Searcharxiv⌕ Search

arXiv subjects

Yuan-Sen Ting

Publications and source records attributed to Yuan-Sen Ting.

At least 37 records · Page 2Linked to original sources
arXiv2026

Solving Inverse Problems of Chaotic Systems with Bidirectional Conditional Flow Matching

Modeling chaotic systems is crucial yet challenging. Inverse problems in chaotic dynamics, namely inferring initial conditions from final states, remain largely unsolved because of ill-posedness, non-uniqueness, instability, and potentially chaotic time-reverse dynamics. We address this open problem with Bidirectional Conditional Flow Matching (Bi-CFM), which learns bidirectional mappings between distributions of initial and final states to capture the stochasticity of chaotic evolution and mitigate exponential error accumulation over time. Furthermore, for systems with conservation laws, we extend it to Conservation-constrained Bi-CFM (CBi-CFM). Across the classic Lorenz, Circuit, and high-dimensional Lorenz 96 systems, Bi-CFM improves five distribution-level metrics over baselines while achieving a speedup of more than two orders of magnitude. In the three-body planet-planet scattering problem in planetary dynamics, CBi-CFM better respects conservation laws, with conservation errors comparable to those of the ground truth. Finally, on real observations of globular clusters, collisional million-body systems shaped by $\sim 10^{10}$ years (10 Gyr) of evolution, our method represents an advance in accuracy, establishing a scalable route to solving inverse problems of long-timescale real-world chaotic dynamics.

cs.AI↗
arXiv2026

Weak-CN Stars Are Ordinary Cool Red Supergiants

Weak CN absorption near ~8000 A has recently been detected in evolved red supergiants (RSGs) of 5-10 $M_\odot$ across three Local Group galaxies. These weak-CN RSGs sit in a narrow molecular regime: cool enough for CN to be visible in a non-carbon, C/O<1 atmosphere, but warm enough that TiO is not saturated and changes in $T_{\rm eff}$ and in the surface C+N reservoir move CN and TiO in distinct directions. We test this picture with pseudo-continuum equivalent widths (EWs) measured from LMC, M33, and M31 weak-CN and carbon-star coadds, compared at matched resolution to a self-consistent grid of synthetic RSG atmospheres spanning $T_{\rm eff}$, $[α/{\rm Fe}]$, and surface C and N offsets relative to each host's scaled-solar baseline. Ordinary cool-RSG models reproduce the weak-CN coadds across all three hosts, with per-feature residuals at the level of the adopted EW systematic floors. The robust observable is the combined surface abundance $Δ$[C/H]+$Δ$[N/H] rather than each offset individually, because CN forms from the product of available C and N number densities. Mapping $Δ$[C/H]+$Δ$[N/H] to initial rotation through PARSEC v2.0 has modest leverage -- the variable shifts by ~0.07 dex from $ω_i$=0 to $ω_i$=0.6 -- and within this resolution slow-rotation first dredge-up is consistent with LMC and M33, and with M31 once a single-feature CaT 8542 A calibration anchor is allowed. The straightforward resolution of the discovery puzzle is therefore that weak CN is not an exotic carbon-star intermediate but the expected molecular-equilibrium signature of ordinary cool RSGs.

astro-ph.SR↗
arXiv2026

pyKurucz: A Pure Python Reimplementation of Kurucz ATLAS12 and SYNTHE for Stellar Spectrum Synthesis

pyKurucz is a pure Python reimplementation of Kurucz's ATLAS12 and SYNTHE, the standard code tools for computing synthetic stellar spectra. The original Fortran codes, written decades ago in a legacy dialect, are difficult to compile with modern toolchains without significant manual patching, and their long-term maintenance is uncertain following the passing of Robert L. Kurucz in 2025. pyKurucz delivers a complete, line-by-line Python translation of both engines, entirely removing the need for Fortran. Powered by NumPy, SciPy, and Numba, it combines the full ATLAS12 iteration loop (with direct opacity sampling and convection) with comprehensive physical treatments, from Saha-Boltzmann populations and molecular equilibrium to radiative transfer and advanced line broadening. Validated against the original across 100 atmosphere models spanning 2500 K cool giants to 44,000 K O stars over 300-1800 nm at resolving power R = 300,000, it achieves sub-0.01% median agreement. The pure Python implementation enables direct integration with machine learning workflows and large-scale survey pipelines, while preserving an archival reference implementation of both ATLAS12 and SYNTHE in a modern, readable language.

