arXiv subjects

Jinming Zhang

Publications and source records attributed to Jinming Zhang.

At least 19 recordsLinked to original sources

arXiv2026

A Two-level Radial-velocity Zero-point Calibration for LAMOST MRS with Gaia and APOGEE and a Value-added RV Catalogue

The LAMOST Medium-Resolution Survey (MRS) provides a large stellar spectroscopic data set for Galactic kinematics and time-domain radial-velocity (RV) studies. However, the multi-spectrograph, multi-exposure, multi-fiber observing strategy can imprint RV zero-point (RVZP) systematics that vary across instrumental and temporal hierarchies. We construct a two-level empirical RVZP correction to LAMOST DR12 MRS using Gaia DR3 magnitude-colour-corrected RVs and APOGEE DR17 RVs as external references: a spectrograph-exposure correction in (lmjm, planid, spid) units, followed by a fiber-time correction in (spid, fiberid, time_tag) units. Within each unit, RVZPs are estimated from Gaia and APOGEE residuals using a weighted-median estimator, and are subtracted from the pipeline RVs to obtain corrected velocities. For high-S/N spectra, the scatter relative to APOGEE DR17 decreases from ~1.1 km/s to ~0.52 km/s after the full two-level correction, implying a ~2x improvement in RV precision. We release a value-added catalogue of two-level-corrected RVs for 11,129,477 blue-arm spectra, including 8,158,271 single-exposure spectra and 2,971,206 coadded spectra, enabling consistent RV analyses across exposures, spectrographs, fibers, and time.

astro-ph.GA↗

arXiv2026

SE-AGCNet: An End-to-End Framework for Joint Speech Enhancement and Loudness Control in Meeting Scenarios

Conventional audio pipelines typically treat speech enhancement (SE) and automatic gain control (AGC) as discrete modules, which often limits overall performance. For instance, applying AGC before SE may inadvertently amplify background noise, while prioritizing SE tends to over-suppress low-volume speech. To address these limitations, we propose SE-AGCNet, an end-to-end framework that jointly optimizes SE and AGC. Tailored for meeting scenarios with significant volume variations, SE-AGCNet leverages the synergy between the two tasks: SE preserves quiet speech, thereby facilitating effective volume adjustment by the AGC component. Furthermore, we propose a specialized data simulation pipeline, SE-AGC-DataGen, and incorporate standardized loudness evaluation metrics: integrated loudness (LUFS), short-term loudness (St LUFS), and LRA. Experiments show that SE-AGCNet consistently achieves target loudness while improving speech quality and ASR accuracy over competitive baselines.

eess.AS↗

arXiv2026

Dependencies in Item-Adaptive CAT Data and Differential Item Functioning Detection: A Multilevel Framework

Differential item functioning (DIF) detection is an important yet understudied problem in computerized adaptive testing (CAT). In this article, we proposed a two-level logistic model to improve DIF detection in CAT by explicitly accounting for nuisance effects arising from CAT-induced structural dependency. First, we conceptualized that adaptive item selection induces systematic dependencies among examinees and items through provisional ability estimates, whereas traditional single-level DIF methods assume independent observations and may yield misleading results in CAT settings. Then, using a numeric example and Monte Carlo simulations, we compared our proposed two-level model with competing single-level models under various CAT conditions, manipulating test length, exposure control, ability estimator, DIF type, and DIF prevalence. Item-level Type-I error and statistical power conditional on joint model convergence were reported for each model. We showed that the proposed two-level model has improved control of spurious DIF and competitive power relative to single-level models, particularly with shorter tests and smaller exposure rates. However, we observed that the model convergence varied systematically across simulated conditions, highlighting that inferential accuracy and convergence reliability are intertwined in complex CAT DIF settings. Through this study, we underscored both the promise of multilevel DIF modeling in CAT and the need for future research to jointly evaluate convergence and inferential performance when assessing DIF models.

stat.AP↗

arXiv2026

A General Framework for Radial Velocity Calibration in Low-Resolution Spectroscopic Surveys: Correcting Wavelength-Dependent and Global Systematics with Application to LAMOST DR9

