arXiv subjects

Regev Cohen

Publications and source records attributed to Regev Cohen.

At least 19 recordsLinked to original sources

arXiv2026

Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis

Humans naturally communicate through abstract concepts like "mood". However, current image editing benchmarks focus primarily on explicit, literal commands, leaving abstract instructions largely underexplored. In this work, we first formalize the definition and taxonomy of abstract image editing. To measure instruction-following in this challenging domain, we introduce Entity-Rubrics, a framework that breaks down abstract edits into individual, entity-level assessments and achieves strong correlation with human judgment. Alongside this framework, we contribute AbstractEdit, the first benchmark dedicated to abstract image editing across diverse real-world scenes. Evaluating 11 leading models on this dataset reveals a fundamental challenge: standard architectures struggle to balance intent and preservation, commonly defaulting to under-editing or over-editing. Our analysis demonstrates that driving meaningful improvements relies heavily on integrating advanced LLM text encoders and iterative thinking. Looking forward, our entity-based paradigm can generalize beyond assessment to serve as a reward model, enable models to correctly interpret abstract communication, or highlight specific failures in test-time critique loops. Ultimately, we hope this work serves as a stepping stone toward seamless multimodal interaction, closing the gap between rigid machine execution and the natural, open-ended way humans communicate.

cs.CV↗

arXiv2026

FUSE: Ensembling Verifiers with Zero Labeled Data

Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In practice, this often involves using imperfect LLM judges and reward models since ground truth acquisition can be time-consuming and expensive. We introduce Fully Unsupervised Score Ensembling (FUSE), a method for improving verification quality by ensembling verifiers without access to ground truth correctness labels. The key idea behind FUSE is to control conditional dependencies between verifiers in a manner that improves the unsupervised performance of a class of spectral algorithms from the ensembling literature. Despite requiring zero ground truth labels, FUSE typically matches or improves upon semi-supervised alternatives in test-time scaling experiments with diverse sets of generator models, verifiers, and benchmarks. In particular, we validate our method on both conventional academic benchmarks such as GPQA Diamond and on frontier, unsaturated benchmarks such as Humanity's Last Exam and IMO Shortlist questions.

stat.ML↗

arXiv2025

Early Estimation of Language to Latent Alignment in Diffusion Models

Conditional diffusion models frequently suffer from language-image misalignments. Due to the ambiguity of intermediate noise corrupted latents, assessing prompt adherence currently requires completing the entire sampling trajectory. This late-stage evaluation incurs even higher computational costs during test-time scaling strategies, such as Best-of-N (BoN) sampling, as all misaligned trajectories must finish generation before being discarded. To tackle this, we propose NoisyCLIP, a noise-aware twin-tower model that enables early language-to-latent alignment estimation. By learning a vision encoder on noise-corrupted latents, we allow the model to "see" through the ambiguity of intermediate diffusion steps. To facilitate this training, we investigate noise-data augmentation sampling strategies and introduce two new benchmark datasets: Noisy-Conceptual-Captions and Noisy-GenAI-Bench. When applied as an early-stopping criterion for BoN, NoisyCLIP at half cost matches or beats frozen CLIP at full cost. Ultimately, this transforms alignment assessment from an expensive final check into a continuous monitoring tool, drastically reducing compute costs without sacrificing semantic fidelity.

cs.CV↗

arXiv2025

Latent Beam Diffusion Models for Generating Visual Sequences

While diffusion models excel at generating high-quality images from text prompts, they struggle with visual consistency when generating image sequences. Existing methods generate each image independently, leading to disjointed narratives - a challenge further exacerbated in non-linear storytelling, where scenes must connect beyond adjacent images. We introduce a novel beam search strategy for latent space exploration, enabling conditional generation of full image sequences with beam search decoding. In contrast to earlier methods that rely on fixed latent priors, our method dynamically samples past latents to search for an optimal sequence of latent representations, ensuring coherent visual transitions. As the latent denoising space is explored, the beam search graph is pruned with a cross-attention mechanism that efficiently scores search paths, prioritizing alignment with both textual prompts and visual context. Human and automatic evaluations confirm that BeamDiffusion outperforms other baseline methods, producing full sequences with superior coherence, visual continuity, and textual alignment.

cs.CV↗

arXiv2024

Streamlining Conformal Information Retrieval via Score Refinement

Information retrieval (IR) methods, like retrieval augmented generation, are fundamental to modern applications but often lack statistical guarantees. Conformal prediction addresses this by retrieving sets guaranteed to include relevant information, yet existing approaches produce large-sized sets, incurring high computational costs and slow response times. In this work, we introduce a score refinement method that applies a simple monotone transformation to retrieval scores, leading to significantly smaller conformal sets while maintaining their statistical guarantees. Experiments on various BEIR benchmarks validate the effectiveness of our approach in producing compact sets containing relevant information.

