Related papers: SemanticBBV: A Semantic Signature for Cross-Progra…

As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or…

The systematic evaluation and understanding of computer vision models under varying conditions require large amounts of data with comprehensive and customized labels, which real-world vision datasets rarely satisfy. While current synthetic…

Shared virtual memory (SVM) is key in heterogeneous systems on chip (SoCs), which combine a general-purpose host processor with a many-core accelerator, both for programmability and to avoid data duplication. However, SVM can bring a…

When reverse engineering a binary, the analyst must first understand the semantics of the binary's functions through either manual or automatic analysis. Manual semantic analysis is time-consuming, because abstractions provided by high…

Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with…

In this paper we address three different computer vision tasks using a single basic architecture: depth prediction, surface normal estimation, and semantic labeling. We use a multiscale convolutional network that is able to adapt easily to…

Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and…

This work uses visual knowledge discovery in parallel coordinates to advance methods of interpretable machine learning. The graphic data representation in parallel coordinates made the concepts of hypercubes and hyperblocks (HBs) simple to…

Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance. Despite the success of deep co-training methods, their underlying mechanisms…

Spatio-temporal pattern recognition is a fundamental ability of the brain which is required for numerous real-world activities. Recent deep learning approaches have reached outstanding accuracies in such tasks, but their implementation on…

A site-specific Type-II codebook design is proposed for downlink massive multiple-input multiple-output (MIMO) limited-feedback beamforming. The key idea is to embed a learned site-specific propagation prior into the Type-II channel state…

In this paper we present the development of Acceleratable UVCs from standard UVCs in SystemVerilog and their usage in UVM based Verification Environment of Image Signal Processing designs to increase run time performance. This paper covers…

In clinical medicine, precise image segmentation can provide substantial support to clinicians. However, obtaining high-quality segmentation typically demands extensive pixel-level annotations, which are labor-intensive and expensive.…

Identifier names convey useful information about the intended semantics of code. Name-based program analyses use this information, e.g., to detect bugs, to predict types, and to improve the readability of code. At the core of name-based…

Transfer learning has proven to be crucial in advancing the state of speech and natural language processing research in recent years. In speech, a model pre-trained by self-supervised learning transfers remarkably well on multiple tasks.…

With the recent success of embeddings in natural language processing, research has been conducted into applying similar methods to code analysis. Most works attempt to process the code directly or use a syntactic tree representation,…

The low-level details and high-level semantics are both essential to the semantic segmentation task. However, to speed up the model inference, current approaches almost always sacrifice the low-level details, which leads to a considerable…

Real-time semantic segmentation presents the dual challenge of designing efficient architectures that capture large receptive fields for semantic understanding while also refining detailed contours. Vision transformers model long-range…

Spatial transcriptomics (ST) technologies enable gene expression profiling with spatial resolution, offering unprecedented insights into tissue organization and disease heterogeneity. However, current analysis methods often struggle with…

Semantic Communication (SemCom) is a promising new paradigm for next-generation communication systems, emphasizing the transmission of core information, particularly in environments characterized by uncertainty, noise, and bandwidth…