Author name cluster

Raja Giryes

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.

16 papers

2 author rows

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

ICLR Conference 2025 Conference Paper

LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content

Nimrod Shabtay
Felipe Maia Polo
Sivan Doveh
Wei Lin 0019
Muhammad Jehanzeb Mirza
Leshem Choshen
Mikhail Yurochkin
Yuekai Sun

The large-scale training of multi-modal models on data scraped from the web has shown outstanding utility in infusing these models with the required world knowledge to perform effectively on multiple downstream tasks. However, one downside of scraping data from the web can be the potential sacrifice of the benchmarks on which the abilities of these models are often evaluated. To safeguard against test data contamination and to truly test the abilities of these foundation models we propose LiveXiv: A scalable evolving live benchmark based on scientific ArXiv papers. LiveXiv accesses domain-specific manuscripts at any given timestamp and proposes to automatically generate visual question-answer pairs (VQA). This is done without any human-in-the-loop, using the multi-modal content in the manuscripts, like graphs, charts, and tables. Moreover, we introduce an efficient evaluation approach that estimates the performance of all models on the evolving benchmark using evaluations of only a subset of models. This significantly reduces the overall evaluation cost. We benchmark multiple open and proprietary Large Multi-modal Models (LMMs) on the first version of our benchmark, showing its challenging nature and exposing the models’ true abilities, avoiding contamination. Lastly, in our commitment to high quality, we have collected and evaluated a manually verified subset. By comparing its overall results to our automatic annotations, we have found that the performance variance is indeed minimal (<2.5%). Our dataset is available online on HuggingFace, and our code is available here.

Details

NeurIPS Conference 2025 Conference Paper

Revisiting Glorot Initialization for Long-Range Linear Recurrences

Noga Bar
Mariia Seleznova
‪Yotam Alexander‬‏
Gitta Kutyniok
Raja Giryes

Proper initialization is critical for Recurrent Neural Networks (RNNs), particularly in long-range reasoning tasks, where repeated application of the same weight matrix can cause vanishing or exploding signals. A common baseline for linear recurrences is Glorot initialization, designed to ensure stable signal propagation---but derived under the infinite-width, fixed-length regime—an unrealistic setting for RNNs processing long sequences. In this work, we show that Glorot initialization is in fact unstable: small positive deviations in the spectral radius are amplified through time and cause the hidden state to explode. Our theoretical analysis demonstrates that sequences of length $t = O(\sqrt{n})$, where $n$ is the hidden width, are sufficient to induce instability. To address this, we propose a simple, dimension-aware rescaling of Glorot that shifts the spectral radius slightly below one, preventing rapid signal explosion or decay. These results suggest that standard initialization schemes may break down in the long-sequence regime, motivating a separate line of theory for stable recurrent initialization.

PDF Details

NeurIPS Conference 2025 Conference Paper

Smooth Regularization for Efficient Video Recognition

Gil Goldman
Raja Giryes
Mahadev Satyanarayanan

We propose a smooth regularization technique that instills a strong temporal inductive bias in video recognition models, particularly benefiting lightweight architectures. Our method encourages smoothness in the intermediate-layer embeddings of consecutive frames by modeling their changes as a Gaussian Random Walk (GRW). This penalizes abrupt representational shifts, thereby promoting low- acceleration solutions that better align with the natural temporal coherence inherent in videos. By leveraging this enforced smoothness, lightweight models can more effectively capture complex temporal dynamics. Applied to such models, our technique yields a 3. 8%–6. 4% accuracy improvement on Kinetics-600. Notably, the MoViNets model family trained with our smooth regularization improves the current state-of-the-art by 3. 8%–6. 1% within their respective FLOP constraints, while MobileNetV3 and the MoViNets-Stream family achieve gains of 4. 9%–6. 4% over prior state-of-the-art models with comparable memory footprints. Our code and models are available at https: //github. com/cmusatyalab/grw-smoothing.