cs.IR↗

arXiv2024

Anchored Diffusion for Video Face Reenactment

Video generation has drawn significant interest recently, pushing the development of large-scale models capable of producing realistic videos with coherent motion. Due to memory constraints, these models typically generate short video segments that are then combined into long videos. The merging process poses a significant challenge, as it requires ensuring smooth transitions and overall consistency. In this paper, we introduce Anchored Diffusion, a novel method for synthesizing relatively long and seamless videos. We extend Diffusion Transformers (DiTs) to incorporate temporal information, creating our sequence-DiT (sDiT) model for generating short video segments. Unlike previous works, we train our model on video sequences with random non-uniform temporal spacing and incorporate temporal information via external guidance, increasing flexibility and allowing it to capture both short and long-term relationships. Furthermore, during inference, we leverage the transformer architecture to modify the diffusion process, generating a batch of non-uniform sequences anchored to a common frame, ensuring consistency regardless of temporal distance. To demonstrate our method, we focus on face reenactment, the task of creating a video from a source image that replicates the facial expressions and movements from a driving video. Through comprehensive experiments, we show our approach outperforms current techniques in producing longer consistent high-quality videos while offering editing capabilities.

cs.CV↗

arXiv2024

On the Semantic Latent Space of Diffusion-Based Text-to-Speech Models

The incorporation of Denoising Diffusion Models (DDMs) in the Text-to-Speech (TTS) domain is rising, providing great value in synthesizing high quality speech. Although they exhibit impressive audio quality, the extent of their semantic capabilities is unknown, and controlling their synthesized speech's vocal properties remains a challenge. Inspired by recent advances in image synthesis, we explore the latent space of frozen TTS models, which is composed of the latent bottleneck activations of the DDM's denoiser. We identify that this space contains rich semantic information, and outline several novel methods for finding semantic directions within it, both supervised and unsupervised. We then demonstrate how these enable off-the-shelf audio editing, without any further training, architectural changes or data requirements. We present evidence of the semantic and acoustic qualities of the edited audio, and provide supplemental samples: https://latent-analysis-grad-tts.github.io/speech-samples/.

cs.SD↗

arXiv2024

Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models

The pursuit of high perceptual quality in image restoration has driven the development of revolutionary generative models, capable of producing results often visually indistinguishable from real data. However, as their perceptual quality continues to improve, these models also exhibit a growing tendency to generate hallucinations - realistic-looking details that do not exist in the ground truth images. Hallucinations in these models create uncertainty about their reliability, raising major concerns about their practical application. This paper investigates this phenomenon through the lens of information theory, revealing a fundamental tradeoff between uncertainty and perception. We rigorously analyze the relationship between these two factors, proving that the global minimal uncertainty in generative models grows in tandem with perception. In particular, we define the inherent uncertainty of the restoration problem and show that attaining perfect perceptual quality entails at least twice this uncertainty. Additionally, we establish a relation between distortion, uncertainty and perception, through which we prove the aforementioned uncertainly-perception tradeoff induces the well-known perception-distortion tradeoff. We demonstrate our theoretical findings through experiments with super-resolution and inpainting algorithms. This work uncovers fundamental limitations of generative models in achieving both high perceptual quality and reliable predictions for image restoration. Thus, we aim to raise awareness among practitioners about this inherent tradeoff, empowering them to make informed decisions and potentially prioritize safety over perceptual performance.

cs.LG↗

arXiv2024

Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models

Analyzing the cardiovascular system condition via Electrocardiography (ECG) is a common and highly effective approach, and it has been practiced and perfected over many decades. ECG sensing is non-invasive and relatively easy to acquire, and yet it is still cumbersome for holter monitoring tests that may span over hours and even days. A possible alternative in this context is Photoplethysmography (PPG): An optically-based signal that measures blood volume fluctuations, as typically sensed by conventional ``wearable devices''. While PPG presents clear advantages in acquisition, convenience, and cost-effectiveness, ECG provides more comprehensive information, allowing for a more precise detection of heart conditions. This implies that a conversion from PPG to ECG, as recently discussed in the literature, inherently involves an unavoidable level of uncertainty. In this paper we introduce a novel methodology for addressing the PPG-2-ECG conversion, and offer an enhanced classification of cardiovascular conditions using the given PPG, all while taking into account the uncertainties arising from the conversion process. We provide a mathematical justification for our proposed computational approach, and present empirical studies demonstrating its superior performance compared to state-of-the-art baseline methods.

