arXiv subjects

Lan Wang

Publications and source records attributed to Lan Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

SEAL: Semantic Attention Learning for Long Video Representation

Long video understanding presents challenges due to the inherent high computational complexity and redundant temporal information. An effective representation for long videos must efficiently process such redundancy while preserving essential contents for downstream tasks. This paper introduces SEmantic Attention Learning (SEAL), a novel unified representation for long videos. To reduce computational complexity, long videos are decomposed into three distinct types of semantic entities: scenes, objects, and actions, allowing models to operate on a compact set of entities rather than a large number of frames or pixels. To further address redundancy, we propose an attention learning module that balances token relevance with diversity, formulated as a subset selection optimization problem. Our representation is versatile and applicable across various long video understanding tasks. Extensive experiments demonstrate that SEAL significantly outperforms state-of-the-art methods in video question answering and temporal grounding tasks across diverse benchmarks, including LVBench, MovieChat-1K, and Ego4D.

cs.CV↗

arXiv2025

Water Quality Data Imputation via A Fast Latent Factorization of Tensors with PID-based Optimizer

Water quality data can supply a substantial decision support for water resources utilization and pollution prevention. However, there are numerous missing values in water quality data due to inescapable factors like sensor failure, thereby leading to biased result for hydrological analysis and failing to support environmental governance decision accurately. A Latent Factorization of Tensors (LFT) with Stochastic Gradient Descent (SGD) proves to be an efficient imputation method. However, a standard SGD-based LFT model commonly surfers from the slow convergence that impairs its efficiency. To tackle this issue, this paper proposes a Fast Latent Factorization of Tensors (FLFT) model. It constructs an adjusted instance error into SGD via leveraging a nonlinear PID controller to incorporates the past, current and future information of prediction error for improving convergence rate. Comparing with state-of-art models in real world datasets, the results of experiment indicate that the FLFT model achieves a better convergence rate and higher accuracy.

cs.LG↗

arXiv2025

Confidence Diagram of Nonparametric Ranking for Uncertainty Assessment in Large Language Models Evaluation

We consider the inference for the ranking of large language models (LLMs). Alignment arises as a significant challenge to mitigate hallucinations in the use of LLMs. Ranking LLMs has proven to be an effective tool to improve alignment based on the best-of-$N$ policy. In this paper, we propose a new inferential framework for hypothesis testing among the ranking for language models. Our framework is based on a nonparametric contextual ranking framework designed to assess large language models' domain-specific expertise, leveraging nonparametric scoring methods to account for their sensitivity to the prompts. To characterize the combinatorial complexity of the ranking, we introduce a novel concept of confidence diagram, which leverages a Hasse diagram to represent the entire confidence set of rankings by a single directed graph. We show the validity of the proposed confidence diagram by advancing the Gaussian multiplier bootstrap theory to accommodate the supremum of independent empirical processes that are not necessarily identically distributed. Extensive numerical experiments conducted on both synthetic and real data demonstrate that our approach offers valuable insight into the evaluation for the performance of different LLMs across various medical domains.

stat.ML↗

arXiv2025

A Dual Active Black Hole Candidate with Mass Ratio ~7:1 in a Disk Galaxy

Dual active galactic nuclei (AGNs) with comparable masses are commonly witnessed among the major merged galaxies with interaction remnants. Considering almost every massive galaxy is associated with multiple dwarf satellites around it, minor mergers involving galaxies with disproportional stellar masses should be much more common than major mergers, which would naturally lead to black hole (BH) pairs with significantly different masses. However, dual AGNs generated by minor mergers involving one or two dwarf galaxies are exceptionally rare and understudied. Moreover, good estimates of the masses of both BHs are not yet available to test this idea. Here we report the evidence of a dual AGN candidate with mass ratio $\sim$7:1 located in an undisturbed disk galaxy. We identify the central BH with mass of $9.4 \times 10^6M_\odot$ from its radio emission as well as AGN-driven galactic-scale biconical outflows. The off-centered BH generates obvious broad and narrow emission-line regions, which gives us a robust estimation of a $1.3 \times 10^6M_\odot$ BH mass. We explore alternative scenarios for explaining the observational features of this system, including the complex gas kinematics triggered by central AGN activity and dust attenuation of the broad-line region of the central BH, finding that they failed to fully account for the kinematics of both the redshifted off-centered broad and narrow emission-line components.

