20 papers · ranked by Valyu relevance
Moumita Kamal, Douglas A. Talbert
In real-world applications, computational constraints often require transforming large models into smaller, more efficient versions through model compression. While these techniques aim to reduce size and computational cost without sacrificing performance, their evaluations have traditionally focused on the trade-off…
Jasmine Quah, Omer Sella, Thomas Heinis
DNA is a leading candidate as the next archival storage media due to its density, durability and sustainability. To read (and write) data DNA storage exploits technology that has been developed over decades to sequence naturally occurring DNA in the life sciences. To achieve higher accuracy for previously unseen…
Chen-Han Tsai
In this report, we investigate the potential use of large language models (LLM's) in the task of data compression. Previous works have demonstrated promising results in applying LLM's towards compressing not only text, but also a wide range of multi-modal data. Despite the favorable performance achieved, there still…
Chun Jiang, Mingxin Hou, Hongxuan Wang, Fangmin Xu
In customized production environments featuring multi-task parallelism, the efficient adaptability of edge intelligent models is essential for ensuring the stable operation of production lines. However, rapidly generating deployable lightweight models under conditions of frequent task changes and constrained hardware…
Aviv Adler, Jennifer Tang
It is well-known in the field of lossless data compression that probabilistic nextsymbol prediction can be used to compress sequences of symbols. Deep neural networks are able to capture rich dependencies in data, offering a powerful means of estimating these probabilities and hence an avenue towards more effective…
Zhimin Li, Harshitha Menon, Charles Jekel, Valerio Pascucci + 1 more
Neural networks are used as generative surrogate models for scientific discovery, which are trainable approximations of scientific simulations. These models enable users to replace time-consuming numerical simulations with learned alternatives, providing quick solutions. However, high-fidelity generative surrogate…
Ye, Zhijing, Di, Sheng + 8 more
Federated learning (FL) enables collaborative model training without exposing clients' private data, but its deployment is often constrained by the communication cost of transmitting gradients between clients and the central server, especially under system heterogeneity where low-bandwidth clients bottleneck overall…
Marek Kokot, Amitava Roy, Travis J Wheeler, Sebastian Deorowicz
Molecular dynamics (MD) simulations model the physical movements of atoms in biomolecular systems over time, providing atomic-resolution insight into conformational changes, binding events, and dynamic behaviors that cannot be captured by static structures alone. As such, MD simulations are playing an increasingly…
Shang Wu, David C. Wong, Jiandong Wang, Yuzhi Jin + 2 more
The rapid growth of data volumes from high-resolution regional climate simulations necessitates effective storage reduction strategies that do not compromise scientific integrity. Applying lossy precision reduction prior to lossless compression provides a promising approach. However, the distinct scientific…
Vojtech Macala, Petr Simecek
Lossless compression and probabilistic sequence modeling are two faces of the same coin: a model that assigns high probability to a sequence can encode it in few bits via arithmetic coding. We exploit this duality to evaluate genomic language models as compressors of DNA, using compression primarily as an objective…
Veronika Hendrychová, Karel Břinda
One important question in bacterial genomics is how to represent and search modern million-genome collections at scale. Phylogenetic compression effectively addresses this by guiding compression and search via evolutionary history, and many related methods similarly rely on tree- and ordering-based heuristics that…
Sibusiso B. Buthelezi, Jules R. Tapamo, Nikolaos Mitianoudis
We present a hybrid end-to-end learned image compression framework that combines a CNN-based variational autoencoder (VAE) with an efficient hierarchical Swin Transformer to address the limitations of existing entropy models in capturing global dependencies under computational constraints. Traditional VAE-based codecs…
Zhening Liu, Rui Song, Yushi Huang, Yingdong Hu + 4 more
3D Gaussian Splatting (3DGS) has emerged as a revolutionary 3D representation. However, its substantial data size poses a major barrier to widespread adoption. While feed-forward 3DGS compression offers a practical alternative to costly per-scene per-train compressors, existing methods struggle to model long-range…
Yanlong Gao, Haiming Xu, Wei Huang, Hao Bai + 3 more
With the extensive applications of satellite image data in environmental monitoring and geographic surveying and mapping, the amount of data has increased rapidly, which brings great challenges for transmitting and storing these images. However, when processing high-resolution and multi-spectral satellite data…
Binmei Liu, Shiwan Zhou, Jing Sun, Xiaojuan Liu + 2 more
The rapid development of digital media demands higher quality in pattern design. Simultaneously, significant redundant information hinders the transmission and sharing of these patterns, creating an urgent need for image compression. However, traditional image compression methods struggle to balance efficiency and…
Satanik Mukherjee, Raphaelle Lesage, Liesbet Geris
Mechanical loading regulates chondrocyte health in articular cartilage. While physiological stimuli maintain homeostasis, supra-physiological stimuli from joint injuries disrupt it, leading to osteoarthritis (OA). OA is a prevalent degenerative joint disease affecting millions worldwide. OA progression involves complex…
Authors not listed
Supervised deep learning has become a standard approach to deliver competitive predictive tools that allow relating the structure of molecules and their physicochemical features to properties such as binding to protein targets, performance as electronic materials, and reactivity. However, efforts to understand how…
Authors not listed
Understanding the complex chemistry of organic materials under dynamic compression is important for many applications, but is challenging due to the large number of reactions occurring at various time scales. Here, we develop a machine learning potential based on Chebyshev polynomials to study the insensitive energetic…
Birte Boes, Jaan-Willem Simon, Hagen Holthusen, Ellen Kuhl
Tofu remains one of the world’s most important plant-based foods, famous for its cultural legacy, nutritional benefits, and environmental sustainability. Made up of only two ingredient–soy beans and water–it has nourished people for centuries; yet, its rheology remains incompletely understood. Here, we use tofu as a…
Authors not listed
Ni40Co20Fe10Cr10Al18W2 additively manufactured using laser powder bed fusion (LPBF) is among the toughest as-built alloys reported and is a promising candidate for use in extreme environments. However, its behavior under multi-megabar pressure regimes remains unexplored. We used femtosecond in situ X-ray diffraction to…