Agentic Active Learning Meets Visual Embeddings: Finding Anomalies among 370 000 Variable Stars from ASAS-SN

arXiv:2608.23688 · astro-ph.SR, astro-ph.IM · Submitted 2026-08-24 · Read on arXiv

astro-ph.SR, astro-ph.IM

Submitted: 2026-08-24

Updated: 2026-08-24

Code: https://github.com/milanpesta/aal

Terminology

• Active Learning — 41× in this paper · explained in 6 episodes
• Embeddings — 34× in this paper · explained in 2 episodes
• Cosine Similarity — 7× in this paper · explained in 3 episodes
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Foundation Model — 4× in this paper · explained in 3 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Clustering — 2× in this paper · explained in 2 episodes
• Failure Modes — 2× in this paper · explained in 3 episodes
• LLM judge — 2× in this paper · explained in 2 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Hallucination — 1× in this paper · explained in 4 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 4 episodes

Sources

• Qwen3-VL Technical Report
• Long-term Study of Changes in the Orbital Periods of 18 Eclipsing SW Sextantis Stars
• Gemma 4 Technical Report
• New Photometric Observations and the 2015 Eclipse of the Symbiotic Nova Candidate ASAS J174600-2321.3
• ASAS-SN Sky Patrol V2.0
• Masked Autoencoders Are Scalable Vision Learners
• The Curious Case of ASAS J174600-2321.3: an Eclipsing Symbiotic Nova in Outburst?
• Spec-o3: A Tool-Augmented Vision-Language Agent for Rare Celestial Object Candidate Vetting via Automated Spectral Inspection
• Variational Inference with Normalizing Flows
• Learning Transferable Visual Models From Natural Language Supervision
• The OGLE Collection of Variable Stars. Over 450 000 Eclipsing and Ellipsoidal Binary Systems Toward the Galactic Bulge
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Can Multimodal LLMs Perform Time Series Anomaly Detection?
• StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• DINOv2: Learning Robust Visual Features without Supervision
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Scikit-learn: Machine Learning in Python

Related papers

• HXI-DLA2: A Physics-Constrained Deep Learning Algorithm for the ASO-S Hard X-ray Imager
• Effect of Neutron Star Jets on Common Envelope Evolution
• Constraining the origin of magnetic white dwarfs
• JW-FD: A 15-Year Multimodal Dataset for Solar Flare Forecasting
• Phlegethon: a fully compressible magnetohydrodynamic code for simulations in stellar astrophysics
• Can MHD Oscillations Modulate Quasi-Periodic Plasma Release from Coronal Streamers?