PDF Details

TMLR Journal 2025 Journal Article

The Diffusion Process as a Correlation Machine: Linear Denoising Insights

Dana Weitzner
Mauricio Delbracio
Peyman Milanfar
Raja Giryes

Recently, diffusion models have gained popularity due to their impressive generative abilities. These models learn the implicit distribution given by a training dataset, and sample new data by transforming random noise through the reverse process, which can be thought of as gradual denoising. In this work, to shed more light on the evolution of denoisers in the reverse process, we examine the generation process as a ``correlation machine'', where random noise is repeatedly enhanced in correlation with the implicit given distribution. To this end, we explore the linear case, where the optimal denoiser in the MSE sense is known to be the PCA projection. This enables us to connect the theory of diffusion models to the spiked covariance model, where the dependence of the denoiser on the noise level and the amount of training data can be expressed analytically, in the rank-1 case. In a series of numerical experiments, we extend this result to general low rank data, and show that low frequencies emerge earlier in the generation process, where the denoising basis vectors are more aligned to the true data with a rate depending on their eigenvalues. This model allows us to show that the linear reverse process is a generalization of the prevalent power iteration method, where the generated distribution is composed of several estimations of the given covariance, in varying stages of convergence. Finally, we empirically demonstrate the applicability of our findings beyond the linear case, in the Jacobians of a deep, non-linear denoiser, used in general image generation tasks.

PDF Details

ICML Conference 2024 Conference Paper

How do Transformers Perform In-Context Autoregressive Learning?

Michael Eli Sander
Raja Giryes
Taiji Suzuki
Mathieu Blondel
Gabriel Peyré

Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a better understanding, we train a Transformer model on a simple next token prediction task, where sequences are generated as a first-order autoregressive process $s_{t+1} = W s_t$. We show how a trained Transformer predicts the next token by first learning $W$ in-context, then applying a prediction mapping. We call the resulting procedure in-context autoregressive learning. More precisely, focusing on commuting orthogonal matrices $W$, we first show that a trained one-layer linear Transformer implements one step of gradient descent for the minimization of an inner objective function, when considering augmented tokens. When the tokens are not augmented, we characterize the global minima of a one-layer diagonal linear multi-head Transformer. Importantly, we exhibit orthogonality between heads and show that positional encoding captures trigonometric relations in the data. On the experimental side, we consider the general case of non-commuting orthogonal matrices and generalize our theoretical findings.

Details

ICML Conference 2024 Conference Paper

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

Noam Razin
Yotam Alexander
Edo Cohen-Karlik
Raja Giryes
Amir Globerson
Nadav Cohen 0001

In modern machine learning, models can often fit training data in numerous ways, some of which perform well on unseen (test) data, while others do not. Remarkably, in such cases gradient descent frequently exhibits an implicit bias that leads to excellent performance on unseen data. This implicit bias was extensively studied in supervised learning, but is far less understood in optimal control (reinforcement learning). There, learning a controller applied to a system via gradient descent is known as policy gradient, and a question of prime importance is the extent to which a learned controller extrapolates to unseen initial states. This paper theoretically studies the implicit bias of policy gradient in terms of extrapolation to unseen initial states. Focusing on the fundamental Linear Quadratic Regulator (LQR) problem, we establish that the extent of extrapolation depends on the degree of exploration induced by the system when commencing from initial states included in training. Experiments corroborate our theory, and demonstrate its conclusions on problems beyond LQR, where systems are non-linear and controllers are neural networks. We hypothesize that real-world optimal control may be greatly improved by developing methods for informed selection of initial states to train on.

Details

NeurIPS Conference 2024 Conference Paper

Provable Benefits of Complex Parameterizations for Structured State Space Models

Yuval Ran-Milo
Eden Lumbroso
Edo Cohen-Karlik
Raja Giryes
Amir Globerson
Nadav Cohen

Structured state space models (SSMs), the core engine behind prominent neural networks such as S4 and Mamba, are linear dynamical systems adhering to a specified structure, most notably diagonal. In contrast to typical neural network modules, whose parameterizations are real, SSMs often use complex parameterizations. Theoretically explaining the benefits of complex parameterizations for SSMs is an open problem. The current paper takes a step towards its resolution, by establishing formal gaps between real and complex diagonal SSMs. Firstly, we prove that while a moderate dimension suffices in order for a complex SSM to express all mappings of a real SSM, a much higher dimension is needed for a real SSM to express mappings of a complex SSM. Secondly, we prove that even if the dimension of a real SSM is high enough to express a given mapping, typically, doing so requires the parameters of the real SSM to hold exponentially large values, which cannot be learned in practice. In contrast, a complex SSM can express any given mapping with moderate parameter values. Experiments corroborate our theory, and suggest a potential extension of the theory that accounts for selectivity, a new architectural feature yielding state of the art performance.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

