arXiv subjects

Yixuan Cheng

Publications and source records attributed to Yixuan Cheng.

4 recordsLinked to original sources

arXiv2026

Identifying Scientifically Interesting Galaxies with Vision-Language Models

Anomaly searches in large astronomical image datasets aim to identify rare objects for follow-up investigation. Yet the objects that are most statistically unusual are not necessarily those of greatest scientific relevance. We investigate whether pretrained vision-language models can directly assess scientific interest from natural-language instructions, enabling galaxy images to be ranked without labeled examples. We evaluate models on a 20,000-image Hubble Space Telescope sample that includes 167 reference anomalies previously identified through machine learning and expert inspection. By scoring images for scientific interest, Gemini 3.1 Flash-Lite places 98.2% of the reference anomalies within the highest-ranked ~2,000 images, at a present-day inference cost of approximately $5.05 per 10,000 images. We recover known gravitational lenses, jellyfish-galaxy candidates, and galaxies with visible jets, and release 102 high-scoring candidates for further investigation. These results show that an off-the-shelf vision-language model, without any training on the target data, offers a practical way to rank large image datasets by scientific relevance rather than rarity. The project code is available at https://github.com/TheCheng2005/Galaxy-Anomaly-Search/

astro-ph.IM↗

arXiv2026

Prototyping the Next-Generation Spectrograph for Space Exploration: Digital Micromirror Device-based Multi-Object Spectrograph (DMD-MOS) Calibration and Performance Assessment

Abandoning the traditional approaches to multi-object spectrographs, the Digital Micro-mirror Device-based Multi-Object Spectrograph (DMD-MOS) leverages a robust, elegant method for creating multi-object spectroscopy slit masks through use of a DMD, which is an array of microscopic flat mirrors where each micro-mirror can be addressed to physically flip between two discrete angles. We have designed two optical channels for DMD-MOS - one for each of these two positions: 1) an imaging channel that can be used for multi-object target selection and 2) a spectrograph channel. Using this two-channel approach, DMD-MOS can simultaneously image the telescope field of view (FOV) with the imaging channel and actuate the specific DMD micro-mirrors to send light from chosen targets into the spectrograph channel. In this work, we present the results of our laboratory testing of DMD-MOS including spectral resolution, line spread function, wavelength coverage, and the mapping between the DMD and imaging channel planes, the latter of which enables DMD-MOS and our control software to instantaneously configure the DMD to observe chosen target(s) in the acquisition field.

astro-ph.IM↗

arXiv2026

DDT: A Dual-Masking Dual-Expert Transformer for Energy Time-Series Forecasting

Accurate energy time-series forecasting is crucial for ensuring grid stability and promoting the integration of renewable energy, yet it faces significant challenges from complex temporal dependencies and the heterogeneity of multi-source data. To address these issues, we propose DDT, a novel and robust deep learning framework for high-precision time-series forecasting. At its core, DDT introduces two key innovations. First, we design a dual-masking mechanism that synergistically combines a strict causal mask with a data-driven dynamic mask. This novel design ensures theoretical causal consistency while adaptively focusing on the most salient historical information, overcoming the rigidity of traditional masking techniques. Second, our architecture features a dual-expert system that decouples the modeling of temporal dynamics and cross-variable correlations into parallel, specialized pathways, which are then intelligently integrated through a dynamic gated fusion module. We conducted extensive experiments on 7 challenging energy benchmark datasets, including ETTh, Electricity, and Solar. The results demonstrate that DDT consistently outperforms strong state-of-the-art baselines across all prediction horizons, establishing a new benchmark for the task.

cs.LG↗

arXiv2025

A Path to Resource Optimization and Technological Innovation: Advancing Space and Climate Research with Bidirectional Technologies

This paper introduces Bidirectional Technologies (BiTs), which is defined as technology that addresses the challenges within the aerospace and climate sectors simultaneously. BiTs presents a means to meet global development agendas, in particular, the United Nations 2030 Agenda for Sustainable Development and the Space2030 Agenda. These frameworks position aerospace innovations as tools to address climate change, explicitly highlighting the shared challenges between both fields. This overlap presents an underexplored opportunity to develop BiTs. To explore this potential, the study conducts an extensive literature review to examine the challenges within four categories in both Earth and space contexts: life support, energy systems, monitoring and exploratory systems, and novel technologies. Key traits that influence the successful development of BiTs are then extracted. Based on these traits, a set of actionable recommendations is proposed to serve as a starting point for policymakers and engineers to adapt technologies beyond single-domain applications. Ultimately, this study presents BiTs as a solution to the interconnected challenges on Earth and in space, offering strategies that advance innovation while contributing to global sustainability efforts.

physics.soc-ph↗