cs.LG↗

arXiv2024

Early Time Classification with Accumulated Accuracy Gap Control

Early time classification algorithms aim to label a stream of features without processing the full input stream, while maintaining accuracy comparable to that achieved by applying the classifier to the entire input. In this paper, we introduce a statistical framework that can be applied to any sequential classifier, formulating a calibrated stopping rule. This data-driven rule attains finite-sample, distribution-free control of the accuracy gap between full and early-time classification. We start by presenting a novel method that builds on the Learn-then-Test calibration framework to control this gap marginally, on average over i.i.d. instances. As this algorithm tends to yield an excessively high accuracy gap for early halt times, our main contribution is the proposal of a framework that controls a stronger notion of error, where the accuracy gap is controlled conditionally on the accumulated halt times. Numerical experiments demonstrate the effectiveness, applicability, and usefulness of our method. We show that our proposed early stopping mechanism reduces up to 94% of timesteps used for classification while achieving rigorous accuracy gap control.

cs.LG↗

arXiv2023

Weakly-Supervised Surgical Phase Recognition

A key element of computer-assisted surgery systems is phase recognition of surgical videos. Existing phase recognition algorithms require frame-wise annotation of a large number of videos, which is time and money consuming. In this work we join concepts of graph segmentation with self-supervised learning to derive a random-walk solution for per-frame phase prediction. Furthermore, we utilize within our method two forms of weak supervision: sparse timestamps or few-shot learning. The proposed algorithm enjoys low complexity and can operate in lowdata regimes. We validate our method by running experiments with the public Cholec80 dataset of laparoscopic cholecystectomy videos, demonstrating promising performance in multiple setups.

cs.CV↗

arXiv2023

Self-Supervised Learning for Endoscopic Video Analysis

Self-supervised learning (SSL) has led to important breakthroughs in computer vision by allowing learning from large amounts of unlabeled data. As such, it might have a pivotal role to play in biomedicine where annotating data requires a highly specialized expertise. Yet, there are many healthcare domains for which SSL has not been extensively explored. One such domain is endoscopy, minimally invasive procedures which are commonly used to detect and treat infections, chronic inflammatory diseases or cancer. In this work, we study the use of a leading SSL framework, namely Masked Siamese Networks (MSNs), for endoscopic video analysis such as colonoscopy and laparoscopy. To fully exploit the power of SSL, we create sizable unlabeled endoscopic video datasets for training MSNs. These strong image representations serve as a foundation for secondary training with limited annotated datasets, resulting in state-of-the-art performance in endoscopic benchmarks like surgical phase recognition during laparoscopy and colonoscopic polyp characterization. Additionally, we achieve a 50% reduction in annotated data size without sacrificing performance. Thus, our work provides evidence that SSL can dramatically reduce the need of annotated data in endoscopy.

cs.CV↗

arXiv2022

What's Behind the Mask: Estimating Uncertainty in Image-to-Image Problems

Estimating uncertainty in image-to-image networks is an important task, particularly as such networks are being increasingly deployed in the biological and medical imaging realms. In this paper, we introduce a new approach to this problem based on masking. Given an existing image-to-image network, our approach computes a mask such that the distance between the masked reconstructed image and the masked true image is guaranteed to be less than a specified threshold, with high probability. The mask thus identifies the more certain regions of the reconstructed image. Our approach is agnostic to the underlying image-to-image network, and only requires triples of the input (degraded), reconstructed and true images for training. Furthermore, our method is agnostic to the distance metric used. As a result, one can use $L_p$-style distances or perceptual distances like LPIPS, which contrasts with interval-based approaches to uncertainty. Our theoretical guarantees derive from a conformal calibration procedure. We evaluate our mask-based approach to uncertainty on image colorization, image completion, and super-resolution tasks, demonstrating high quality performance on each.

cs.CV↗

arXiv2020

Regularization by Denoising via Fixed-Point Projection (RED-PRO)

Inverse problems in image processing are typically cast as optimization tasks, consisting of data-fidelity and stabilizing regularization terms. A recent regularization strategy of great interest utilizes the power of denoising engines. Two such methods are the Plug-and-Play Prior (PnP) and Regularization by Denoising (RED). While both have shown state-of-the-art results in various recovery tasks, their theoretical justification is incomplete. In this paper, we aim to bridge between RED and PnP, enriching the understanding of both frameworks. Towards that end, we reformulate RED as a convex optimization problem utilizing a projection (RED-PRO) onto the fixed-point set of demicontractive denoisers. We offer a simple iterative solution to this problem, by which we show that PnP proximal gradient method is a special case of RED-PRO, while providing guarantees for the convergence of both frameworks to globally optimal solutions. In addition, we present relaxations of RED-PRO that allow for handling denoisers with limited fixed-point sets. Finally, we demonstrate RED-PRO for the tasks of image deblurring and super-resolution, showing improved results with respect to the original RED framework.

