Related papers: ProductAE: Toward Deep Learning Driven Error-Corre…

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…

Faced with continuously increasing scale of data, original back-propagation neural network based machine learning algorithm presents two non-trivial challenges: huge amount of data makes it difficult to maintain both efficiency and…

Entanglement-assisted quantum error correcting codes (EAQECCs) are a simple and fundamental class of codes. They allow for the construction of quantum codes from classical codes by relaxing the duality condition and using pre-shared…

Code editing encompasses a variety of pragmatic tasks that developers deal with daily. Despite its relevance and practical usefulness, automatic code editing remains an underexplored area in the evolution of deep learning models, partly due…

Existing vision-language models (VLMs) mostly rely on vision encoders to extract visual features followed by large language models (LLMs) for visual-language tasks. However, the vision encoders set a strong inductive bias in abstracting…

Generalizing learned representations across significantly different visual domains is a fundamental yet crucial ability of the human visual system. While recent self-supervised learning methods have achieved good performances with…

Domain shift is a problem commonly encountered when developing automated histopathology pipelines. The performance of machine learning models such as convolutional neural networks within automated histopathology pipelines is often…

VQ-VAE, as a mainstream approach of speech tokenizer, has been troubled by ``index collapse'', where only a small number of codewords are activated in large codebooks. This work proposes product-quantized (PQ) VAE with more codebooks but…

Quantum error correction (QEC) is essential for scalable quantum computing. However, it requires classical decoders that are fast and accurate enough to keep pace with quantum hardware. While quantum low-density parity-check codes have…

We show that a Modular Neural Network (MNN) can combine various speech enhancement modules, each of which is a Deep Neural Network (DNN) specialized on a particular enhancement job. Differently from an ordinary ensemble technique that…

Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…

An autoencoder (AE) is a neural network that, using self-supervised training, learns a succinct parameterized representation, and a corresponding encoding and decoding process, for all instances in a given class. Here, we introduce the…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

In one-class novelty detection, a model learns solely on the in-class data to single out out-class instances. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, thus differentiating the…

Auto-encoder is a special kind of neural network based on reconstruction. De-noising auto-encoder (DAE) is an improved auto-encoder which is robust to the input by corrupting the original data first and then reconstructing the original…

Deep learning on graphs has become a popular research topic with many applications. However, past work has concentrated on learning graph embedding tasks, which is in contrast with advances in generative models for images and text. Is it…

With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are…

Deep learning has received much attention lately due to the impressive empirical performance achieved by training algorithms. Consequently, a need for a better theoretical understanding of these problems has become more evident in recent…

Machine learning algorithms are typically run on large scale, distributed compute infrastructure that routinely face a number of unavailabilities such as failures and temporary slowdowns. Adding redundant computations using coding-theoretic…

Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks. However, current instruction tuning methods for Code LLMs…