Radial velocity (RV) is crucial for stellar kinematics and Galactic archaeology. The Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST) has obtained over ten million low-resolution spectra ($R \sim 1800$), yielding RVs for millions of stars, but these suffer from (1) wavelength-dependent inconsistencies (relative shifts between spectral segments) and (2) global zero-point offsets (uniform shifts of entire spectra). In this work, we comprehensively characterize and correct both. Each spectrum is first divided into eight segments of about 500 Angstrom. We organize the data at the spectrograph and fiber levels, measure segment-wise RV offsets relative to the full spectrum at each level, and then fit these offsets with low-order polynomials to correct wavelength-dependent systematics. We then correct zero-points hierarchically: at the spectrograph level by minimizing a joint chi-squared constrained by repeat observations and cross-matches with APOGEE and Gaia RVS, and at the fiber level by averaging seasonal offsets. After correction, RV precision improves significantly: for cross-night repeats, the standard deviation of RV differences at high signal-to-noise ratios drops by a factor of two from about 3.6 to about 1.8 km s$^{-1}$, implying a single-measurement precision of about 1.3 km s$^{-1}$. External checks with APOGEE and Gaia show dispersions drop from about 4.0 to about 2.0 km s$^{-1}$. The precision approaches, though slightly below, the theoretical limit at $R \sim 1800$. We release a value-added RV catalog with corrected velocities for about 5.7 million spectra, providing a homogeneous and systematically corrected dataset. The framework established in this work is also applicable to RV calibration in other large-scale spectroscopic surveys.

astro-ph.SR↗

arXiv2026

Pareto-Guided Optimization for Uncertainty-Aware Medical Image Segmentation

Uncertainty in medical image segmentation is inherently non-uniform, with boundary regions exhibiting substantially higher ambiguity than interior areas. Conventional training treats all pixels equally, leading to unstable optimization during early epochs when predictions are unreliable. We argue that this instability hinders convergence toward Pareto-optimal solutions and propose a region-wise curriculum strategy that prioritizes learning from certain regions and gradually incorporates uncertain ones, reducing gradient variance. Methodologically, we introduce a Pareto-consistent loss that balances trade-offs between regional uncertainties by adaptively reshaping the loss landscape and constraining convergence dynamics between interior and boundary regions; this guides the model toward Pareto-approximate solutions. To address boundary ambiguity, we further develop a fuzzy labeling mechanism that maintains binary confidence in non-boundary areas while enabling smooth transitions near boundaries, stabilizing gradients, and expanding flat regions in the loss surface. Experiments on brain metastasis and non-metastatic tumor segmentation show consistent improvements across multiple configurations, with our method outperforming traditional crisp-set approaches in all tumor subregions.

cs.CV↗

arXiv2025

Analysis and Evaluation of Synthetic Data Generation in Speech Dysfluency Detection

Speech dysfluency detection is crucial for clinical diagnosis and language assessment, but existing methods are limited by the scarcity of high-quality annotated data. Although recent advances in TTS model have enabled synthetic dysfluency generation, existing synthetic datasets suffer from unnatural prosody and limited contextual diversity. To address these limitations, we propose LLM-Dys -- the most comprehensive dysfluent speech corpus with LLM-enhanced dysfluency simulation. This dataset captures 11 dysfluency categories spanning both word and phoneme levels. Building upon this resource, we improve an end-to-end dysfluency detection framework. Experimental validation demonstrates state-of-the-art performance. All data, models, and code are open-sourced at https://github.com/Berkeley-Speech-Group/LLM-Dys.

eess.AS↗

arXiv2025

Seamless Dysfluent Speech Text Alignment for Disordered Speech Analysis

Accurate alignment of dysfluent speech with intended text is crucial for automating the diagnosis of neurodegenerative speech disorders. Traditional methods often fail to model phoneme similarities effectively, limiting their performance. In this work, we propose Neural LCS, a novel approach for dysfluent text-text and speech-text alignment. Neural LCS addresses key challenges, including partial alignment and context-aware similarity mapping, by leveraging robust phoneme-level modeling. We evaluate our method on a large-scale simulated dataset, generated using advanced data simulation techniques, and real PPA data. Neural LCS significantly outperforms state-of-the-art models in both alignment accuracy and dysfluent speech segmentation. Our results demonstrate the potential of Neural LCS to enhance automated systems for diagnosing and analyzing speech disorders, offering a more accurate and linguistically grounded solution for dysfluent speech alignment.