astro-ph.GA↗

arXiv2024

Robust Inference for High-dimensional Linear Models with Heavy-tailed Errors via Partial Gini Covariance

This paper introduces the partial Gini covariance, a novel dependence measure that addresses the challenges of high-dimensional inference with heavy-tailed errors, often encountered in fields like finance, insurance, climate, and biology. Conventional high-dimensional regression inference methods suffer from inaccurate type I errors and reduced power in heavy-tailed contexts, limiting their effectiveness. Our proposed approach leverages the partial Gini covariance to construct a robust statistical inference framework that requires minimal tuning and does not impose restrictive moment conditions on error distributions. Unlike traditional methods, it circumvents the need for estimating the density of random errors and enhances the computational feasibility and robustness. Extensive simulations demonstrate the proposed method's superior power and robustness over standard high-dimensional inference approaches, such as those based on the debiased Lasso. The asymptotic relative efficiency analysis provides additional theoretical insight on the improved efficiency of the new approach in the heavy-tailed setting. Additionally, the partial Gini covariance extends to the multivariate setting, enabling chi-square testing for a group of coefficients. We illustrate the method's practical application with a real-world data example.

stat.ME↗

arXiv2024

Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines

The Structured Dialogue System, referred to as SuDoSys, is an innovative Large Language Model (LLM)-based chatbot designed to provide psychological counseling. SuDoSys leverages the World Health Organization (WHO)'s Problem Management Plus (PM+) guidelines to deliver stage-aware multi-turn dialogues. Existing methods for employing an LLM in multi-turn psychological counseling typically involve direct fine-tuning using generated dialogues, often neglecting the dynamic stage shifts of counseling sessions. Unlike previous approaches, SuDoSys considers the different stages of counseling and stores essential information throughout the counseling process, ensuring coherent and directed conversations. The system employs an LLM, a stage-aware instruction generator, a response unpacker, a topic database, and a stage controller to maintain dialogue flow. In addition, we propose a novel technique that simulates counseling clients to interact with the evaluated system and evaluate its performance automatically. When assessed using both objective and subjective evaluations, SuDoSys demonstrates its effectiveness in generating logically coherent responses. The system's code and program scripts for evaluation are open-sourced.

cs.CL↗

arXiv2024

An End-To-End Stuttering Detection Method Based On Conformer And BILSTM

Stuttering is a neurodevelopmental speech disorder characterized by common speech symptoms such as pauses, exclamations, repetition, and prolongation. Speech-language pathologists typically assess the type and severity of stuttering by observing these symptoms. Many effective end-to-end methods exist for stuttering detection, but a commonly overlooked challenge is the uncertain relationship between tasks involved in this process. Using a suitable multi-task strategy could improve stuttering detection performance. This paper presents a novel stuttering event detection model designed to help speech-language pathologists assess both the type and severity of stuttering. First, the Conformer model extracts acoustic features from stuttered speech, followed by a Long Short-Term Memory (LSTM) network to capture contextual information. Finally, we explore multi-task learning for stuttering and propose an effective multi-task strategy. Experimental results show that our model outperforms current state-of-the-art methods for stuttering detection. In the SLT 2024 Stuttering Speech Challenge based on the AS-70 dataset [1], our model improved the mean F1 score by 24.8% compared to the baseline method and achieved first place. On this basis, we conducted relevant extensive experiments on LSTM and multi-task learning strategies respectively. The results show that our proposed method improved the mean F1 score by 39.8% compared to the baseline method.

