Papers Data Compression
“Data Compression” 태그가 달린 논문 459편 · 필터 해제
Lossless data compression by large models
Modern data compression methods are slowly reaching their limits after 80 years of research, millions of papers, and wide range of applications. Yet, the extravagant 6G communication speed requirement raises a major open…
Data CompressionRanking LLMs by compression
We conceptualize the process of understanding as information compression, and propose a method for ranking large language models (LLMs) based on lossless data compression. We demonstrate the equivalence of compression le…
coreference-resolutionCoreference ResolutionData CompressionLanguage Modeling+5Measuring Sample Importance in Data Pruning for Language Models based on Information Entropy
Compute-efficient training of language models has become an important issue. We consider data pruning for data-efficient training of LLMs. In this work, we consider a data pruning method based on information entropy. We …
Data CompressionInformativenessLanguage ModelingLanguage ModellingLearned Image Compression for HE-stained Histopathological Images via Stain Deconvolution
Processing histopathological Whole Slide Images (WSI) leads to massive storage requirements for clinics worldwide. Even after lossy image compression during image acquisition, additional lossy compression is frequently p…
Data CompressionImage CompressionMS-SSIMSSIM+1Language Models Resist Alignment: Evidence From Data Compression
Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-c…
Data CompressionDeep Generative Modeling Reshapes Compression and Transmission: From Efficiency to Resiliency
Information theory and machine learning are inextricably linked and have even been referred to as "two sides of the same coin". One particularly elegant connection is the essential equivalence between probabilistic gener…
Data CompressionA 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior
Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resourc…
Data CompressionDecoderDeep LearningImage EnhancementSATSense: Multi-Satellite Collaborative Framework for Spectrum Sensing
Low Earth Orbit satellite Internet has recently been deployed, providing worldwide service with non-terrestrial networks. With the large-scale deployment of both non-terrestrial and terrestrial networks, limited spectrum…
Contrastive LearningData CompressionGraph Neural NetworkSparse $L^1$-Autoencoders for Scientific Data Compression
Scientific datasets present unique challenges for machine learning-driven compression methods, including more stringent requirements on accuracy and mitigation of potential invalidating artifacts. Drawing on results from…
compressed sensingData CompressionDistributed ComputingRate-Adaptive Quantization: A Multi-Rate Codebook Adaptation for Vector Quantization-based Generative Models
Learning discrete representations with vector quantization (VQ) has emerged as a powerful approach in various generative models. However, most VQ-based models rely on a single, fixed-rate codebook, requiring extensive re…
Data CompressionImage GenerationImage ReconstructionQuantization"Turing Tests" For An AI Scientist
While LLMs have shown impressive capabilities in solving math or coding problems, the ability to make scientific discoveries remains a distinct challenge. This paper proposes a "Turing test for an AI scientist" to assess…
AI AgentData CompressionMathscientific discoveryEfficient Learned Wavelet Image and Video Coding
Learned wavelet image and video coding approaches provide an explainable framework with a latent space corresponding to a wavelet decomposition. The wavelet image coder iWave++ achieves state-of-the-art performance and h…
Data CompressionVideo CompressionEffective In-Context Example Selection through Data Compression
In-context learning has been extensively validated in large language models. However, the mechanism and selection strategy for in-context example selection, which is a crucial ingredient in this approach, lacks systemati…
Data CompressionIn-Context LearningGoal-oriented compression for $L_p$-norm-type goal functions: Application to power consumption scheduling
Conventional data compression schemes aim at implementing a trade-off between the rate required to represent the compressed data and the resulting distortion between the original and reconstructed data. However, in more …
Data CompressionQuantizationSchedulingSome Notes on the Sample Complexity of Approximate Channel Simulation
Channel simulation algorithms can efficiently encode random samples from a prescribed target distribution $Q$ and find applications in machine learning-based lossy data compression. However, algorithms that encode exact …
Data CompressionPointCompress3D: A Point Cloud Compression Framework for Roadside LiDARs in Intelligent Transportation Systems
In the context of Intelligent Transportation Systems (ITS), efficient data compression is crucial for managing large-scale point cloud data acquired by roadside LiDAR sensors. The demand for efficient storage, streaming,…
Data Compressionobject-detectionObject DetectionReal-Time Object DetectionLightweight Conceptual Dictionary Learning for Text Classification Using Information Compression
We propose a novel, lightweight supervised dictionary learning framework for text classification based on data compression and representation. This two-phase algorithm initially employs the Lempel-Ziv-Welch (LZW) algorit…
Data CompressionDictionary LearningInformation Planetext-classification+1Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning
Inductive biases are crucial in disentangled representation learning for narrowing down an underspecified solution set. In this work, we consider endowing a neural network autoencoder with three select inductive biases f…
Data CompressionDecoderDisentanglementQuantization+1Quantization of Large Language Models with an Overdetermined Basis
In this paper, we introduce an algorithm for data quantization based on the principles of Kashin representation. This approach hinges on decomposing any given vector, matrix, or tensor into two factors. The first factor …
Data CompressionQuantizationtext-classificationText ClassificationA Joint Data Compression and Time-Delay Estimation Method For Distributed Systems via Extremum Encoding
Motivated by the proliferation of mobile devices, we consider a basic form of the ubiquitous problem of time-delay estimation (TDE), but with communication constraints between two non co-located sensors. In this setting,…
Data CompressionTime Series