565 citations · 1.1k across the 18 of their papers we have counts for
19 papers
StarCoder 2 and The Stack v2: The Next Generation
Anton Lozhkov, Raymond Li, Loubna Ben Allal +63
The BigCode project, an open-scientific collaboration focused on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder2. In partnership wi…
Semi-Supervised Semantic Segmentation via Marginal Contextual Information
Moshe Kimhi, Shai Kimhi, Evgenii Zheltonozhskii +2
We present a novel confidence refinement scheme that enhances pseudo labels in semi-supervised semantic segmentation. Unlike existing methods, which filter pixels with low-confiden…
StarCoder: may the source be with you!
Raymond Li, Loubna Ben Allal, Yangtian Zi +64
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase…
GoToNet: Fast Monocular Scene Exposure and Exploration
Tom Avrech, Evgenii Zheltonozhskii, Chaim Baskin +1
Autonomous scene exposure and exploration, especially in localization or communication-denied areas, useful for finding targets in unknown scenes, remains a challenging problem in…
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao +448
Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabil…
Graph Representation Learning via Aggregation Enhancement
Maxim Fishman, Chaim Baskin, Evgenii Zheltonozhskii +3
Graph neural networks (GNNs) have become a powerful tool for processing graph-structured data but still face challenges in effectively aggregating and propagating information betwe…
End-to-End Referring Video Object Segmentation with Multimodal Transformers
Adam Botach, Evgenii Zheltonozhskii, Chaim Baskin
The referring video object segmentation task (RVOS) involves segmentation of a text-referred object instance in the frames of a given video. Due to the complex nature of this multi…
Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
Evgenii Zheltonozhskii, Chaim Baskin, Avi Mendelson +2
The success of learning with noisy labels (LNL) methods relies heavily on the success of a warm-up stage where standard supervised training is performed using the full (noisy) trai…
Single-Node Attacks for Fooling Graph Neural Networks
Ben Finkelshtein, Chaim Baskin, Evgenii Zheltonozhskii +1
Graph neural networks (GNNs) have shown broad applicability in a variety of domains. These domains, e.g., social networks and product recommendations, are fertile ground for malici…
Self-Supervised Learning for Large-Scale Unsupervised Image Clustering
Evgenii Zheltonozhskii, Chaim Baskin, Alex M. Bronstein +1
Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data.…
HCM: Hardware-Aware Complexity Metric for Neural Network Architectures
Alex Karbachevsky, Chaim Baskin, Evgenii Zheltonozhskii +4
Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing. Although CNN hardware acceler…
Colored Noise Injection for Training Adversarially Robust Neural Networks
Evgenii Zheltonozhskii, Chaim Baskin, Yaniv Nemcovsky +3
Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that le…
Smoothed Inference for Adversarially-Trained Models
Yaniv Nemcovsky, Evgenii Zheltonozhskii, Chaim Baskin +4
Deep neural networks are known to be vulnerable to adversarial attacks. Current methods of defense from such attacks are based on either implicit or explicit regularization, e.g.,…
Loss Aware Post-training Quantization
Yury Nahshan, Brian Chmiel, Chaim Baskin +4
Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for I…
CAT: Compression-Aware Training for bandwidth reduction
Chaim Baskin, Brian Chmiel, Evgenii Zheltonozhskii +3
Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous u…
Feature Map Transform Coding for Energy-Efficient CNN Inference
Brian Chmiel, Chaim Baskin, Ron Banner +5
Convolutional neural networks (CNNs) achieve state-of-the-art accuracy in a variety of tasks in computer vision and beyond. One of the major obstacles hindering the ubiquitous use…
Towards Learning of Filter-Level Heterogeneous Compression of Convolutional Neural Networks
Yochai Zur, Chaim Baskin, Evgenii Zheltonozhskii +4
Recently, deep learning has become a de facto standard in machine learning with convolutional neural networks (CNNs) demonstrating spectacular success on a wide variety of tasks. H…
UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks
Chaim Baskin, Eli Schwartz, Evgenii Zheltonozhskii +4
We present a novel method for neural network quantization that emulates a non-uniform -quantile quantizer, which adapts to the distribution of the quantized parameters. Our appr…
Streaming Architecture for Large-Scale Quantized Neural Networks on an FPGA-Based Dataflow Platform
Chaim Baskin, Natan Liss, Evgenii Zheltonozhskii +2
Deep neural networks (DNNs) are used by different applications that are executed on a range of computer architectures, from IoT devices to supercomputers. The footprint of these ne…