Related papers: Transformer Embeddings for Fast Microlensing Infer…

Gravitational lensing is one of the most powerful probes of dark matter, yet creating high-fidelity lensed images at scale remains a bottleneck. Existing tools rely on ray-tracing or forward-modeling pipelines that, while precise, are…

This paper presents GPFC, a novel Graphics Processing Unit (GPU) Phase Folding and Convolutional Neural Network (CNN) system to detect exoplanets using the transit method. We devise a fast folding algorithm parallelized on a GPU to amplify…

The global and local contexts significantly contribute to the integrity of predictions in Salient Object Detection (SOD). Unfortunately, existing methods still struggle to generate complete predictions with fine details. There are two major…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

Transformers have been widely applied in text classification. Unfortunately, real-world data contain anomalies and noisy labels that cause challenges for state-of-art Transformers. This paper proposes Protoformer, a novel self-learning…

Temporal Forgery Localization (TFL) aims to precisely identify manipulated segments in video and audio, offering strong interpretability for security and forensics. While recent State Space Models (SSMs) show promise in precise temporal…

In this study, we present a transformer-based multi-task model for Fast Radio Burst (FRB) detection, signal segmentation, and parameter estimation directly from time-frequency data, without requiring computationally expensive de-dispersion…

Microlensing can be used to discover exoplanets of a wide range of masses with orbits beyond ~ 1 AU, and even free-floating planets. The WFIRST mission will use microlensing to discover approximately 1600 planets by monitoring ~100 million…

Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain…

Bayesian clustering accounts for uncertainty but is computationally demanding at scale. Furthermore, real-world datasets often contain missing values, and simple imputation ignores the associated uncertainty, resulting in suboptimal…

We report the application of implicit likelihood inference to the prediction of the macro-parameters of strong lensing systems with neural networks. This allows us to perform deep learning analysis of lensing systems within a well-defined…

This paper addresses the task of anomaly diagnosis when the underlying data generation process has a complex spatio-temporal (ST) dependency. The key technical challenge is to extract actionable insights from the dependency tensor…

Transformers have reached remarkable success in sequence modeling. However, these models have efficiency issues as they need to store all the history token-level representations as memory. We present Memformer, an efficient neural network…

Collaborative path planning for robot swarms in complex, unknown environments without external positioning is a challenging problem. This requires robots to find safe directions based on real-time environmental observations, and to…

This paper investigates fake news detection as a downstream evaluation of Transformer representations, benchmarking encoder-only and decoder-only pre-trained models (BERT, GPT-2, Transformer-XL) as frozen embedders paired with lightweight…

The extended source effect on microlensing magnification is non-negligible and must be taken into account for in an analysis of microlensing. However, the evaluation of the extended source magnification is numerically expensive because it…

Fingerprint feature extraction is a task that is solved using either a global or a local representation. State-of-the-art global approaches use heavy deep learning models to process the full fingerprint image at once, which makes the…

The detection and atmospheric characterization of potentially habitable, temperate terrestrial exoplanets using a space-based mid-infrared nulling interferometer is a major goal of contemporary astrophysics. A central part of the analysis…

Many real-world time series exhibit strong periodic structures arising from physical laws, human routines, or seasonal cycles. However, modern deep forecasting models often fail to capture these recurring patterns due to spectral bias and a…

Flow-based generative modeling is a powerful tool for solving inverse problems in physical sciences that can be used for sampling and likelihood evaluation with much lower inference times than traditional methods. We propose to refine flows…