Related papers: Transformer Embeddings for Fast Microlensing Infer…
Event cameras have higher temporal resolution, and require less storage and bandwidth compared to traditional RGB cameras. However, due to relatively lagging performance of event-based approaches, event cameras have not yet replace…
Imaging phantoms are test patterns used to measure image quality in computer tomography (CT) systems. A new phantom platform (Mercury Phantom, Gammex) provides test patterns for estimating the task transfer function (TTF) or noise power…
Characterizing the interior structure of exoplanets is an inverse problem often solved using Bayesian inference, but this approach is hampered by the high computational cost of planetary structure models. To overcome this barrier, we…
Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training…
The WFIRST microlensing mission will measure precise light curves and relative parallaxes for millions of stars, giving it the potential to characterize short-period transiting planets all along the line of sight and into the galactic…
We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup. Our method consists of two distinct components, one of which focuses on…
Recovering the physical attributes of an object's appearance from its images captured under an unknown illumination is challenging yet essential for photo-realistic rendering. Recent approaches adopt the emerging implicit scene…
This paper presents a new C++ framework, DELPHES, performing a fast multipurpose detector response simulation. The simulation includes a tracking system, embedded into a magnetic field, calorimeters and a muon system, and possible very…
We present a novel method for local image feature matching. Instead of performing image feature detection, description, and matching sequentially, we propose to first establish pixel-wise dense matches at a coarse level and later refine the…
We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,\mu$s using convolutional…
In the era of the James Webb Space Telescope (JWST), the dramatic improvement in the spectra of exoplanetary atmospheres demands a corresponding leap forward in our ability to analyze them: atmospheric retrievals need to be performed on…
A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transformer-based language…
Transformers have achieved superior performances in many tasks in natural language processing and computer vision, which also triggered great interest in the time series community. Among multiple advantages of Transformers, the ability to…
Face clustering is a useful tool for applications like automatic face annotation and retrieval. The main challenge is that it is difficult to cluster images from the same identity with different face poses, occlusions, and image quality.…
One of most important applications of microlensing observations is detecting free-floating planets(FFPs). The time scale of microlensing due to FFPs ($t_{\rm E}$) is short (a few days). Discerning the annual parallax effect in observations…
While optical surveys regularly discover slow transients like supernovae on their own, the most common way to discover extragalactic fast transients, fading away in a few nights, is via follow-up observations of gamma-ray burst and…
The current data acquisition rate of astronomical transient surveys and the promise for significantly higher rates during in the next decade necessitate the development of novel approaches to analyze astronomical data sets and promptly…
We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling. As telescopes and simulations rapidly expand the volume and resolution of astrophysical data, fast simulation-based…
Interpreting the observations of exoplanet atmospheres to constrain physical and chemical properties is typically done using Bayesian retrieval techniques. Because these methods require many model computations, a compromise is made between…
Recent Transformer-based large language models (LLMs) demonstrate in-context learning ability to perform various functions based solely on the provided context, without updating model parameters. To fully utilize the in-context capabilities…