eess.AS↗

arXiv2025

VisAlgae 2023: A Dataset and Challenge for Algae Detection in Microscopy Images

Microalgae, vital for ecological balance and economic sectors, present challenges in detection due to their diverse sizes and conditions. This paper summarizes the second "Vision Meets Algae" (VisAlgae 2023) Challenge, aiming to enhance high-throughput microalgae cell detection. The challenge, which attracted 369 participating teams, includes a dataset of 1000 images across six classes, featuring microalgae of varying sizes and distinct features. Participants faced tasks such as detecting small targets, handling motion blur, and complex backgrounds. The top 10 methods, outlined here, offer insights into overcoming these challenges and maximizing detection accuracy. This intersection of algae research and computer vision offers promise for ecological understanding and technological advancement. The dataset can be accessed at: https://github.com/juntaoJianggavin/Visalgae2023/.

cs.CV↗

arXiv2025

Dysfluent WFST: A Framework for Zero-Shot Speech Dysfluency Transcription and Detection

Automatic detection of speech dysfluency aids speech-language pathologists in efficient transcription of disordered speech, enhancing diagnostics and treatment planning. Traditional methods, often limited to classification, provide insufficient clinical insight, and text-independent models misclassify dysfluency, especially in context-dependent cases. This work introduces Dysfluent-WFST, a zero-shot decoder that simultaneously transcribes phonemes and detects dysfluency. Unlike previous models, Dysfluent-WFST operates with upstream encoders like WavLM and requires no additional training. It achieves state-of-the-art performance in both phonetic error rate and dysfluency detection on simulated and real speech data. Our approach is lightweight, interpretable, and effective, demonstrating that explicit modeling of pronunciation behavior in decoding, rather than complex architectures, is key to improving dysfluency processing systems.

eess.AS↗

arXiv2025

Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games

Interactive Fiction games (IF games) are where players interact through natural language commands. While recent advances in Artificial Intelligence agents have reignited interest in IF games as a domain for studying decision-making, existing approaches prioritize task-specific performance metrics over human-like comprehension of narrative context and gameplay logic. This work presents a cognitively inspired framework that guides Large Language Models (LLMs) to learn and play IF games systematically. Our proposed **L**earning to **P**lay **L**ike **H**umans (LPLH) framework integrates three key components: (1) structured map building to capture spatial and narrative relationships, (2) action learning to identify context-appropriate commands, and (3) feedback-driven experience analysis to refine decision-making over time. By aligning LLMs-based agents' behavior with narrative intent and commonsense constraints, LPLH moves beyond purely exploratory strategies to deliver more interpretable, human-like performance. Crucially, this approach draws on cognitive science principles to more closely simulate how human players read, interpret, and respond within narrative worlds. As a result, LPLH reframes the IF games challenge as a learning problem for LLMs-based agents, offering a new path toward robust, context-aware gameplay in complex text-based environments.

cs.CL↗

arXiv2025

Metallicities of 20 Million Giant Stars Based on Gaia XP spectra

We design an uncertainty-aware cost-sensitive neural network (UA-CSNet) to estimate metallicities from dereddened and corrected Gaia BP/RP (XP) spectra for giant stars. This method accounts for both stochastic errors in the input spectra and the imbalanced density distribution in [Fe/H] values. With a specialized architecture and training strategy, the UA-CSNet improves the precision of the predicted metallicities, especially for very metal-poor (VMP; $\rm [Fe/H] \leq -2.0$) stars. With the PASTEL catalog as the training sample, our model can estimate metallicities down to $\rm [Fe/H] \sim -4$. We compare our estimates with a number of external catalogs and conduct tests using star clusters, finding overall good agreement. We also confirm that our estimates for VMP stars are unaffected by carbon enhancement. Applying the UA-CSNet, we obtain reliable and precise metallicity estimates for approximately 20 million giant stars, including 360,000 VMP stars and 50,000 extremely metal-poor (EMP; $\rm [Fe/H] \leq -3.0$) stars. The resulting catalog is publicly available at https://doi.org/10.12149/101604. This work highlights the potential of low-resolution spectra for metallicity estimation and provides a valuable dataset for studying the formation and chemo-dynamical evolution of our Galaxy.