eess.AS↗

arXiv2024

Data Augmentation for End-to-end Code-switching Speech Recognition

Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited. In this paper, three novel approaches are proposed for code-switching data augmentation. Specifically, they are audio splicing with the existing code-switching data, and TTS with new code-switching texts generated by word translation or word insertion. Our experiments on 200 hours Mandarin-English code-switching dataset show that all the three proposed approaches yield significant improvements on code-switching ASR individually. Moreover, all the proposed approaches can be combined with recent popular SpecAugment, and an addition gain can be obtained. WER is significantly reduced by relative 24.0% compared to the system without any data augmentation, and still relative 13.0% gain compared to the system with only SpecAugment

cs.CL↗

arXiv2024

Apostle--Auriga: Effects of stellar feedback subgrid models on the evolution of angular momentum in disc galaxies

Utilizing the Apostle--Auriga simulations, which start from the same zoom-in initial conditions of Local Group-like systems but run with different galaxy formation subgrid models and hydrodynamic solvers, we study the impact of stellar feedback models on the evolution of angular momentum in disc galaxies. At $z = 0$, Auriga disc galaxies tend to exhibit higher specific angular momenta compared to their cross-matched Apostle counterparts. By tracing the evolution history of the Lagrangian mass tracers of the in-situ star particles in the $z = 0$ galaxies, we find that the specific angular momentum distributions of the gas tracers from the two simulations at the halo accretion time are relatively similar. The present-day angular momentum difference is mainly driven by the physical processes occurring inside dark matter haloes, especially galactic fountains. Due to the different subgrid implementations of stellar feedback processes, Auriga galaxies contain a high fraction of gas that has gone through recycled fountain (${\sim} 65$ per cent) which could acquire angular momentum through mixing with the high angular momentum circumgalactic medium (CGM). In Apostle, however, the fraction of gas that has undergone the recycled fountain process is significantly lower (down to ${\sim} 20$ per cent for Milky Way-sized galaxies) and the angular momentum acquisition from the CGM is marginal. As a result, the present-day Auriga galaxies overall have higher specific angular momenta.

astro-ph.GA↗

arXiv2024

Off-policy Evaluation in Doubly Inhomogeneous Environments

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we propose a class of latent factor models for the reward and observation transition functions, under which we develop a general OPE framework that consists of both model-based and model-free approaches. To our knowledge, this is the first paper that develops statistically sound OPE methods in offline RL with double inhomogeneities. It contributes to a deeper understanding of OPE in environments, where standard RL assumptions are not met, and provides several practical approaches in these settings. We establish the theoretical properties of the proposed value estimators and empirically show that our approach outperforms competing methods that ignore either temporal nonstationarity or individual heterogeneity. Finally, we illustrate our method on a data set from the Medical Information Mart for Intensive Care.

stat.ME↗

arXiv2024

Photometric properties of classical bulge and pseudo-bulge galaxies at $0.5\le z<1.0$

We compare the photometric properties and specific star formation rate (sSFR) of classical and pseudo-bulge galaxies with $M_* \ge 10^{9.5} \rm M_{\odot}$ at $0.5\le z<1.0$, selected from all five CANDELS fields. We also compare these properties of bulge galaxies at lower redshift selected from MaNGA survey (Hu et al. 2024). This paper aims to study the properties of galaxies with classical and pseudo-bulges at intermediate redshift, to compare the differences between different bulge types, and to understand the evolution of bulges with redshift. Galaxies are classified into classical bulge and pseudo-bulge samples according to the S$\mathrm{\acute{e}}$rsic index n of the bulge component based on results of two-component decomposition of galaxies, as well as the position of bulges on the Kormendy diagram. For the 105 classical bulge and 86 pseudo-bulge galaxies selected, we compare their size, luminosity, and sSFR of various components. At given stellar mass, most classical bulge galaxies have smaller effective radii, larger $B/T$, brighter and relatively larger bulges, and less active star formation than pseudo-bulge galaxies. Besides, the two types of galaxies have larger differences in sSFR at large radii than at the central region at both low and mid-redshifts. The differences between properties of the two types of bulge galaxies are in general smaller at mid-redshift than at low redshift, indicating that they are evolving to more distinct populations towards the local universe. Bulge type is correlated with the properties of their outer disks, and the correlation is already present at redshift as high as $0.5<z<1$.

