Related papers: Masked Generative Modeling with Enhanced Sampling …

Speech enhancement remains challenging due to the trade-off between efficiency and perceptual quality. In this paper, we introduce MAGE, a Masked Audio Generative Enhancer that advances generative speech enhancement through a compact and…

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized…

Generative self-supervised learning (SSL), especially masked autoencoders, has become one of the most exciting learning paradigms and has shown great potential in handling graph data. However, real-world graphs are always heterogeneous,…

Recurrent neural networks have been widely used to generate millions of de novo molecules in a known chemical space. These deep generative models are typically setup with LSTM or GRU units and trained with canonical SMILEs. In this study,…

Tagging based methods are one of the mainstream methods in relational triple extraction. However, most of them suffer from the class imbalance issue greatly. Here we propose a novel tagging based model that addresses this issue from…

Referring Expression Segmentation (RES), which is aimed at localizing and segmenting the target according to the given language expression, has drawn increasing attention. Existing methods jointly consider the localization and segmentation…

The main goal of our research is to develop an effective method with a wide range of applications for the statistical reconstruction of heterogeneous microstructures with compact inclusions of any shape, such as highly irregular grains. The…

Referring expression segmentation (RES), a task that involves localizing specific instance-level objects based on free-form linguistic descriptions, has emerged as a crucial frontier in human-AI interaction. It demands an intricate…

Multivariate time series (MTS) data, when sampled irregularly and asynchronously, often present extensive missing values. Conventional methodologies for MTS analysis tend to rely on temporal embeddings based on timestamps that necessitate…

Sampling is a fundamental technique, and sampling without replacement is often desirable when duplicate samples are not beneficial. Within machine learning, sampling is useful for generating diverse outputs from a trained model. We present…

In quantum many-body systems, measurements can induce qualitative new features, but their simulation is hindered by the exponential complexity involved in sampling the measurement results. We propose to use machine learning to assist the…

The absence of large-scale masked face datasets challenges masked face detection and recognition. We propose a two-step generative data augmentation framework combining rule-based mask warping with unpaired image-to-image translation via…

Given the abundance of unlabeled Satellite Image Time Series (SITS) and the scarcity of labeled data, contrastive self-supervised pretraining emerges as a natural tool to leverage this vast quantity of unlabeled data. However, designing…

Point-based interactive image segmentation can ease the burden of mask annotation in applications such as semantic segmentation and image editing. However, fully extracting the target mask with limited user inputs remains challenging. We…

Retrieval-Augmented Generation (RAG) systems are increasingly vital for navigating the ever-expanding body of scientific literature, particularly in high-stakes domains such as chemistry. Despite the promise of RAG, foundational design…

Anomaly detection is widely used in network intrusion detection, autonomous driving, medical diagnosis, credit card frauds, etc. However, several key challenges remain open, such as lack of ground truth labels, presence of complex temporal…

Many promising applications of supervised machine learning face hurdles in the acquisition of labeled data in sufficient quantity and quality, creating an expensive bottleneck. To overcome such limitations, techniques that do not depend on…

Test-Time Adaptation (TTA) via entropy minimization (EM) has proven effective for classification tasks, yet its application to generative autoregressive models remains theoretically fragmented. Existing approaches typically rely on distinct…

Recent advances in Bayesian models for random partitions have led to the formulation and exploration of Exchangeable Sequences of Clusters (ESC) models. Under ESC models, it is the cluster sizes that are exchangeable, rather than the…

Unsupervised outlier detection is attractive because it eliminates the need for labeled data. Moreover, forming multi-model ensembles can improve detection robustness. However, composing an ensemble without labeled data is challenging.…