Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Barkan, Oren"'
Despite the many advances of Large Language Models (LLMs) and their unprecedented rapid evolution, their impact and integration into every facet of our daily lives is limited due to various reasons. One critical factor hindering their widespread adop
Externí odkaz:
http://arxiv.org/abs/2403.02889
Autor:
Uzrad, Noy, Barkan, Oren, Elharar, Almog, Shvartzman, Shlomi, Laufer, Moshe, Wolf, Lior, Koenigstein, Noam
This paper presents DiffMoog - a differentiable modular synthesizer with a comprehensive set of modules typically found in commercial instruments. Being differentiable, it allows integration into neural networks, enabling automated sound matching, to
Externí odkaz:
http://arxiv.org/abs/2401.12570
We introduce Iterated Integrated Attributions (IIA) - a generic method for explaining the predictions of vision models. IIA employs iterative integration across the input image, the internal representations generated by the model, and their gradients
Externí odkaz:
http://arxiv.org/abs/2310.18585
We present Learning to Explain (LTX), a model-agnostic framework designed for providing post-hoc explanations for vision models. The LTX framework introduces an "explainer" model that generates explanation maps, highlighting the crucial regions that
Externí odkaz:
http://arxiv.org/abs/2310.16584
Autor:
Barkan, Oren, Elisha, Yehonatan, Weill, Jonathan, Asher, Yuval, Eshel, Amit, Koenigstein, Noam
This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the intermediate representations of the model, coupled with their corresponding g
Externí odkaz:
http://arxiv.org/abs/2310.15368
Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond
Autor:
Barkan, Oren, Reiss, Tal, Weill, Jonathan, Katz, Ori, Hirsch, Roy, Malkiel, Itzik, Koenigstein, Noam
Visual similarities discovery (VSD) is an important task with broad e-commerce applications. Given an image of a certain object, the goal of VSD is to retrieve images of different objects with high perceptual visual similarity. Although being a highl
Externí odkaz:
http://arxiv.org/abs/2308.14753
Autor:
Barkan, Oren, Caciularu, Avi, Rejwan, Idan, Katz, Ori, Weill, Jonathan, Malkiel, Itzik, Koenigstein, Noam
We present Variational Bayesian Network (VBN) - a novel Bayesian entity representation learning model that utilizes hierarchical and relational side information and is particularly useful for modeling entities in the ``long-tail'', where the data is
Externí odkaz:
http://arxiv.org/abs/2306.16326
Autor:
Malkiel, Itzik, Alon, Uri, Yehuda, Yakir, Keren, Shahar, Barkan, Oren, Ronen, Royi, Koenigstein, Noam
Transcriptions of phone calls are of significant value across diverse fields, such as sales, customer service, healthcare, and law enforcement. Nevertheless, the analysis of these recorded conversations can be an arduous and time-intensive process, e
Externí odkaz:
http://arxiv.org/abs/2306.07941
Autor:
Malkiel, Itzik, Ginzburg, Dvir, Barkan, Oren, Caciularu, Avi, Weill, Jonathan, Koenigstein, Noam
Recently, there has been growing interest in the ability of Transformer-based models to produce meaningful embeddings of text with several applications, such as text similarity. Despite significant progress in the field, the explanations for similari
Externí odkaz:
http://arxiv.org/abs/2208.06612
We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for recommenda
Externí odkaz:
http://arxiv.org/abs/2208.06610