9 accepted papers
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 intro…
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 seque…
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 tend…
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 spee…
In recent years there has been increasing interest in leveraging denoisers for solving general inverse problems. Two leading frameworks are regularization-by-denoising (RED) and plug-and-play priors (PnP) which incorporate explicit likelihood functions with priors induced by denoising algorithms. R…
Sparse and low-rank decomposition, also known as robust principle component analysis, has been applied successfully in numerous applications. Typically, this approach leads to a minimization problem which is solved using iterative algorithms. Drawing inspiration from recurrent networks, in recent ye…
The real-time nature that makes diagnostic ultrasonography so appealing to clinicians imposes strong constraints on the computational complexity of image reconstruction algorithms. As such, these typically rely on traditional delay-and-sum beamforming, a low-complexity approach that unfortunately co…
Sparse arrays are of great interest since they can identify O(N <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) uncorrelated sources with N physical sensors. This stems from their large difference coarray, defined as the differences between se…
The number of elements of a uniform linear array (ULA) is the main bottleneck in many applications in array processing in terms of cost and power consumption. This motivates the use of sparse arrays where some of the elements are removed. However, designing a sparse array configuration with the smal…