UDPM: Upsampling Diffusion Probabilistic Models

Shady Abu-Hussein
Raja Giryes

Denoising Diffusion Probabilistic Models (DDPM) have recently gained significant attention. DDPMs compose a Markovian process that begins in the data domain and gradually adds noise until reaching pure white noise. DDPMs generate high-quality samples from complex data distributions by defining an inverse process and training a deep neural network to learn this mapping. However, these models are inefficient because they require many diffusion steps to produce aesthetically pleasing samples. Additionally, unlike generative adversarial networks (GANs), the latent space of diffusion models is less interpretable. In this work, we propose to generalize the denoising diffusion process into an Upsampling Diffusion Probabilistic Model (UDPM). In the forward process, we reduce the latent variable dimension through downsampling, followed by the traditional noise perturbation. As a result, the reverse process gradually denoises and upsamples the latent variable to produce a sample from the data distribution. We formalize the Markovian diffusion processes of UDPM and demonstrate its generation capabilities on the popular FFHQ, AFHQv2, and CIFAR10 datasets. UDPM generates images with as few as three network evaluations, whose overall computational cost is less than a single DDPM or EDM step while achieving an FID score of 6. 86. This surpasses current state-of-the-art efficient diffusion models that use a single denoising step for sampling. Additionally, UDPM offers an interpretable and interpolable latent space, which gives it an advantage over traditional DDPMs. Our code is available online: \url{https: //github. com/shadyabh/UDPM/}

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

Sivan Doveh
Assaf Arbelle
Sivan Harary
Roei Herzig
Donghyun Kim
Paola Cascante-Bonilla
Amit Alfassy
Rameswar Panda

Vision and Language (VL) models offer an effective method for aligning representation spaces of images and text allowing for numerous applications such as cross-modal retrieval, visual and multi-hop question answering, captioning, and many more. However, the aligned image-text spaces learned by all the popular VL models are still suffering from the so-called 'object bias' - their representations behave as 'bags of nouns' mostly ignoring or downsizing the attributes, relations, and states of objects described/appearing in texts/images. Although some great attempts at fixing these `compositional reasoning' issues were proposed in the recent literature, the problem is still far from being solved. In this paper, we uncover two factors limiting the VL models' compositional reasoning performance. These two factors are properties of the paired VL dataset used for finetuning (or pre-training) the VL model: (i) the caption quality, or in other words 'image-alignment', of the texts; and (ii) the 'density' of the captions in the sense of mentioning all the details appearing on the image. We propose a fine-tuning approach for automatically treating these factors on a standard collection of paired VL data (CC3M). Applied to CLIP, we demonstrate its significant compositional reasoning performance increase of up to $\sim27$\% over the base model, up to $\sim20$\% over the strongest baseline, and by $6. 7$\% on average. Our code is provided in the Supplementary and would be released upon acceptance.

PDF Details

ICLR Conference 2023 Conference Paper

Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets

Edo Cohen-Karlik
Itamar Menuhin-Gruman
Raja Giryes
Nadav Cohen 0001
Amir Globerson

Overparameterization in deep learning refers to settings where a trained Neural Network (NN) has representational capacity to fit the training data in many ways, some of which generalize well, while others do not. In the case of Recurrent Neural Networks (RNNs) there exists an additional layer of overparameterization, in the sense that a model may exhibit many solutions that generalize well for sequence lengths seen in training, some of which \emph{extrapolate} to longer sequences, while others do not. Numerous works studied the tendency of Gradient Descent (GD) to fit overparameterized NNs with solutions that generalize well. On the other hand, its tendency to fit overparameterized RNNs with solutions that extrapolate has been discovered only lately, and is far less understood. In this paper, we analyze the extrapolation properties of GD when applied to overparameterized linear RNNs. In contrast to recent arguments suggesting an implicit bias towards short-term memory, we provide theoretical evidence for learning low dimensional state spaces, which can also model long-term memory. Our result relies on a dynamical characterization showing that GD (with small step size and near zero initialization) strives to maintain a certain form of balancedness, as well as tools developed in the context of the \emph{moment problem} from statistics (recovery of discrete probability distribution from its moments). Experiments corroborate our theory, demonstrating extrapolation via learning low dimensional state spaces with both linear and non-linear RNNs.

