Related papers: SOAR: Scale Optimization for Accurate Reconstructi…

Deep learning has been used to image compressive sensing (CS) for enhanced reconstruction performance. However, most existing deep learning methods train different models for different subsampling ratios, which brings additional hardware…

We investigate the reconstruction of multivariate functions from samples using sparse recovery techniques. For Square Root Lasso, Orthogonal Matching Pursuit, and Compressive Sampling Matching Pursuit, we demonstrate both theoretically and…

This retrospective-prospective study evaluated whether a deep learning-based MRI reconstruction algorithm can preserve diagnostic quality in brain MRI scans accelerated up to fourfold, using both public and prospective clinical data. The…

Supervised fine-tuning is a standard method for adapting pre-trained large language models (LLMs) to downstream tasks. Quantization has been recently studied as a post-training technique for efficient LLM deployment. To obtain quantized…

While the deep learning techniques promote the rapid development of the speech enhancement (SE) community, most schemes only pursue the performance in a black-box manner and lack adequate model interpretability. Inspired by Taylor's…

Neural Radiance Field (NeRF) has emerged as a promising 3D reconstruction method, delivering high-quality results for AR/VR applications. While quantization methods and hardware accelerators have been proposed to enhance NeRF's…

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into individual layer-wise sub-problems, and minimizing per-layer…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Existing hologram super-resolution (HSR) methods primarily focus on angle-of-view expansion. Adapting them for volumetric spatial up-sampling introduces severe quadratic depth distortion, degrading 3D focal accuracy. We propose CV-HoloSR, a…

Stochastic First-Order (SFO) methods have been a cornerstone in addressing a broad spectrum of modern machine learning (ML) challenges. However, their efficacy is increasingly questioned, especially in large-scale applications where…

We introduce SMURF, a scalable and unsupervised machine learning method for simultaneously segmenting vascular geometries and reconstructing velocity fields from 4D flow MRI data. SMURF models geometry and velocity fields using multilayer…

Extremely low-bit quantization is critical for efficiently deploying Large Language Models (LLMs), yet it often leads to severe performance degradation at 2 bits and even at 4 bits (e.g., MXFP4). We present SignRoundV2, a post-training…

In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of stereo matching at…

Inference optimizations such as quantization, pruning, format and datatype conversion, model export, and serialization can lead to functional degradations in language model task performance. While most efforts on performance recovery for…

We develop fast spectral algorithms for tensor decomposition that match the robustness guarantees of the best known polynomial-time algorithms for this problem based on the sum-of-squares (SOS) semidefinite programming hierarchy. Our…

Label noise is a common issue in real-world datasets that inevitably impacts the generalization of models. This study focuses on robust classification tasks where the label noise is instance-dependent. Estimating the transition matrix…

With the rapid increase in the size of neural networks, model compression has become an important area of research. Quantization is an effective technique at decreasing the model size, memory access, and compute load of large models.…

The increasing computational demands of foundation models have spurred research into low-precision training, with 4-bit floating-point (\texttt{FP4}) formats emerging as a frontier for maximizing hardware throughput. While numerous…

Development of optical technology has enabled imaging of two-dimensional (2D) sound fields. This acousto-optic sensing enables understanding of the interaction between sound and objects such as reflection and diffraction. Moreover, it is…

Model quantization reduces the bit-width of weights and activations, improving memory efficiency and inference speed in diffusion models. However, achieving 4-bit quantization remains challenging. Existing methods, primarily based on…