Related papers: FASTR: Reimagining FASTQ via Compact Image-inspire…
The split-inference paradigm divides an artificial intelligence (AI) model into two parts. This necessitates the transfer of intermediate feature data between the two halves. Here, effective compression of the feature data becomes vital. In…
Molecular dynamics simulations yield large amounts of trajectory data. For their durable storage and accessibility an efficient compression algorithm is paramount. State of the art domain-specific algorithms combine quantization, Huffman…
Synchrosqueezing transform (SST) is a useful tool for vibration signal analysis due to its high time-frequency (TF) concentration and reconstruction properties. However, existing SST requires much processing time for large-scale data. In…
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…
Foerster Resonance Energy Transfer (FRET) allows for the visualization of nanometer-scale distances and distance changes. This sensitivity is regularly achieved in single-molecule experiments in vitro but is still challenging in biological…
We present an extremely simple Ultra-Resolution Style Transfer framework, termed URST, to flexibly process arbitrary high-resolution images (e.g., 10000x10000 pixels) style transfer for the first time. Most of the existing state-of-the-art…
This work introduces a compact and hardware efficient method for compressing color images using near term quantum devices. The approach segments the image into fixed size blocks called bixels, and computes the total intensity within each…
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements. Due to these factors, it has become the norm for modern graphics-heavy websites to…
Tensor algebra is a crucial component for data-intensive workloads such as machine learning and scientific computing. As the complexity of data grows, scientists often encounter a dilemma between the highly specialized dense tensor algebra…
Hyperspectral neutron computed tomography is a tomographic imaging technique in which thousands of wavelength-specific neutron radiographs are measured for each tomographic view. In conventional hyperspectral reconstruction, data from each…
While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computational efficiency and memory usage in both prefill and…
One-step diffusion-based image super-resolution (OSDSR) models are showing increasingly superior performance nowadays. However, although their denoising steps are reduced to one and they can be quantized to 8-bit to reduce the costs…
Processing sequential data of variable length is a major challenge in a wide range of applications, such as speech recognition, language modeling, generative image modeling and machine translation. Here, we address this challenge by…
Referring image segmentation is an advanced semantic segmentation task where target is not a predefined class but is described in natural language. Most of existing methods for this task rely heavily on convolutional neural networks, which…
Since only a small number of traces generated from distributed tracing helps in troubleshooting, its storage requirement can be significantly reduced by biasing the selection towards anomalous traces. To aid in this scenario, we propose…
Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple…
Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error. The root cause lies in the Hessian…
Quantum computers have rapidly improved in scale and fidelity, yet access to large systems remains limited for most researchers. This makes accurate and scalable noisy quantum simulation essential. While density matrix simulation provides…
Scientific applications produce vast amounts of data, posing grand challenges in the underlying data management and analytic tasks. Progressive compression is a promising way to address this problem, as it allows for on-demand data…
The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various…