astro-ph.GA↗

arXiv2024

Resolved properties of classical bulge and pseudo-bulge galaxies

We compare properties of classical and pseudo-bulges and properties of their hosting galaxies selected from the MaNGA survey. Bulge types are identified based on the S$\mathrm{\acute{e}}$rsic index n of bulge component and the position of bulges on the Kormandy diagram. For the 393 classical bulges and 422 pseudo-bulges selected and their hosting galaxies, we study their kinematic properties including a proxy for specific angular momentum and central velocity dispersion, their stellar population properties including stellar age, metallicity, and specific star formation rate, as well as HI fractions of the galaxies. Our results show that at given stellar mass, disc components of pseudo-bulge galaxies are younger, have more active star formation, rotate more, and may contain more HI content compared with those of classical bulge galaxies, and the differences are larger than those between bulges themselves. The correlations between bulge types and disc properties indicate that different types of bulges are shaped by different processes that may regulate both growth of central components and evolution of outer discs in galaxies. In addition, we propose a stellar mass dependent divider of central velocity dispersion to separate galaxies with classical bulges from those with pseudo-bulges in galaxy mass range of $10.4<\mathrm{log}(M_*/M_\odot)<11.4$: $\mathrm{log}(σ_0) = 0.23 \times \mathrm{log}(M_*/M_\odot)-0.46$. Galaxies with larger/smaller $σ_0$ can be classified as hosts of classical/pseudo-bulges.

astro-ph.GA↗

arXiv2024

Kinematic morphology of low-mass galaxies in IllustrisTNG

The origin of diverse kinematic morphologies observed in low-mass galaxies is unclear. In this study, we investigate the kinematic morphologies of central galaxies with stellar mass $10^{8.5-9.0} M_\odot$ at $z=0$ in the TNG50-1 cosmological simulation. The majority of the low-mass galaxies in TNG50-1 are dispersion-dominated, consistent with observations. By tracing the evolutionary histories of simulated low-mass galaxies, we find that while most stars form in rotating cold gas discs, the orientation of the star-forming discs relative to the galaxies may evolve with cosmic time. If the cold gas disc remains aligning with the galaxy during its evolution, stars formed at different times share the same rotational direction, leading to a rotation-dominated system. On the contrary, frequent misalignment of cold gas disc would result in a dispersion-dominated system. In addition, we also find that the two-body scattering can have a non-negligible numerical heating effect on the simulated galaxy morphology, especially at central regions of galaxies and for relatively low-mass galaxies. By comparing results of simulations with different resolutions, our results suggest that the simulated morphology of galaxies is roughly reliable when their number of stellar particles exceeds about $10^{4}$, and bulge morphology of galaxies can not be resolved robustly at the resolution level of TNG50-1.

astro-ph.GA↗

arXiv2024

Representation learning with CGAN for casual inference

Conditional Generative Adversarial Nets (CGAN) is often used to improve conditional image generation performance. However, there is little research on Representation learning with CGAN for causal inference. This paper proposes a new method for finding representation learning functions by adopting the adversarial idea. We apply the pattern of CGAN and theoretically emonstrate the feasibility of finding a suitable representation function in the context of two distributions being balanced. The theoretical result shows that when two distributions are balanced, the ideal representation function can be found and thus can be used to further research.