astro-ph.SR↗

arXiv2025

Examining Differential Item Functioning (DIF) in Self-Reported Health Survey Data: Via Multilevel Modeling

Few health-related constructs or measures have received a critical evaluation in terms of measurement equivalence, such as self-reported health survey data. Differential item functioning (DIF) analysis is crucial for evaluating measurement equivalence in self-reported health surveys, which are often hierarchical in structure. Traditional single-level DIF methods in this case fall short, making multilevel models a better alternative. We highlight the benefits of multilevel modeling for DIF analysis, when applying a health survey data set to multilevel binary logistic regression (for analyzing binary response data) and multilevel multinominal logistic regression (for analyzing polytomous response data), and comparing them with their single-level counterparts. Our findings show that multilevel models fit better and explain more variance than single-level models. This article is expected to raise awareness of multilevel modeling and help healthcare researchers and practitioners understand the use of multilevel modeling for DIF analysis.

stat.AP↗

arXiv2025

TS-SatMVSNet: Slope Aware Height Estimation for Large-Scale Earth Terrain Multi-view Stereo

3D terrain reconstruction with remote sensing imagery achieves cost-effective and large-scale earth observation and is crucial for safeguarding natural disasters, monitoring ecological changes, and preserving the environment.Recently, learning-based multi-view stereo~(MVS) methods have shown promise in this task. However, these methods simply modify the general learning-based MVS framework for height estimation, which overlooks the terrain characteristics and results in insufficient accuracy. Considering that the Earth's surface generally undulates with no drastic changes and can be measured by slope, integrating slope considerations into MVS frameworks could enhance the accuracy of terrain reconstructions. To this end, we propose an end-to-end slope-aware height estimation network named TS-SatMVSNet for large-scale remote sensing terrain reconstruction.To effectively obtain the slope representation, drawing from mathematical gradient concepts, we innovatively proposed a height-based slope calculation strategy to first calculate a slope map from a height map to measure the terrain undulation. To fully integrate slope information into the MVS pipeline, we separately design two slope-guided modules to enhance reconstruction outcomes at both micro and macro levels. Specifically, at the micro level, we designed a slope-guided interval partition module for refined height estimation using slope values. At the macro level, a height correction module is proposed, using a learnable Gaussian smoothing operator to amend the inaccurate height values. Additionally, to enhance the efficacy of height estimation, we proposed a slope direction loss for implicitly optimizing height estimation results. Extensive experiments on the WHU-TLC dataset and MVS3D dataset show that our proposed method achieves state-of-the-art performance and demonstrates competitive generalization ability.

cs.CV↗

arXiv2024

MLD-EA: Check and Complete Narrative Coherence by Introducing Emotions and Actions

Narrative understanding and story generation are critical challenges in natural language processing (NLP), with much of the existing research focused on summarization and question-answering tasks. While previous studies have explored predicting plot endings and generating extended narratives, they often neglect the logical coherence within stories, leaving a significant gap in the field. To address this, we introduce the Missing Logic Detector by Emotion and Action (MLD-EA) model, which leverages large language models (LLMs) to identify narrative gaps and generate coherent sentences that integrate seamlessly with the story's emotional and logical flow. The experimental results demonstrate that the MLD-EA model enhances narrative understanding and story generation, highlighting LLMs' potential as effective logic checkers in story writing with logical coherence and emotional consistency. This work fills a gap in NLP research and advances border goals of creating more sophisticated and reliable story-generation systems.

