BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Xiaodong Li

Xiaodong Li contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
eess.ASSoundMachine Learningcond-mat.supr-coneess.SPArtificial IntelligenceComputer Visioncond-mat.str-elmath.OCphysics.chem-phphysics.flu-dynastro-ph.GAastro-ph.IMastro-ph.SRComputation and Languagecond-mat.mtrl-sciInformation Retrievalmath.STMultimediaphysics.data-anphysics.ins-detq-fin.STq-fin.TRStatistics Theory

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
33works
0followers
24topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

33 published item(s)

preprint2026arXiv

Advancing multi-site emission control: A physics-informed transfer learning framework with mixture of experts for carbon-pollutant synergy

Municipal solid waste incineration is increasingly central to urban waste management, yet its sustainability benefit depends on controlling carbon emissions and multiple air pollutants under highly heterogeneous operating conditions. Current data-driven models are often accurate within individual plants but are difficult to transfer across facilities, limiting their value for scalable emission-control strategies. Here we show that multi-site emission behaviour can be represented through transferable system-level structures when physical constraints, operating-regime heterogeneity and carbon--pollutant coupling are jointly considered. We develop a physics-informed transfer learning framework built on a carbon--pollutant mixture-of-experts model, which combines regime-dependent expert routing with conservation-based regularization and a carbon--pollutant synergistic index for integrated risk evaluation. Across 13 municipal solid waste incineration plants, the model captured both pollutant-specific emissions and system-level risk, achieving source-domain average pollutant $R^2$ values of 0.668--0.904 and CPSI $R^2$ values of 0.666--0.970. After transfer from a reference facility to 12 target plants, average pollutant $R^2$ remained between 0.661 and 0.842, while CPSI retained comparable transferability ($R^2$ = 0.610--0.841). Expert-utilization patterns further indicate that adaptation occurs through structured re-weighting of operating regimes rather than complete model re-learning. By extending the learned representation into an interpretable digital twin, this framework provides a route from emission prediction to regime-aware operational navigation, supporting scalable carbon--pollutant synergistic control across heterogeneous waste-to-energy systems.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Personalized Multi-Interest Modeling for Cross-Domain Recommendation to Cold-Start Users

Cross-domain recommendation (CDR) has demonstrated to be an effective solution for alleviating the user cold-start issue. By leveraging rich user-item interactions available in a richly informative source domain, CDR could improve the recommendation performance for cold-start users in the target domain. Previous CDR approaches mostly adhere the Embedding and Mapping (EMCDR) paradigm, which learns a user-shared mapping function to transfer users' preference from the source domain to the target domain, neglecting users' personalized preference. Recent CDR approaches further leverage the meta-learning paradigm, considering the CDR task for each user independently and learning user-specific mapping functions for each user. However, they mostly learn representations for each user individually, which ignores the common preference between different users, neglecting valuable information for CDR. In addition, all these approaches usually summarize the user's preference into an overall representation, which can hardly capture the user's multi-interest preference. To this end, we propose a personalized multi-interest modeling framework for CDR to cold-start users, termed as NF-NPCDR. Specifically, we propose a personalized preference encoder that enhances the neural process (NP) with the normalizing flow (NF) to convert the Gaussian (unimodal) distribution to a multimodal distribution, providing a novel way to capture the user's personalized multi-interest preference. Then, we propose a common preference encoder with a preference pool to capture the common preference between different users. Furthermore, we introduce a stochastic adaptive decoder to incorporate both the personalized and common preference for cold-start users, adaptively modulating both preference for better recommendation.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Space-time nonlinear reduced-order modelling for unsteady flows