cs.LG↗

arXiv2024

Multi-species optically addressable spin defects in a van der Waals material

Optically addressable spin defects hosted in two-dimensional van der Waals materials represent a new frontier for quantum technologies, promising to lead to a new class of ultrathin quantum sensors and simulators. Recently, hexagonal boron nitride (hBN) has been shown to host several types of optically addressable spin defects, thus offering a unique opportunity to simultaneously address and utilise various spin species in a single material. Here we demonstrate an interplay between two separate spin species within a single hBN crystal, namely $S=1$ boron vacancy defects and visible emitter spins. We unambiguously prove that the visible emitters are $S=\frac{1}{2}$ spins and further demonstrate room temperature coherent control and optical readout of both spin species. Importantly, by tuning the two spin species into resonance with each other, we observe cross-relaxation indicating strong inter-species dipolar coupling. We then demonstrate magnetic imaging using the $S=\frac{1}{2}$ defects, both under ambient and cryogenic conditions, and leverage their lack of intrinsic quantization axis to determine the anisotropic magnetic susceptibility of a test sample. Our results establish hBN as a versatile platform for quantum technologies in a van der Waals host at room temperature.

cond-mat.mes-hall↗

arXiv2024

Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition

The Mandarin Chinese language is known to be strongly influenced by a rich set of regional accents, while Mandarin speech with each accent is quite low resource. Hence, an important task in Mandarin speech recognition is to appropriately model the acoustic variabilities imposed by accents. In this paper, an investigation of implicit and explicit use of accent information on a range of deep neural network (DNN) based acoustic modelling techniques is conducted. Meanwhile, approaches of multi-accent modelling including multi-style training, multi-accent decision tree state tying, DNN tandem and multi-level adaptive network (MLAN) tandem hidden Markov model (HMM) modelling are combined and compared in this paper. On a low resource accented Mandarin speech recognition task consisting of four regional accents, an improved MLAN tandem HMM systems explicitly leveraging the accent information was proposed and significantly outperformed the baseline accent independent DNN tandem systems by 0.8%-1.5% absolute (6%-9% relative) in character error rate after sequence level discriminative training and adaptation.

eess.AS↗

arXiv2024

Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition

Disordered speech recognition profound implications for improving the quality of life for individuals afflicted with, for example, dysarthria. Dysarthric speech recognition encounters challenges including limited data, substantial dissimilarities between dysarthric and non-dysarthric speakers, and significant speaker variations stemming from the disorder. This paper introduces Perceiver-Prompt, a method for speaker adaptation that utilizes P-Tuning on the Whisper large-scale model. We first fine-tune Whisper using LoRA and then integrate a trainable Perceiver to generate fixed-length speaker prompts from variable-length inputs, to improve model recognition of Chinese dysarthric speech. Experimental results from our Chinese dysarthric speech dataset demonstrate consistent improvements in recognition performance with Perceiver-Prompt. Relative reduction up to 13.04% in CER is obtained over the fine-tuned Whisper.

eess.AS↗

arXiv2024

Bayesian Learning for Deep Neural Network Adaptation

A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techniques play a vital role to reduce the mismatch. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensure robustness. When the amount of speaker level data is limited, speaker adaptation is prone to overfitting and poor generalization. To address the issue, this paper proposes a full Bayesian learning based DNN speaker adaptation framework to model speaker-dependent (SD) parameter uncertainty given limited speaker specific adaptation data. This framework is investigated in three forms of model based DNN adaptation techniques: Bayesian learning of hidden unit contributions (BLHUC), Bayesian parameterized activation functions (BPAct), and Bayesian hidden unit bias vectors (BHUB). In the three methods, deterministic SD parameters are replaced by latent variable posterior distributions for each speaker, whose parameters are efficiently estimated using a variational inference based approach. Experiments conducted on 300-hour speed perturbed Switchboard corpus trained LF-MMI TDNN/CNN-TDNN systems suggest the proposed Bayesian adaptation approaches consistently outperform the deterministic adaptation on the NIST Hub5'00 and RT03 evaluation sets. When using only the first five utterances from each speaker as adaptation data, significant word error rate reductions up to 1.4% absolute (7.2% relative) were obtained on the CallHome subset. The efficacy of the proposed Bayesian adaptation techniques is further demonstrated in a comparison against the state-of-the-art performance obtained on the same task using the most recent systems reported in the literature.

cs.SD↗