cs.CL↗

arXiv2024

Time and Tokens: Benchmarking End-to-End Speech Dysfluency Detection

Speech dysfluency modeling is a task to detect dysfluencies in speech, such as repetition, block, insertion, replacement, and deletion. Most recent advancements treat this problem as a time-based object detection problem. In this work, we revisit this problem from a new perspective: tokenizing dysfluencies and modeling the detection problem as a token-based automatic speech recognition (ASR) problem. We propose rule-based speech and text dysfluency simulators and develop VCTK-token, and then develop a Whisper-like seq2seq architecture to build a new benchmark with decent performance. We also systematically compare our proposed token-based methods with time-based methods, and propose a unified benchmark to facilitate future research endeavors. We open-source these resources for the broader scientific community. The project page is available at https://rorizzz.github.io/

eess.AS↗

arXiv2024

Evaluating Four Methods for Detecting Differential Item Functioning in Large-Scale Assessments with More Than Two Groups

This study evaluated four multi-group differential item functioning (DIF) methods (the root mean square deviation approach, Wald-1, generalized logistic regression procedure, and generalized Mantel-Haenszel method) via Monte Carlo simulation of controlled testing conditions. These conditions varied in the number of groups, the ability and sample size of the DIF-contaminated group, the parameter associated with DIF, and the proportion of DIF items. When comparing Type-I error rates and powers of the methods, we showed that the RMSD approach yielded the best Type-I error rates when it was used with model-predicted cutoff values. Also, this approach was found to be overly conservative when used with the commonly used cutoff value of 0.1. Implications for future research for educational researchers and practitioners were discussed.

stat.AP↗

arXiv2024

Flexible, Model-Agnostic Method for Materials Data Extraction from Text Using General Purpose Language Models

Accurate and comprehensive material databases extracted from research papers are crucial for materials science and engineering, but their development requires significant human effort. With large language models (LLMs) transforming the way humans interact with text, LLMs provide an opportunity to revolutionize data extraction. In this study, we demonstrate a simple and efficient method for extracting materials data from full-text research papers leveraging the capabilities of LLMs combined with human supervision. This approach is particularly suitable for mid-sized databases and requires minimal to no coding or prior knowledge about the extracted property. It offers high recall and nearly perfect precision in the resulting database. The method is easily adaptable to new and superior language models, ensuring continued utility. We show this by evaluating and comparing its performance on GPT-3 and GPT-3.5/4 (which underlie ChatGPT), as well as free alternatives such as BART and DeBERTaV3. We provide a detailed analysis of the method's performance in extracting sentences containing bulk modulus data, achieving up to 90% precision at 96% recall, depending on the amount of human effort involved. We further demonstrate the method's broader effectiveness by developing a database of critical cooling rates for metallic glasses over twice the size of previous human curated databases.

cond-mat.mtrl-sci↗

arXiv2024

A star-based method for precise flux calibration of the Chinese Space Station Telescope (CSST) slitless spectroscopic survey

The upcoming Chinese Space Station Telescope (CSST) slitless spectroscopic survey poses a challenge of flux calibration, which requires a large number of flux-standard stars. In this work, we design an uncertainty-aware residual attention network, the UaRA-net, to derive the CSST SEDs with a resolution of R = 200 over the wavelength range of 2500-10000 Åusing LAMOST normalized spectra with a resolution of R = 2000 over the wavelength range of 4000-7000 Å. With the special structure and training strategy, the proposed model can not only provide accurate predictions of SEDs but also their corresponding errors. The precision of the predicted SEDs depends on effective temperature (Teff), wavelength, and the LAMOST spectral signal-to-noise ratios (SNRs), particularly in the GU band. For stars with Teff = 6000 K, the typical SED precisions in the GU band are 4.2%, 2.1%, and 1.5% at SNR values of 20, 40, and 80, respectively. As Teff increases to 8000 K, the precision increases to 1.2%, 0.6%, and 0.5%, respectively. The precision is higher at redder wavelengths. In the GI band, the typical SED precisions for stars with Teff = 6000 K increase to 0.3%, 0.1%, and 0.1% at SNR values of 20, 40, and 80, respectively. We further verify our model using the empirical spectra of the MILES and find good performance. The proposed method will open up new possibilities for optimal utilization of slitless spectra of the CSST and other surveys.

astro-ph.IM↗