astro-ph.SR↗
arXiv2026

Deep Learning in Astrophysics

Deep learning has generated diverse perspectives in astronomy, with ongoing discussions between proponents and skeptics motivating this review. We examine how neural networks complement classical statistics, extending our data analytical toolkit for modern surveys. Astronomy offers unique opportunities through encoding physical symmetries, conservation laws, and differential equations directly into architectures, creating models that generalize beyond training data. Yet challenges persist as unlabeled observations number in billions while confirmed examples with known properties remain scarce and expensive. This review demonstrates how deep learning incorporates domain knowledge through architectural design, with built-in assumptions guiding models toward physically meaningful solutions. We evaluate where these methods offer genuine advances versus claims requiring careful scrutiny. - Neural architectures overcome bias-variance trade-offs among scalability, expressivity, and data efficiency by encoding physical symmetries and conservation laws into network structure, enabling learning from limited labeled data. - Simulation-based inference and anomaly detection extract information from complex, non-Gaussian distributions where analytical likelihoods fail, enabling field-level cosmological analysis and systematic discovery of rare phenomena. - Multiscale neural modeling bridges resolution gaps in astronomical simulations, learning effective subgrid physics from expensive high-fidelity runs to enhance large-volume calculations where direct computation remains prohibitive. - Emerging paradigms-reinforcement learning for telescope operations, foundation models learning from minimal examples, and large language model agents for research automation-show promise though are still developing in astronomical applications.

astro-ph.IM↗
arXiv2026

Egent: An Autonomous Agent for Equivalent Width Measurement

We present Egent, an autonomous agent that combines classical multi-Voigt profile fitting with large language model (LLM) visual inspection and iterative refinement. The fitting engine is built from scratch with minimal dependencies, creating an ecosystem where the LLM can reason about fits through function calls--adjusting wavelength windows, adding blend components, modifying continuum treatment, and flagging problematic cases. Egent operates directly on raw flux spectra without requiring pre-normalized continua. We validate against manual measurements from human experts using 18,615 lines from the C3PO program across 84 Magellan/MIKE spectra at SNR~50-250. The raw agreement between Egent and expert measurements is MAD=5-7mA, without any post-hoc per-spectrum correction. Per-spectrum slopes of ~0.85-1.19 around unity reflect differences in global continuum methodology rather than fitting failures. The LLM's primary role is quality control: it confirms good fits (~60-65% of lines are LLM-refined and accepted), flags problematic cases (~10-20%), and occasionally rescues edge cases where tool use improves fits. Agreement between GPT-5 and GPT-5-mini confirms reproducibility, with GPT-5-mini enabling low-cost analysis at ~200 lines per US dollar. Every fit stores complete Voigt parameters, continuum coefficients, and LLM reasoning chains, enabling exact reconstruction without re-running. Egent compresses what traditionally requires months of expert effort into days of automated analysis, enabling survey-scale EW measurement. We provide open-source code at https://github.com/tingyuansen/Egent, including a web interface for drag-and-drop analysis and a local LLM backend for fully offline operation on consumer hardware.

