Related papers: StarWhisper Telescope: An AI framework for automat…
We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for…
In recent decades, astronomy and astrophysics have experienced several fundamental changes. On one hand, there has been a significant increase in the observation of transient phenomena, which are short-lived events such as supernova…
We present the first public release of our generic neural network training algorithm, called SkyNet. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for…
Robo-AO is the first autonomous laser adaptive optics system and science instrument operating on sky. With minimal human oversight, the system robotically executes large scale surveys, monitors long-term astrophysical dynamics and…
Observatories are complex scientific and technical institutions serving diverse users and purposes. Their telescopes, instruments, software, and human resources engage in interwoven workflows over a broad range of timescales. These…
As AI technology advances, it is driving innovation across industries, increasing the demand for scalable AI project deployment. However, deployment remains a critical challenge due to complex environment configurations, dependency…
As new large-scale astronomical surveys greatly increase the number of objects targeted and discoveries made, the requirement for efficient follow-up observations is crucial. Adaptive optics imaging, which compensates for the image-blurring…
Large-scale astronomical image data processing and prediction are essential for astronomers, providing crucial insights into celestial objects, the universe's history, and its evolution. While modern deep learning models offer high…
Our paper introduces a generative, multiagent AI framework designed to overcome the rigidity, limited flexibility and technical barriers of current bibliometric tools. The objective is to enable researchers to perform fully dynamic,…
The field of time-domain astronomy has experienced unprecedented growth due to the increasing deployment of robotic telescopes capable of autonomous, round-the-clock sky monitoring. These instruments have revolutionized the detection and…
The history of science is punctuated by serendipitous discoveries, where unexpected observations, rather than targeted hypotheses, opened new fields of inquiry. While modern autonomous laboratories excel at accelerating hypothesis testing,…
Astronomical research has long relied on human expertise to interpret complex data and formulate scientific hypotheses. In this study, we introduce Mephisto -- a multi-agent collaboration framework powered by large language models (LLMs)…
Human-computer symbiosis is a crucial direction for the development of artificial intelligence. As intelligent systems become increasingly prevalent in our work and personal lives, it is important to develop strategies to support users…
Modern science is reaching a critical inflection point. Instruments across disciplines, from particle physics and astronomy to genomics and climate modeling, now produce data of such scale, diversity, and interdependence that traditional…
The Five-hundred-meter Aperture Spherical Telescope (FAST), the world's largest single-dish radio telescope, lists the search for extraterrestrial intelligence (SETI) as one of its key scientific objectives. In this work, we present a…
In the rapidly advancing research fields such as AI, managing and staying abreast of the latest scientific literature has become a significant challenge for researchers. Although previous efforts have leveraged AI to assist with literature…
Robo-AO is the first astronomical laser guide star adaptive optics (AO) system designed to operate completely independent of human supervision. A single computer commands the AO system, the laser guide star, visible and near-infrared…
Existing approaches to monitoring AI agents rely on supervised evaluation: human-written rules or LLM-based judges that check for known failure modes. However, novel misbehaviors may fall outside predefined categories entirely and LLM-based…
Agentic AI is rapidly transforming the way research is conducted, from prototyping ideas to reproducing results found in the literature. In this paper, we explore the ability of agentic AI to autonomously design wireless communication…
Artificial intelligence (AI) models trained on published scientific findings have been used to invent valuable materials and targeted therapies, but they typically ignore the human scientists who continually alter the landscape of…