Related papers: Regularized Residual Quantization: a multi-layer s…

Large language models (LLMs) have revolutionized natural language processing, albeit at the cost of immense memory and computation requirements. Post-training quantization (PTQ) is becoming the de facto method to reduce the memory footprint…

Reservoir computing (RC) is an effective method for predicting chaotic systems by using a high-dimensional dynamic reservoir with fixed internal weights, while keeping the learning phase linear, which simplifies training and reduces…

State-of-the-art deep neural networks are trained with large amounts (millions or even billions) of data. The expensive computation and memory costs make it difficult to train them on limited hardware resources, especially for recent…

Sparsity-based methods have a long history in the field of signal processing and have been successfully applied to various image reconstruction problems. The involved sparsifying transformations or dictionaries are typically either…

Since the first success of Dong et al., the deep-learning-based approach has become dominant in the field of single-image super-resolution. This replaces all the handcrafted image processing steps of traditional sparse-coding-based methods…

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

Recurrence quantification analysis (RQA) is a widely used tool for studying complex dynamical systems, but its standard implementation requires computationally expensive calculations of recurrence plots (RPs) and line length histograms.…

Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conversion. Existing model…

Quantum Reservoir Computing (QRC) leverages the natural dynamics of quantum systems for information processing, without requiring a fault-tolerant quantum computer. In this work, we apply QRC within a hybrid quantum classical framework for…

Signal models based on sparse representations have received considerable attention in recent years. On the other hand, deep models consisting of a cascade of functional layers, commonly known as deep neural networks, have been highly…

Methods based on weight compensation, which iteratively apply quantization and weight compensation to minimize the output error, have recently demonstrated remarkable success in quantizing Large Language Models (LLMs). The representative…

Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, and related preconditioners usually impose structural approximations early, often…

We present an adaptive regularization algorithm that can be effectively applied to the optimization problem in deep learning framework. Our regularization algorithm aims to take into account the fitness of data to the current state of model…

Diffusion models have been achieving remarkable performance in face restoration. However, the heavy computations hamper the widespread adoption of these models. In this work, we propose QuantFace, a novel low-bit quantization framework for…

Super-resolution (SR) applied to real-world low-resolution (LR) images often results in complex, irregular degradations that stem from the inherent complexity of natural scene acquisition. In contrast to SR artifacts arising from synthetic…

Quantum computing is a promising candidate for accelerating machine learning tasks. Limited by the control accuracy of current quantum hardware, reducing the consumption of quantum resources is the key to achieving quantum advantage. Here,…

Cross-resolution face recognition has become a challenging problem for modern deep face recognition systems. It aims at matching a low-resolution probe image with high-resolution gallery images registered in a database. Existing methods…

Discrete image tokenization is a key bottleneck for scalable visual generation: a tokenizer must remain compact for efficient latent-space priors while preserving semantic structure and using discrete capacity effectively. Existing…

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks…