Searcharxiv⌕ Search

arXiv subjects

Min Gao

Publications and source records attributed to Min Gao.

At least 19 recordsLinked to original sources
arXiv2026

CCAT: Prime-Cam Control System and Related Software

Prime-Cam is one of the primary instruments being developed for use by the CCAT collaboration with the Fred Young Submillimeter Telescope (FYST), which is undergoing construction at a height of 5600 m in Cerro Chajnantor. Prime-Cam can host up to seven instrument modules with kinetic inductance detectors (KIDs), including broadband modules ranging 280-850 GHz and imaging spectrometers for line-intensity mapping. Prime-Cam requires a number of hardware devices for standard operation and data collection, and so a distributed control system must be developed for software integration of these devices and user-friendliness when controlling Prime-Cam in the field, especially during remote operation that will be typical during observations. The Prime-Cam Control System (PCS) is being developed using the Observatory Control System (OCS) framework originally developed for Simons Observatory (SO) and is adapted for Prime-Cam and CCAT-specific requirements. Within OCS/PCS, hardware devices are controlled individually by long-running software processes known as agents, which are typically deployed in Docker containers running in the background of one of the Prime-Cam network computers. These agents are controlled by client scripts through the command line or frontend tools like Nextline and PCS-web. PCS also makes use of several external open source software tools for remote operations, data management, and logging. This system is being tested in the lab in preparation for deployment in 2026 for use with Prime-Cam on FYST.

astro-ph.IM↗
arXiv2026

Beyond the Evidence Coherence Trap: Agent-Driven Evidence Selection for Temporally Disordered Fake News Detection

Fake news undermines public trust and the integrity of online information ecosystems. Temporally disordered fake news is especially elusive because it rearranges factual events into a false chronology. Individual events may remain factually valid even when their temporal relations are misrepresented. When similar events involving the same entity recur, retrieval may return semantically plausible evidence from the wrong period. Consequently, independent event verification may rely on locally coherent but temporally mismatched evidence and incorrectly validate the article. We call this the \textit{evidence coherence trap}. Because existing benchmarks rarely isolate this setting, we construct ChronoFake, a source-disjoint benchmark of 30,706 articles derived from temporally anchored real events. It distinguishes temporal manipulation from valid narration, including flashbacks. To address this, we propose DelSA, a \underline{D}ocument S\underline{el}ection \underline{S}elf-Updating \underline{A}gent that iteratively refines evidence selection during training and applies a frozen rulebook for one-pass evidence selection at inference. DelSA uses an LLM to characterize candidate evidence, while a verifier-trained reranker balances local relevance against timeline consistency. Finally, the classifier compares the article-implied chronology extracted by the LLM with the evidence-derived chronology to reveal global temporal conflicts. DelSA outperforms existing methods on ChronoFake, while remaining competitive on PolitiFact and GossipCop.

cs.AI↗
arXiv2026

LESSRec: Level-Specific History Modeling for Semantic ID-Based Recommendation

Semantic ID-based recommendation represents each item as a sequence of semantic tokens obtained through residual quantization. This paradigm generates the next item's tokens autoregressively from coarse to fine, entailing each prediction attending to historical tokens at all semantic levels. However, our inference-time analysis reveals that historical tokens at the target-token's semantic level tend to be more informative, whereas other levels can introduce interference. Motivated by these findings, we propose LESSRec that separately encodes the historical token sequence at each semantic level and restricts attention over historical tokens to the sequence at the target token's semantic level during prediction. To complement these level-specific histories, LESSRec explicitly provides an item-level semantic sequence that represents each historical item's overall semantics in chronological order. The decoder accesses the level-aligned token sequence and the item-level semantic sequence through two separate cross-attention branches and fuses their contexts. We further introduce LESSRec+, which uses separate encoders for different semantic-level histories with the same total parameter count to reduce encoder computation. Extensive experiments across three public datasets and three tokenizers demonstrate the recommendation effectiveness of LESSRec and LESSRec+, with efficiency analyses highlighting the computational benefits of LESSRec+.

cs.IR↗
arXiv2026

EnvLunch: The Environment as a Free Lunch for Learning to Interact

For agentic data analysis, language-model agents often require a large number of annotated tasks to learn how to interact effectively with executable environments (i.e., databases). While high-quality annotated tasks require heavy manual effort, an executable environment already provides rich interaction structure and verifiable outcomes. In this sense, the environment itself offers a free lunch, an additional set of verifiable tasks that require no human annotation. We propose EnvLunch, a warm-up stage that turns this environmental signal into agent training without human-written or model-generated task descriptions, before downstream agentic reinforcement learning. EnvLunch samples valid action trajectories, executes them to obtain final observations, and trains an agent to recover a functionally equivalent trajectory given only its final observation. This label-free warm-up enables the model to outperform the baseline by over 9 points on average across all downstream training budgets, and with few labels, the baseline needs 8 to 32 times as many annotated examples to match the accuracy that the EnvLunch model reaches at its smallest training budget. Letting the environment alone define the task yields a larger gain than having the model write its own tasks over the same environments, and this warm-up also improves fine-tuning on benchmarks beyond data analysis. EnvLunch therefore saves annotated tasks and provides a better starting point for fine-tuning agentic models when such tasks are limited.

cs.AI↗
arXiv2026

SharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News Detection

Fake news detection under low resource conditions is challenged by the scarcity of labeled data and the difficulty of capturing subtle deceptive patterns. In this work, we focus on low resource fake news detection, where only a small labeled set is available for training, while evaluation is performed under a fixed and unchanged test protocol. This setting is motivated by costly, ambiguous fact-checking and emerging topics and domains that are poorly covered by existing benchmarks. Existing data augmentation methods, such as synonym substitution, generative adversarial networks, and large language model (LLM)-based generation, often produce fluent but overly generic content, lacking the task-specific relevance needed for accurate detection. To address this, we propose SharP, a boundary-aware text generation framework guided by soft and hard prompts, which leverages LLMs as tools adapted to produce task-specific synthetic samples. SharP employs a dual prompt mechanism: hard prompts provide structured guidance and factual constraints, while soft prompts introduce learned semantic patterns from the data. These two types of prompts are combined to guide the generation process, enabling the model to produce samples that closely align with the characteristics of news. To further enhance detection performance, we incorporate a boundary-aware strategy that steers generation toward areas where the classifier is less confident, helping to clarify subtle distinctions between real and fake content. In addition, we adopt a dual objective optimization that balances semantic alignment with the source data and classifier feedback. This encourages the generation of samples that are both domain-consistent and helpful for refining decision boundaries, ultimately improving model robustness and generalization in low resource fake news detection.

cs.CL↗
arXiv2026

Automated Volumetric Segmentation of Microaneurysms on OCT Using Artificial Intelligence

Purpose: To develop and validate a deep learning-based method for the automated identification and volumetric segmentation of microaneurysms (MAs) in diabetic retinopathy (DR) using OCT. Participants: A total of 125 participants were enrolled, including 20 healthy eyes, 27 with mild NPDR, 30 with moderate NPDR, 30 with severe NPDR, and 18 with PDR. Methods: We obtained multiple repeated 3x3-mm scans from each participant using a commercial 120-kHz spectral-domain OCT system (Solix; Visionix/Optovue, Inc., California, USA), which were registered and averaged to generate high-definition volumes. We developed a 3D deep learning network to segment MAs volumetrically. The input to the network consists of the original OCT volume concatenated with its reflectance-inverted counterpart. Expert graders manually delineated MAs to generate annotations. We evaluated model performance at multiple levels, including voxel-level segmentation, lesion-level detection, and eye-level diagnosis. Results: In the test dataset (20 healthy, 20 DR eyes), the algorithm demonstrated high voxel-level accuracy, with F1 scores of 79.2% on single volumes and 86.1% on averaged volumes. Lesion-level detection reached an F1 score of 96.0% (single) and 97.1% (averaged), while scan-level diagnostic accuracy for MA presence was 97.5% (single and averaged). Conclusions: A deep learning-based method can accurately identify and segment MAs volumetrically on OCT, enabling quantification and characterization, and potentially aiding in the diagnosis, monitoring, and management of DR.

q-bio.QM↗
arXiv2026

Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning

Test-time adaptation has emerged as a lightweight alternative to costly post-training for improving the reasoning capabilities of Large Language Models (LLMs) on downstream tasks. Predictive entropy provides a model-derived signal for such adaptation, guiding models toward higher-confidence reasoning states without external verifiers or reward models. However, higher confidence does not necessarily imply correctness, as LLMs may remain highly confident along incorrect reasoning trajectories. We observe that high-confidence reasoning is more likely to be correct when confidence remains stable under local perturbations. Based on this observation, we propose Test-Time Adaptation via Stability-Aware Confidence Optimization (TASCO), a framework that incorporates local stability into confidence-based test-time adaptation while keeping the LLM frozen. TASCO operationalizes local stability by optimizing a lightweight task-level prefix under two alternative perturbation strategies: Random Perturbation promotes distributional stability across trajectories induced by nearby perturbed prefixes, whereas Sharpness-Aware Perturbation targets worst-case local sensitivity. Experiments demonstrate that TASCO improves reasoning accuracy and token efficiency across diverse LLMs and reasoning benchmarks, while behavioral analyses show that it maintains stable confidence under local perturbations without prematurely concentrating the model's predictive distribution.