Details

NeurIPS Conference 2023 Conference Paper

Neural (Tangent Kernel) Collapse

Mariia Seleznova
Dana Weitzner
Raja Giryes
Gitta Kutyniok
Hung-Hsu Chou

This work bridges two important concepts: the Neural Tangent Kernel (NTK), which captures the evolution of deep neural networks (DNNs) during training, and the Neural Collapse (NC) phenomenon, which refers to the emergence of symmetry and structure in the last-layer features of well-trained classification DNNs. We adopt the natural assumption that the empirical NTK develops a block structure aligned with the class labels, i. e. , samples within the same class have stronger correlations than samples from different classes. Under this assumption, we derive the dynamics of DNNs trained with mean squared (MSE) loss and break them into interpretable phases. Moreover, we identify an invariant that captures the essence of the dynamics, and use it to prove the emergence of NC in DNNs with block-structured NTK. We provide large-scale numerical experiments on three common DNN architectures and three benchmark datasets to support our theory.

PDF Details

NeurIPS Conference 2021 Conference Paper

SAPE: Spatially-Adaptive Progressive Encoding for Neural Optimization

Amir Hertz
Or Perel
Raja Giryes
Olga Sorkine-hornung
Daniel Cohen-or

Multilayer-perceptrons (MLP) are known to struggle learning functions of high-frequencies, and in particular, instances of wide frequency bands. We present a progressive mapping scheme for input signals of MLP networks, enabling them to better fit a wide range of frequencies without sacrificing training stability or requiring any domain specific preprocessing. We introduce Spatially Adaptive Progressive Encoding (SAPE) layers, which gradually unmask signal components with increasing frequencies as a function of time and space. The progressive exposure of frequencies is monitored by a feedback loop throughout the neural optimization process, allowing changes to propagate at different rates among local spatial portions of the signal space. We demonstrate the advantage of our method on variety of domains and applications: regression of low dimensional signals and images, representation learning of occupancy networks, and a geometric task of mesh transfer between 3D shapes.

PDF Details

AAAI Conference 2021 Conference Paper

StarNet: towards Weakly Supervised Few-Shot Object Detection

Leonid Karlinsky
Joseph Shtok
Amit Alfassy
Moshe Lichtenstein
Sivan Harary
Eli Schwartz
Sivan Doveh
Prasanna Sattigeri

Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches rarely provide localization of objects in the scene. In this paper, we introduce StarNet - a few-shot model featuring an end-to-end differentiable non-parametric star-model detection and classification head. Through this head, the backbone is meta-trained using only image-level labels to produce good features for jointly localizing and classifying previously unseen categories of few-shot test tasks using a star-model that geometrically matches between the query and support images (to find corresponding object instances). Being a few-shot detector, StarNet does not require any bounding box annotations, neither during pre-training, nor for novel classes adaptation. It can thus be applied to the previously unexplored and challenging task of Weakly Supervised Few-Shot Object Detection (WS-FSOD), where it attains significant improvements over the baselines. In addition, StarNet shows significant gains on few-shot classification benchmarks that are less cropped around the objects (where object localization is key).

PDF Details

AAAI Conference 2020 Conference Paper

Image-Adaptive GAN Based Reconstruction

Shady Abu Hussein
Tom Tirer
Raja Giryes

In the recent years, there has been a signiﬁcant improvement in the quality of samples produced by (deep) generative models such as variational auto-encoders and generative adversarial networks. However, the representation capabilities of these methods still do not capture the full distribution for complex classes of images, such as human faces. This deﬁciency has been clearly observed in previous works that use pre-trained generative models to solve imaging inverse problems. In this paper, we suggest to mitigate the limited representation capabilities of generators by making them image-adaptive and enforcing compliance of the restoration with the observations via back-projections. We empirically demonstrate the advantages of our proposed approach for image super-resolution and compressed sensing.

PDF Details

NeurIPS Conference 2018 Conference Paper

Delta-encoder: an effective sample synthesis method for few-shot object recognition

Eli Schwartz
Leonid Karlinsky
Joseph Shtok
Sivan Harary
Mattias Marder
Abhishek Kumar
Rogerio Feris
Raja Giryes

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we propose a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or "deltas", between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves the state-of-the-art of one-shot object-recognition and performs comparably in the few-shot case.

PDF Details