without learning $G_{BA}$. This is done by learning a mapping that maintains the distance between a pair of samples. Moreover, good mappings are obtained, even by maintaining the distance between different parts of the same sample before and after mapping. We present experimental results that the new method not only allows for one sided mapping learning, but also leads to preferable numerical results over the existing circularity-based constraint. Our entire code is made publicly available at~\url{https: //github. com/sagiebenaim/DistanceGAN}.

PDF Details

ICRA Conference 2016 Conference Paper

Softbot: Software-based lead-through for rigid servo robots

Yackov Lubarsky
Amit Wolf
Lior Wolf
Curime Batliner
Jake Newsum

In this paper, we present an interactive control method for rigid robotics. The core of the method is a neural network classifier that maps position and torque readings to a force direction in 3D space. We show that running our method online allows a human to move the robot along a desired path by performing intuitive pushes and pulls on the robot's joints. The setup is sensorless: no additional sensors, other than those already integral to the rigid joint itself, are added to the manipulator or used in the process.

Details

JMLR Journal 2005 Journal Article

Feature Selection for Unsupervised and Supervised Inference: The Emergence of Sparsity in a Weight-Based Approach

Lior Wolf
Amnon Shashua

The problem of selecting a subset of relevant features in a potentially overwhelming quantity of data is classic and found in many branches of science. Examples in computer vision, text processing and more recently bio-informatics are abundant. In text classification tasks, for example, it is not uncommon to have 10 4 to 10 7 features of the size of the vocabulary containing word frequency counts, with the expectation that only a small fraction of them are relevant. Typical examples include the automatic sorting of URLs into a web directory and the detection of spam email. In this work we present a definition of "relevancy" based on spectral properties of the Laplacian of the features' measurement matrix. The feature selection process is then based on a continuous ranking of the features defined by a least-squares optimization process. A remarkable property of the feature relevance function is that sparse solutions for the ranking values naturally emerge as a result of a "biased non-negativity" of a key matrix in the process. As a result, a simple least-squares optimization process converges onto a sparse solution, i.e., a selection of a subset of features which form a local maximum over the relevance function. The feature selection algorithm can be embedded in both unsupervised and supervised inference problems and empirical evidence show that the feature selections typically achieve high accuracy even when only a small fraction of the features are relevant. [abs] [ pdf ][ bib ] &copy JMLR 2005. ( edit, beta )

PDF Details

JMLR Journal 2003 Journal Article

Learning over Sets using Kernel Principal Angles (Kernel Machines Section)

Lior Wolf
Amnon Shashua

We consider the problem of learning with instances defined over a space of sets of vectors. We derive a new positive definite kernel f ( A, B ) defined over pairs of matrices A, B based on the concept of principal angles between two linear subspaces. We show that the principal angles can be recovered using only inner-products between pairs of column vectors of the input matrices thereby allowing the original column vectors of A, B to be mapped onto arbitrarily high-dimensional feature spaces. We demonstrate the usage of the matrix-based kernel function f ( A, B ) with experiments on two visual tasks. The first task is the discrimination of "irregular" motion trajectory of an individual or a group of individuals in a video sequence. We use the SVM approach using f ( A, B ) where an input matrix represents the motion trajectory of a group of individuals over a certain (fixed) time frame. We show that the classification (irregular versus regular) greatly outperforms the conventional representation where all the trajectories form a single vector. The second application is the visual recognition of faces from input video sequences representing head motion and facial expressions where f ( A, B ) is used to compare two image sequences. [abs] [ pdf ][ ps.gz ][ ps ]

PDF Details