cs.AI↗
arXiv2026

Lightweight Soft X-ray Imager (LSXI) with glass-based coded mask

The coded mask technique has been widely used in X-ray and Gamma-ray imagers, especially in space astronomy. However, the traditional design of coded mask imagers usually has problems with large size and heavy weight. Here, we propose a novel design for a coded mask imager made of glass based on microchannel plate (MCP) technology, making it lightweight (within 1 kg), compact, and self-supporting, which is very suitable for space exploration satellites. The design is initially demonstrated by reconstructing encoded patterns from measurements at the X-ray beamline. Monte Carlo simulations of the module integrated into a 6U CubeSat are conducted to assess its in-orbit detector performance, including sensitivity and source localization.

astro-ph.IM↗
arXiv2026

Personalized Communication Skills for Agentic Recommender Systems

Agentic recommender systems increasingly employ large language model-based UserAgents to evaluate candidate items through simulated feedback before recommendations are delivered. However, existing UserAgents typically reason in isolation based on limited personal histories, which may lead to perspective narrowing: the agent evaluates candidates from a local and incomplete view, overlooks relevant preference facets, and consequently produces inaccurate judgments. A natural way to alleviate this problem is to introduce other users as advisor agents, whose diverse histories provide complementary evidence that helps the target user reconsider overlooked preference signals. Nevertheless, a generic user-advisor communication process is insufficient, as different user decision states require different forms of external advice. Based on this insight, we propose AgentCom, a personalized communication skill framework for agentic recommender systems. AgentCom organizes reusable communication skills into a shared why--what--how--who skill bank: why identifies the decision deficiency that necessitates communication, what specifies the information task, how determines the advisor interaction protocol, and who retrieves advisors capable of executing that protocol. To make the shared skill bank personalized at use time and adaptive over time, AgentCom introduces two complementary mechanisms: personalized skill routing and failure-driven skill evolution. Personalized skill routing constructs a communication path by sequentially selecting suitable skills for each user and recommendation context. Failure-driven skill evolution learns from unsuccessful communication cases and enriches the shared bank with reusable skills that address previously uncovered communication needs. Experiments show that AgentCom consistently improves recommendation performance across traditional, social, and agentic recommenders.

cs.IR↗
arXiv2026

CCAT: Design and Characterization of the 350 GHz Instrument Module

The CCAT Collaboration's Prime-Cam instrument will soon be deployed to the Fred Young Submillimeter Telescope (FYST) in Chile's Atacama Desert. Featuring prominently in Prime-Cam's calibration and early science observations will be the 350 GHz instrument module, a broadband camera that will field more than 10,000 microwave kinetic inductance detectors (KIDs) across three detector arrays. Forecasts show this module will be capable of making the most sensitive to-date measurements of polarized dust emission over a large fraction of the sky at this frequency, enabling new galactic polarization science and improved understanding of cosmological foregrounds. In this work we discuss the design of the 350 GHz instrument module, covering aspects of the optics, readout, and detector arrays. We then report on the results of in-lab testing of the fully-integrated module, achieving stable cryogenic performance with a 100 mK focal plane, high detector yield, and a passband comparable to designed specifications. Upon completion of these tests, this module was shipped to the telescope site in Chile for integration in Prime-Cam.

astro-ph.IM↗
arXiv2026

Where Reasoning Matters: Rethinking Latent Reasoning in Semantic ID-based Generative Recommendation