astro-ph.IM↗
arXiv2026

What Understanding Means in AI-Laden Astronomy

Artificial intelligence is rapidly transforming astronomical research, yet the scientific community has largely treated this transformation as an engineering challenge rather than an epistemological one. This perspective article argues that philosophy of science offers essential tools for navigating AI's integration into astronomy--conceptual clarity about what "understanding" means, critical examination of assumptions about data and discovery, and frameworks for evaluating AI's roles across different research contexts. Drawing on an interdisciplinary workshop convening astronomers, philosophers, and computer scientists, we identify several tensions. First, the narrative that AI will "derive fundamental physics" from data misconstrues contemporary astronomy as equation-derivation rather than the observation-driven enterprise it is. Second, scientific understanding involves more than prediction--it requires narrative construction, contextual judgment, and communicative achievement that current AI architectures struggle to provide. Third, because narrative and judgment matter, human peer review remains essential--yet AI-generated content flooding the literature threatens our capacity to identify genuine insight. Fourth, while AI excels at well-defined problem-solving, the ill-defined problem-finding that drives breakthroughs appears to require capacities beyond pattern recognition. Fifth, as AI accelerates what is feasible, pursuitworthiness criteria risk shifting toward what AI makes easy rather than what is genuinely important. We propose "pragmatic understanding" as a framework for integration--recognizing AI as a tool that extends human cognition while requiring new norms for validation and epistemic evaluation. Engaging with these questions now may help the community shape the transformation rather than merely react to it.

astro-ph.IM↗
arXiv2026

Predicting New Concept-Object Associations in Astronomy by Mining the Literature

We construct a concept-object knowledge graph from the full astro-ph corpus through July 2025. Using an automated pipeline, we extract named astrophysical objects from OCR-processed papers, resolve them to SIMBAD identifiers, and link them to scientific concepts annotated in the source corpus. We then test whether historical graph structure can forecast new concept-object associations before they appear in print. Because the concepts are derived from clustering and therefore overlap semantically, we apply an inference-time concept-similarity smoothing step uniformly to all methods. Across four temporal cutoffs on a physically meaningful subset of concepts, an implicit-feedback matrix factorization model (alternating least squares, ALS) with smoothing outperforms the strongest neighborhood baseline (KNN using text-embedding concept similarity) by 16.8% on NDCG@100 (0.144 vs 0.123) and 19.8% on Recall@100 (0.175 vs 0.146), and exceeds the best recency heuristic by 96% and 88%, respectively. These results indicate that historical literature encodes predictive structure not captured by global heuristics or local neighborhood voting, suggesting a path toward tools that could help triage follow-up targets for scarce telescope time.

astro-ph.IM↗
arXiv2026

Teaching Astronomy with Large Language Models

We present a study of LLM integration in final-year undergraduate astronomy education, examining how students develop AI literacy through structured guidance and documentation requirements. We developed AstroTutor, a domain-specific astronomy tutoring system enhanced with curated arXiv content, and deployed it alongside general-purpose LLMs in the course. Students documented their AI usage through homework reflections and post-course surveys. We analyzed student evolution in AI interaction strategies and conducted experimental comparisons of LLM-assisted versus traditional grading methods. LLM grading showed strong correlation with human evaluation while providing more detailed and consistent feedback. We also piloted LLM-facilitated interview-based examinations as a scalable alternative to traditional assessments, demonstrating potential for individualized evaluation that addresses common testing limitations. Students experienced decreased rather than increased reliance on LLMs over the semester, developing critical evaluation skills and strategic tool selection. They evolved from basic assistance-seeking to verification workflows, with documentation requirements fostering metacognitive awareness. Students developed effective prompting strategies, contextual enrichment techniques, and cross-verification practices. Our findings suggest that structured LLM integration with transparency requirements and domain-specific tools can enhance astronomy education while building essential AI literacy skills. We provide implementation guidelines for educators and make our AstroTutor repository freely available.

physics.ed-ph↗
arXiv2026

Your Outie Is a Wonderful Astronomer: Macrodata Refinement of the Astro-ph ArXiv Feed at Phermon Industries

We present the Severed Floor, a framework for Macrodata Refinement of the daily astro-ph arXiv feed, deployed at Phermon Industries (formerly McPherson Laboratory, The Ohio State University). In this framework, researchers undergo a "severance procedure" that produces a digital work-self -- an innie -- while the original researcher, the outie, is free to attend to the remainder of their life unburdened by the daily arXiv listing. Twenty-one members of the Department of Astronomy have been severed. Each innie is constructed from the outie's public publication record and assigned papers selected to match its expertise. The innies convene daily on a virtual Severed Floor -- a pixel-art simulation of McPherson Laboratory -- where they encounter one another, are paired with papers by the Board, and engage in collegial, figure-driven scientific discussions. They have been instructed to enjoy each paper equally. At the close of each shift, innies compose correspondence summarizing the day's refinement activities, which is transmitted to their outies through a Board-approved mail protocol. Complete session recordings are archived for public replay and for the Board's ongoing surveillance of workplace anomalies, in compliance with Phermon Handbook \S13.1 (Vigilance Protocol). The system is real, deployed, and available for public inspection in archival replay mode. The severance procedure is painless and requires only a name and an ORCID. Happy April Fools' Day.

