Related papers: Single-Thread JPEG Decoder Benchmarks Mis-Evaluate…

Image loading represents a critical bottleneck in modern machine learning pipelines, particularly in computer vision tasks where JPEG remains the dominant format. This study presents a systematic performance analysis of nine popular Python…

With the emergence of social networks and improvements in computational photography, billions of JPEG images are shared and viewed on a daily basis. Desktops, tablets and smartphones constitute the vast majority of hardware platforms used…

The JPEG compression format has been the standard for lossy image compression for over multiple decades, offering high compression rates at minor perceptual loss in image quality. For GPU-accelerated computer vision and deep learning tasks,…

This paper analyzes the design and competitiveness of four neural network (NN) architectures recently proposed as decoders for forward error correction (FEC) codes. We first consider the so-called single-label neural network (SLNN) and the…

Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM…

This paper delves into recent hardware implementations of the Lempel-Ziv 4 (LZ4) algorithm, highlighting two key factors that limit the throughput of single-kernel compressors. Firstly, the actual parallelism exhibited in single-kernel…

We present YOLOBench, a benchmark comprised of 550+ YOLO-based object detection models on 4 different datasets and 4 different embedded hardware platforms (x86 CPU, ARM CPU, Nvidia GPU, NPU). We collect accuracy and latency numbers for a…

Zero-knowledge proofs (ZKP) are becoming a gold standard in scaling blockchains and bringing Web3 to life. At the same time, ZKP for transactions running on the Ethereum Virtual Machine require powerful servers with hundreds of CPU cores.…

Efficient point cloud coding has become increasingly critical for multiple applications such as virtual reality, autonomous driving, and digital twin systems, where rich and interactive 3D data representations may functionally make the…

Data center networks (DCNs) require a low-cost, low-power optical transceiver to handle increased traffic from generative artificial intelligence, video streaming services, and more. Improving the required signal-to-noise ratio (RSNR) by…

Neural image compression methods have seen increasingly strong performance in recent years. However, they suffer orders of magnitude higher computational complexity compared to traditional codecs, which hinders their real-world deployment.…

LLMs demonstrate strong performance on code benchmarks, yet consistent reasoning across forward and backward execution remains elusive. We present RoundTripCodeEval (RTCE), a benchmark of four code execution reasoning tasks that evaluates…

Video compression is indispensable to most video analysis systems. Despite saving transportation bandwidth, it also deteriorates downstream video understanding tasks, especially at low-bitrate settings. To systematically investigate this…

While NVIDIA remains the dominant provider of AI accelerators within cloud data center, emerging vendors such as AMD, Intel, Mac, and Huawei offer cost-effective alternatives with claims of compatibility and performance. This paper presents…

Deep learning models have grown increasingly complex, with input data sizes scaling accordingly. Despite substantial advances in specialized deep learning hardware, data loading continues to be a major bottleneck that limits training and…

In recent years, the global demand for high-resolution videos and the emergence of new multimedia applications have created the need for a new video coding standard. Hence, in July 2020 the Versatile Video Coding (VVC) standard was released…

Large language models perform well on many medical QA benchmarks, but real clinical reasoning often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated…

This paper describes our solution for the 2$^\text{nd}$ YouTube-8M video understanding challenge organized by Google AI. Unlike the video recognition benchmarks, such as Kinetics and Moments, the YouTube-8M challenge provides pre-extracted…

Resource-constrained hardware, such as edge devices or cell phones, often rely on cloud servers to provide the required computational resources for inference in deep vision models. However, transferring image and video data from an edge or…

The remarkable progress of Multi-modal Large Language Models (MLLMs) has attracted significant attention due to their superior performance in visual contexts. However, their capabilities in turning visual figure to executable code, have not…