Semantic ID-based generative recommendation predicts an item by generating a short sequence of semantic ID tokens, where each token is produced autoregressively. Latent reasoning has recently been introduced to improve this process through additional hidden-state computation before each token decision. This raises a practical question: when one item is represented by a sequence of semantic ID tokens, should each token receive the same fixed number of latent refinement steps, or should these steps be allocated more effectively across positions? We study this question through position-wise information-gain (IG), which measures how much each semantic ID position reduces the uncertainty of the target item. We observe that earlier semantic ID positions usually provide higher information-gain, while later positions contribute less additional information. We further analyze that applying more refinement to high-IG positions tends to bring larger expected benefits. Based on this observation, we propose IBA, an Information-Gain Budget Allocation framework for semantic ID-based generative recommendation. IBA treats latent refinement steps as a limited computational resource and learns how to allocate them across semantic ID positions, assigning more refinement to informative positions and less to positions with smaller contribution. Experiments on multiple public datasets show that IBA consistently improves strong generative recommendation baselines and achieves a better accuracy--computation trade-off than fixed or poorly matched step allocations.

cs.IR↗
arXiv2026

BICEP/Keck XXI: Constraints on Early-Universe Parity Violation from Multipole-Dependent Birefringence

We present the first constraints on multipole-dependent cosmic birefringence using CMB polarization data from the BK18 dataset, which combines observations from BICEP2, Keck Array, and BICEP3 at frequencies of 95, 150, and 220 GHz. Photon coupling to an axion-like field leads to the rotation of CMB polarization, inducing non-zero EB cross-correlations. We show that a multipole-dependent rotation beta(l) imprints a distinct signature in the polarization spectra that can be constrained. Specifically, we consider an Early Dark Energy (EDE) scenario in which a pseudoscalar field couples to photons through a Chern-Simons interaction, generating a polarization rotation with multipole dependence. We introduce a phenomenological beta(l) as a step function, obtaining constraints on the step function size consistent with zero, with uncertainties less than 0.15 degrees (68% CL). In addition, using multi-frequency EE, BB, and EB cross-spectra, along with robust BICEP/Keck foreground treatment and likelihood framework, we derive constraints on the axion-photon coupling amplitude g for several choices of EDE parameters. For the baseline best-fit value f_{EDE} = 0.087 from the Planck 2018 analysis, we obtain g = 0.11 +/- 0.37 (68% CL), consistent with previous limits.

astro-ph.CO↗
arXiv2026

Three-Dimensional Retinal Microvasculature Restoration in OCT Angiography

Optical coherence tomographic angiography (OCTA) is a powerful technique for imaging retinal microvasculature. However, acquiring reliable quantification of retinal blood flow and areas of retinal nonperfusion is challenging because of imaging artifacts. Existing methods primarily focus on noise suppression, projection artifact removal, or signal enhancement to improve the image quality of OCTA in cross-sectional or two-dimensional (2D) en face projections, while neglecting the intrinsic three-dimensional vascular architecture. In this study, we propose a deep learning-based algorithm for restoring capillary anatomical vasculature from a single OCTA volume. The network consists of an EfficientNet-B5 encoder and a decoder incorporating concurrent spatial and channel squeeze-and-excitation modules, connected via skip connections to preserve spatial resolution. Three adjacent B-frames are used as input to predict the restored middle B-frame. We evaluated the performance of the model using the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) against ground truth generated from averaging multiple scans. The results show that the proposed model significantly (both p < 0.001) improved image quality compared with the original single OCTA volume, with a PSNR of 26.16 +/- 1.26 vs. 22.23 +/- 0.78 and an SSIM of 0.91 +/- 0.02 vs. 0.72 +/- 0.03. The proposed model also significantly (p < 0.001) improved microvascular fidelity, measured by the Dice coefficient overlap between the model output and ground truth, in both 2D and 3D by at least 3.8% and 51.2%, respectively, across several different vascular slabs.

cs.CV↗
arXiv2026

Deep Learning-assisted AMD Staging based on OCT and OCT Angiography

To develop and evaluate deep learning models for automated grading of age-related macular degeneration (AMD) severity using optical coherence tomography (OCT) and OCT angiography (OCTA) data. Two hundred seventy-one participants aged >= 50 years with varying AMD severities. Central macular 6 x 6 mm OCT/OCTA volumes were acquired using a swept-source OCTA system (SOLIX; Visionix/Optovue Inc., CA). AMD severity was graded into four stages (No AMD, Early AMD, Intermediate AMD, and Advanced AMD) according to the AREDS simplified severity scale. Three deep learning models were developed using different input modalities: (1) biomarker maps derived from segmented pathological features, including retinal fluid, drusen, geographic atrophy (GA), and macular neovascularization (MNV); (2) two-dimensional (2D) en face OCT and OCTA projections; and (3) three-dimensional (3D) OCT/OCTA volumes. EfficientNet-based architectures were trained using normalized inputs, data augmentation, and five-fold cross-validation. A total of 2,030 OCT/OCTA volumes from 351 eyes of 271 participants were analyzed. All models demonstrated strong AMD staging performance with substantial agreement with the reference standard (QWK >= 0.83). The biomarker-based model achieved the highest overall performance (QWK = 0.85 +/- 0.03, mean +/- standard deviation) and the best detection of early AMD (F1-score = 0.59 +/- 0.14). The 3D model achieved performance comparable to the 2D OCT/OCTA model (QWK = 0.83 +/- 0.04 vs. 0.83 +/- 0.09), while the 2D OCT/OCTA model showed the highest precision (0.79 +/- 0.06) and most accurately identified eyes without AMD. Deep learning models using OCT/OCTA data can accurately and automatically grade AMD severity. Among the evaluated approaches, the biomarker-based model provided the most balanced performance and showed particular value for early AMD detection.