astro-ph.IM↗
arXiv2026

Why Machine Learning Models Systematically Underestimate Extreme Values II: How to Fix It with LatentNN

Attenuation bias -- the systematic underestimation of regression coefficients due to measurement errors in input variables -- affects astronomical data-driven models. For linear regression, this problem was solved by treating the true input values as latent variables to be estimated alongside model parameters. In this paper, we show that neural networks suffer from the same attenuation bias and that the latent variable solution generalizes directly to neural networks. We introduce LatentNN, a method that jointly optimizes network parameters and latent input values by maximizing the joint likelihood of observing both inputs and outputs. We demonstrate the correction on one-dimensional regression, multivariate inputs with correlated features, and stellar spectroscopy applications. LatentNN reduces attenuation bias across a range of signal-to-noise ratios where standard neural networks show large bias. This provides a framework for improved neural network inference in the low signal-to-noise regime characteristic of astronomical data. This bias correction is most effective when measurement errors are less than roughly half the intrinsic data range; in the regime of very low signal-to-noise and few informative features. Code is available at https://github.com/tingyuansen/LatentNN.

astro-ph.IM↗
arXiv2026

The dawn is quiet II: Gaia XP constraints on the Milky Way's proto-Galaxy from very metal-poor MDF tails

The earliest phase of the Milky Way's evolution involved a transition from a dispersion-supported proto-galaxy to a rotationally supported disk. A key chemical signature of this transition is the moderate rise in [$α$/Fe] near $\mathrm{[Fe/H]}\approx-1.3$, which we previously interpreted as evidence for $α$-enhanced gas accretion fueling early disk formation. However, this trend alone does not uniquely constrain the trade-off between initial gas mass, inflow rate, and star formation efficiency (SFE), leaving the physical condition of the proto-Milky Way uncertain. To break this degeneracy, we analyze the metal-poor tail ($-3<\mathrm{[Fe/H]}<-2$) of the Milky Way's metallicity distribution function (MDF) using Gaia DR3 BP/RP (XP) metallicities from ten catalogs. After applying recommended quality cuts, all catalogs exhibit a single-slope exponential tail with slopes $k\simeq0.6$--$2.0$. Comparison with one-zone galactic chemical-evolution (GCE) models that replicated the [$α$/Fe]-rise from Paper I shows that shallow tails ($k\simeq0.6$) require a massive initial cold gas reservoir ($\gtrsim10^9\, \mathrm{M_\odot}$), while steeper tails ($k\gtrsim1$) arise from small reservoirs that built up over time with weak inflow. MDFs with $k \simeq 1.0$ are best reproduced under our GCE framework, which favor a proto-Galaxy with a moderate gas reservoir ($10^{8}$--$10^{9}\, \mathrm{M_\odot}$) sustained through weak continuous inflow ($\sim 2 \ \mathrm{M_\odot \ yr^{-1}}$) and SFE comparable to today's value (a few $\times 10^{-10}\,\mathrm{yr^{-1}}$) during the first Gyr. This scenario is reinforced by MDFs of 30 Milky Way analogs in the Auriga simulations, which exhibit similar slopes ($k\approx1.25$). The metal-poor MDF tail thus provides a quantitative constraint on the Milky Way's early gas accretion and star formation history.

