Related papers: TransFit: An Efficient Framework for Transient Lig…
Next-generation solar spectrographs increasingly record dense wavelength windows in which tens to hundreds of spectral lines are sampled at each spatial location and time step. This expands the scope for multi-line, multi-height diagnostics…
Besides their huge technological importance, fluidized beds have attracted a large amount of research because they are perfect playgrounds to investigate highly dynamic particulate flows. Their over-all behavior is determined by…
The paper presents a model reduction framework geared towards the analysis and design of systems that switch and oscillate. While such phenomena are ubiquitous in nature and engineering, model reduction methods are not well developed for…
Transient detection and flux measurement via image subtraction stand at the base of time domain astronomy. Due to the varying seeing conditions, the image subtraction process is non-trivial, and existing solutions suffer from a variety of…
Diffusion models have proven to be highly effective in generating high-quality images. However, adapting large pre-trained diffusion models to new domains remains an open challenge, which is critical for real-world applications. This paper…
Increasingly, homeowners opt for photovoltaic (PV) systems and/or battery storage to minimize their energy bills and maximize renewable energy usage. This has spurred the development of advanced control algorithms that maximally achieve…
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for…
We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for effective lighting transfer. Given a source image and a target lighting image, LumiNet synthesizes a relit version of the…
Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise…
In recent years, a variety of ML architectures and techniques have seen success in producing skillful medium range weather forecasts. In particular, Vision Transformer (ViT)-based models (e.g. Pangu-Weather, FuXi) have shown strong…
The ongoing optical time-domain astronomy surveys are routinely reporting fifty transient candidates per night. Here, I investigate the demographics of astronomical transients and supernova classifications reported to the Transient Name…
We present an imaging and neural rendering technique that seeks to synthesize videos of light propagating through a scene from novel, moving camera viewpoints. Our approach relies on a new ultrafast imaging setup to capture a first-of-its…
This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed…
Astrophysical light curves are particularly challenging data objects due to the intensity and variety of noise contaminating them. Yet, despite the astronomical volumes of light curves available, the majority of algorithms used to process…
In the past decades, numerous heat conduction models beyond Fourier have been developed to account for the large gradients, fast phenomena, wave propagation, or heterogeneous material structure, such as being typical for biological systems,…
Accurate medical image segmentation requires both long-range contextual reasoning and precise boundary delineation, a task where existing transformer- and diffusion-based paradigms are frequently bottlenecked by quadratic computational…
Temporal sampling does more than add another axis to the vector of observables. Instead, under the recognition that how objects change (and move) in time speaks directly to the physics underlying astronomical phenomena, next-generation…
Machine-learning models in high-energy physics are often trained on simulated data, where fully simulated samples are computationally expensive while fast simulation provides large statistics at reduced realism. In this work, we…
Weather recognition is an essential support for many practical life applications, including traffic safety, environment, and meteorology. However, many existing related works cannot comprehensively describe weather conditions due to their…
Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity. We ask whether this principle remains useful after images…