cs.CV↗
arXiv2026

Robust and Reliable AI for Predictive Quality in Semiconductor Materials Manufacturing with MLOps and Uncertainty Quantification

Semiconductor materials manufacturing presents unique challenges for machine learning deployment due to evolving process conditions, equipment degradation, and raw material variability that can cause model performance deterioration over time. This study benchmarks machine learning operations (MLOps) retraining strategies using five years of real manufacturing data to identify optimal retraining approaches for quality prediction. We evaluate various retraining frequencies and hyperparameter optimization strategies using control limit normalized residuals as key performance metric. Results demonstrate that a fixed retraining cadence every five production batches without hyperparameter retuning achieves superior performance across all drift conditions while significantly reducing computational overhead compared to strategies incorporating hyperparameter optimization. This approach effectively maintains model accuracy during both abrupt process changes and gradual equipment degradation patterns. To address the critical need for uncertainty quantification in manufacturing decision-making, we implement conformal prediction to generate prediction confidence intervals with strong statistical guarantees. This enables proactive quality control by identifying when prediction intervals fall within acceptable control limits, transforming traditional reactive quality management into a predictive framework. The findings provide practical guidelines for implementing robust MLOps strategies in manufacturing environments where computational efficiency and reliable uncertainty quantification are paramount for operational success.

cs.LG↗
arXiv2026

Charge-dependent spectral softenings of primary cosmic-rays below the knee

In most particle acceleration or propagation theories, the characteristic features of the cosmic ray spectra due to acceleration limits or propagation phase changes are charge dependent. Alternatively, the interaction scenario would expect mass dependent spectral features in general. The observational verification of which relation takes effect in nature is still lack due to the difficulty of measuring the spectra of individual particles up to very high energies. Here we report direct measurements of the carbon, oxygen, and iron spectra from ~20 gigavolts to ~100 teravolts (~60 teravolts for iron) with 9 years of on-orbit data collected by the Dark Matter Particle Explorer. Distinct spectral softenings have been directly detected in these spectra for the first time. Combined with the updated proton and helium spectra, the spectral softening appears universally at a rigidity of ~15 teravolts. A nuclei mass dependent softening is rejected at a confidence level of >99.999%. Possible interpretations of these results, including a nearby cosmic ray source and other models such as the propagation effect, are discussed.

astro-ph.HE↗
arXiv2026

The trigger and localization system of SVOM-GRM

The Space multi-band Variable Object Monitor (SVOM) is an astronomical satellite jointly developed by China and France, primarily focused on the detection of gamma-ray bursts (GRBs) and transient sources. The SVOM satellite was launched on 22nd June, 2024 with four payloads installed onboard. As one of payload, GRM comprises 3 gamma-ray detectors (each detector has an effective area of approximately 200~cm$^{2}$) with distinct pointing directions, enabling the temporal and spectral measurements as well as localization of GRBs in the energy range of 15-5000 keV. This article firstly introduces the on-board localization algorithm design for GRM and presents preliminary test results. Then, leveraging abundant ground-based computational resources, a joint fitting method for spectral and localization analysis using Monte Carlo Markov Chain (MCMC) is implemented. In contrast to the on-board localization algorithm, the on-ground MCMC method comprehensively considers the influence of spectral characteristics, thereby mitigating systematic biases. Finally, a systematic analysis based on this method is provided, highlighting the localization and spectral measurement capabilities of GRM. The preliminary localization analysis result for the on-board detected GRB 240629A by both GRM and Fermi/GBM shows that the localization result (error$\sim$4.14$^{\circ}$) of GRM is consistent with the Fermi/GBM result.

astro-ph.IM↗