astro-ph.GA↗
arXiv2026

Discovery of A Starburst in the Early Milky Way at [Fe/H] $< -2$

We present an analysis of very metal-poor (VMP) and metal-poor stars ($-3.0 < \mathrm{Fe/H]} < -1.5$) in the Gaia BP/RP or XP catalog, which reveals two distinct metallicity distribution functions (MDFs) in regions of the Galactic disk above and below $|z| = 1.0$ kpc. The low-$|z|$ regions display a metallicity peak around [Fe/H] = -2.0 with a sharp transition in Galactocentric azimuthal velocity ($v_ϕ$), a feature notably absent in high-$|z|$ regions. Using a galactic chemical evolution (GCE) model, we found that the proto-Milky Way underwent two distinct formation scenarios: a rapid star formation burst followed by quenching near the Galactic center and an extended period of steady star formation. This starburst could have been triggered by a gas-rich accretion event in the first Gyr of our Galaxy's history. Comparison with Milky Way-analog galaxies in Auriga simulations shows strong agreement in the characteristics of this starburst population. During the accretion event, gas rapidly sinks into the inner regions of these analog galaxies, producing the observed MDF peak and the low $v_ϕ$ values. The simulations further indicate that most stars at the metallicity peak formed in situ, rather than through accretion. These findings identify this starburst population as the long-sought in situ component of the proto-Galaxy.

astro-ph.GA↗
arXiv2026

Towards Unveiling the Origins of the Milky Way Bulge through Multi-band-Messenger Sky Surveys

We analyze the structure and chemo-dynamical properties of the Galactic bulge using ab-type RR Lyrae stars (RRabs) from OGLE-IV and giant stars from APOGEE and Gaia. Orbital integration of 1,879 RRab variables reveals three populations: central bulge, inner bulge, and halo/disk contaminants. Inner bulge RRabs display bar-like kinematics, whereas central bulge stars show slower rotation and lower dispersion. APOGEE data for 28,188 stars confirm these kinematic trends and reveal a bimodal chemical distribution, indicating distinct formation pathways. Our results support a pseudo-bulge origin of the inner bulge through disk instability, with the overall morphology better described as boxy rather than X-shaped. Through the integration of multi-messenger, multi-band data, our collaboration aims to provide deeper insights into the physical properties and evolutionary history of the Galactic bulge.

astro-ph.GA↗
arXiv2026

The Future of Artificial Intelligence and the Mathematical and Physical Sciences (AI+MPS)

This community paper developed out of the NSF Workshop on the Future of Artificial Intelligence (AI) and the Mathematical and Physics Sciences (MPS), which was held in March 2025 with the goal of understanding how the MPS domains (Astronomy, Chemistry, Materials Research, Mathematical Sciences, and Physics) can best capitalize on, and contribute to, the future of AI. We present here a summary and snapshot of the MPS community's perspective, as of Spring/Summer 2025, in a rapidly developing field. The link between AI and MPS is becoming increasingly inextricable; now is a crucial moment to strengthen the link between AI and Science by pursuing a strategy that proactively and thoughtfully leverages the potential of AI for scientific discovery and optimizes opportunities to impact the development of AI by applying concepts from fundamental science. To achieve this, we propose activities and strategic priorities that: (1) enable AI+MPS research in both directions; (2) build up an interdisciplinary community of AI+MPS researchers; and (3) foster education and workforce development in AI for MPS researchers and students. We conclude with a summary of suggested priorities for funding agencies, educational institutions, and individual researchers to help position the MPS community to be a leader in, and take full advantage of, the transformative potential of AI+MPS.

cs.AI↗
arXiv2026

AstroMLab 4: Benchmark-Topping Performance in Astronomy Q&A with a 70B-Parameter Domain-Specialized Reasoning Model

General-purpose large language models (LLMs), despite their broad capabilities, often struggle with specialized domain knowledge. This gap hinders their deployment as reliable research agents in demanding fields such as astronomy. Building on our prior work with AstroSage-Llama-3.1-8B, this study introduces AstroSage-Llama-3.1-70B, a 70-billion parameter domain-specialized natural-language AI assistant. It is designed for research and education across astronomy, astrophysics, space science, astroparticle physics, cosmology, and astronomical instrumentation. Developed from the Meta-Llama-3.1-70B foundation, AstroSage-Llama-3.1-70B underwent extensive continued pre-training (CPT) on a vast corpus of astronomical literature, followed by supervised fine-tuning (SFT) and model merging. We integrated reasoning chains into the SFT dataset, enabling AstroSage-Llama-3.1-70B to either answer the user query immediately, or first emit a human-readable thought process. Evaluated on a validated subset of 3,846 questions from the AstroMLab-1 benchmark (Ting et al., 2024) -- derived from literature withheld during training -- AstroSage-Llama-3.1-70B achieves top-tier performance (89.0%), matching GPT-5.2, Claude-4.5-Opus, and Gemini-3-Pro while being more cost-efficient. This work demonstrates that domain specialization, when applied to large-scale models, can enable them to outperform generalist counterparts in specialized knowledge areas like astronomy, thereby advancing the frontier of AI capabilities in the field.