eess.IV↗

arXiv2020

Sparse Array Design via Fractal Geometries

Sparse sensor arrays have attracted considerable attention in various fields such as radar, array processing, ultrasound imaging and communications. In the context of correlation-based processing, such arrays enable to resolve more uncorrelated sources than physical sensors. This property of sparse arrays stems from the size of their difference coarrays, defined as the differences of element locations. Thus, the design of sparse arrays with large difference coarrays is of great interest. In addition, other array properties such as symmetry, robustness and array economy are important in different applications. Numerous studies have proposed diverse sparse geometries, focusing on certain properties while lacking others. Incorporating multiple properties into the design task leads to combinatorial problems which are generally NP-hard. For small arrays these optimization problems can be solved by brute force, however, in large scale they become intractable. In this paper, we propose a scalable systematic way to design large sparse arrays considering multiple properties. To that end, we introduce a fractal array design in which a generator array is recursively expanded according to its difference coarray. Our main result states that for an appropriate choice of the generator such fractal arrays exhibit large difference coarrays. Furthermore, we show that the fractal arrays inherit their properties from their generators. Thus, a small generator can be optimized according to desired requirements and then expanded to create a fractal array which meets the same criteria. This approach paves the way to efficient design of large arrays of hundreds or thousands of elements with specific properties.

eess.SP↗

arXiv2020

Sparse Convolutional Beamforming for 3D Ultrafast Ultrasound Imaging

Real-time three dimensional (3D) ultrasound provides complete visualization of inner body organs and blood vasculature, which is crucial for diagnosis and treatment of diverse diseases. However, 3D systems require massive hardware due to the huge number of transducer elements and consequent data size. This increases cost significantly and limits both frame rate and image quality, thus preventing 3D ultrasound from being common practice in clinics worldwide. A recent study proposed a technique, called convolutional beamforming algorithm (COBA), which obtains improved image quality while allowing notable element reduction. COBA was developed and tested for 2D focused imaging using full and sparse arrays. The later was referred to as sparse COBA (SCOBA). In this paper, we build upon previous work and introduce a nonlinear beamformer for 3D imaging, called COBA-3D, consisting of 2D spatial convolution of the in-phase and quadrature received signals. The proposed technique considers diverging-wave transmission, thus, achieves improved image resolution and contrast compared with standard delay-and-sum beamforming, while enabling high frame rate. Incorporating 2D sparse arrays into our method creates SCOBA-3D: a sparse beamformer which offers significant element reduction and thus allows to perform 3D imaging with the resources typically available for 2D setups. To create 2D thinned arrays, we present a scalable and systematic way to design 2D fractal sparse arrays. The proposed framework paves the way for affordable ultrafast ultrasound devices that perform high-quality 3D imaging, as demonstrated using phantom and ex-vivo data.

eess.SP↗

arXiv2019

Adaptive Ultrasound Beamforming using Deep Learning

Biomedical imaging is unequivocally dependent on the ability to reconstruct interpretable and high-quality images from acquired sensor data. This reconstruction process is pivotal across many applications, spanning from magnetic resonance imaging to ultrasound imaging. While advanced data-adaptive reconstruction methods can recover much higher image quality than traditional approaches, their implementation often poses a high computational burden. In ultrasound imaging, this burden is significant, especially when striving for low-cost systems, and has motivated the development of high-resolution and high-contrast adaptive beamforming methods. Here we show that deep neural networks that adopt the algorithmic structure and constraints of adaptive signal processing techniques can efficiently learn to perform fast high-quality ultrasound beamforming using very little training data. We apply our technique to two distinct ultrasound acquisition strategies (plane wave, and synthetic aperture), and demonstrate that high image quality can be maintained when measuring at low data-rates, using undersampled array designs. Beyond biomedical imaging, we expect that the proposed deep~learning based adaptive processing framework can benefit a variety of array and signal processing applications, in particular when data-efficiency and robustness are of importance.

eess.SP↗

arXiv2019

Deep learning in ultrasound imaging

We consider deep learning strategies in ultrasound systems, from the front-end to advanced applications. Our goal is to provide the reader with a broad understanding of the possible impact of deep learning methodologies on many aspects of ultrasound imaging. In particular, we discuss methods that lie at the interface of signal acquisition and machine learning, exploiting both data structure (e.g. sparsity in some domain) and data dimensionality (big data) already at the raw radio-frequency channel stage. As some examples, we outline efficient and effective deep learning solutions for adaptive beamforming and adaptive spectral Doppler through artificial agents, learn compressive encodings for color Doppler, and provide a framework for structured signal recovery by learning fast approximations of iterative minimization problems, with applications to clutter suppression and super-resolution ultrasound. These emerging technologies may have considerable impact on ultrasound imaging, showing promise across key components in the receive processing chain.

eess.SP↗