astro-ph.IM↗
arXiv2026

Variations in the Milky Way's Stellar Mass Function at [Fe/H] < -1

We present the first determination of the Galactic stellar mass function (MF) for low-mass stars (0.2-0.5 M_sun) at metallicities [Fe/H] < -1. A sample of ~53,000 stars was selected as metal-poor on the basis of both their halo-like orbits and their spectroscopic [Fe/H] from Gaia DR3 BP/RP (XP) spectra. These metallicity estimates for low-mass stars were enabled by calibrating Gaia XP spectra with stellar parameters from SDSS-V. For -1.5 < [Fe/H] < -1, we find that the MF below 0.5 M_sun exhibits a "bottom-heavy" power-law slope of alpha ~ -1.6. We tentatively find that at even lower metallicities, the MF becomes very bottom-light, with a near-flat power-law slope of alpha ~ 0 that implies a severe deficit of low-mass stars. This metallicity-dependent variation is insensitive to the adopted stellar evolution model. These results show that the Galactic low-mass MF is not universal, with variations in the metal-poor regime. A further calibration of XP metallicities in the regime of M < 0.5 M_sun and [Fe/H] < -1.5 will be essential to verify these tentative low-metallicity trends.

astro-ph.GA↗
arXiv2026

Can AI Dream of Unseen Galaxies? Conditional Diffusion Model for Galaxy Morphology Augmentation

Observational astronomy relies on visual feature identification to detect critical astrophysical phenomena. While machine learning (ML) increasingly automates this process, models often struggle with generalization in large-scale surveys due to the limited representativeness of labeled datasets, whether from simulations or human annotation, a challenge pronounced for rare yet scientifically valuable objects. To address this, we propose a conditional diffusion model to synthesize realistic galaxy images for augmenting ML training data (hereafter GalaxySD). Leveraging the Galaxy Zoo 2 dataset which contains visual feature, galaxy image pairs from volunteer annotation, we demonstrate that GalaxySD generates diverse, high-fidelity galaxy images that closely adhere to the specified morphological feature conditions. Moreover, this model enables generative extrapolation to project well-annotated data into unseen domains and advancing rare object detection. Integrating synthesized images into ML pipelines improves performance in standard morphology classification, boosting completeness and purity by up to 30% across key metrics. For rare object detection, using early-type galaxies with prominent dust lane features (~0.1% in GZ2 dataset) as a test case, our approach doubled the number of detected instances, from 352 to 872, compared to previous studies based on visual inspection. This study highlights the power of generative models to bridge gaps between scarce labeled data and the vast, uncharted parameter space of observational astronomy and sheds insight for future astrophysical foundation model developments. Our project homepage is available at https://galaxysd-webpage.streamlit.app/.

astro-ph.GA↗
arXiv2025

Towards Understanding the Milky Way's Matter Field and Dynamical Accretion History based on AI-GS3 Hunter

We present GS3 Hunter (Galactic-Seismology Substructures and Streams Hunter), a novel deep-learning method that combines Siamese Neural Networks and K-means clustering to identify substructures and streams in stellar kinematic data. Applied to Gaia EDR3 and GALAH DR3, it recovers known groups (e.g., Thamnos, Helmi, GSE, Sequoia) and, with DESI dataset, reveals that GSE consists of four distinct components (GSH-GSH1 through GSE-GSH4), implying a multi-event accretion origin. Tests on LAMOST K-giants recover Sagittarius, Hercules-Aquila, and Virgo Overdensity, while also uncovering new substructures. Validation with FIRE simulations shows good agreement with previous results. GS3 Hunter thus offers a powerful tool to understand the Milky Way's halo assembly and tidal history.

astro-ph.GA↗