This work investigates projection-based Reduced-Order Models (ROMs) formulated in the frequency domain, employing a space-time basis constructed with Spectral Proper Orthogonal Decomposition to efficiently represent dominant spatio-temporal coherent structures. Although frequency domain formulations are well suited to capturing time-periodic solutions, such as unstable periodic orbits, this study focusses on modelling statistically stationary flows by computing long-time solutions that approximate their underlying statistics. In contrast to traditional ROMs based solely on spatial modes, a space-time formulation achieves simultaneous reduction in both space and time. This is accomplished by Galerkin projection of the Navier-Stokes equations onto the basis using a space-time inner product, yielding a quadratic algebraic system of equations in the unknown amplitude coefficients. Solutions of the ROM are obtained by identifying amplitude coefficients that minimise an objective function corresponding to the sum of the squares of the residuals of the algebraic system across all frequencies and modes, quantifying the aggregate violation of momentum conservation within the reduced subspace. A robust gradient-based optimisation algorithm is employed to identify the minima of this objective function. The method is demonstrated for chaotic flow in a two-dimensional lid-driven cavity at $Re=20{,}000$, where solutions with extended temporal periods approximately fifteen times the dominant shear layer time scale are sought. Even without employing closure models to represent the truncated spatio-temporal triadic interactions, multiple ROM solutions are found that successfully reproduce the dominant dynamical flow features and predict the statistical distribution of turbulent quantities with good fidelity, although they tend to overpredict energy at spatio-temporal scales near the truncation boundary.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning

Prototype-based Personalized Federated Learning (ProtoPFL) enables efficient multi-domain adaptation by communicating compact class prototypes, but directly sharing them poses privacy risks. A common defense involves per-example $\ell_2$ clipping before prototype computation to bound sensitivity, followed by isotropic Gaussian noise to enforce Local Differential Privacy (LDP). However, Isotropic Gaussian Prototype Perturbation (IGPP) typically over-perturbs discriminative dimensions and struggles to balance the clipping threshold with representation fidelity. In this paper, we propose VPDR, a client-side privacy plug-in that seamlessly integrates into existing ProtoPFLs. Motivated by the observation that dimension-wise class variance reflects discriminability, we introduce Variance-adaptive Prototype Perturbation (VPP), which allocates less noise to discriminative subspaces, preserving semantic separability while ensuring privacy. We further develop Distillation-guided Clipping Regularization (DCR), which enables feature norms to adaptively concentrate near the predefined clipping threshold while maintaining prediction consistency. Theoretical analysis shows that our groupwise mechanism provides privacy guarantees no weaker than the isotropic baseline under the same privacy constraints. Extensive experiments on multi-domain benchmarks demonstrate that VPDR achieves a superior privacy-utility trade-off, outperforming IGPP in personalized federated fine-tuning without sacrificing robustness against realistic attacks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

When to Invoke: Refining LLM Fairness with Toxicity Assessment

Large Language Models (LLMs) are increasingly used for toxicity assessment in online moderation systems, where fairness across demographic groups is essential for equitable treatment. However, LLMs often produce inconsistent toxicity judgements for subtle expressions, particularly those involving implicit hate speech, revealing underlying biases that are difficult to correct through standard training. This raises a key question that existing approaches often overlook: when should corrective mechanisms be invoked to ensure fair and reliable assessments? To address this, we propose FairToT, an inference-time framework that enhances LLM fairness through prompt-guided toxicity assessment. FairToT identifies cases where demographic-related variation is likely to occur and determines when additional assessment should be applied. In addition, we introduce two interpretable fairness indicators that detect such cases and improve inference consistency without modifying model parameters. Experiments on benchmark datasets show that FairToT reduces group-level disparities while maintaining stable and reliable toxicity predictions, demonstrating that inference-time refinement offers an effective and practical approach for fairness improvement in LLM-based toxicity assessment systems. The source code can be found at https://aisuko.github.io/fair-tot/.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A deep complex multi-frame filtering network for stereophonic acoustic echo cancellation

In hands-free communication system, the coupling between loudspeaker and microphone generates echo signal, which can severely influence the quality of communication. Meanwhile, various types of noise in communication environments further reduce speech quality and intelligibility. It is difficult to extract the near-end signal from the microphone signal within one step, especially in low signal-to-noise ratio scenarios. In this paper, we propose a deep complex network approach to address this issue. Specially, we decompose the stereophonic acoustic echo cancellation into two stages, including linear stereophonic acoustic echo cancellation module and residual echo suppression module, where both modules are based on deep learning architectures. A multi-frame filtering strategy is introduced to benefit the estimation of linear echo by capturing more inter-frame information. Moreover, we decouple the complex spectral mapping into magnitude estimation and complex spectrum refinement. Experimental results demonstrate that our proposed approach achieves stage-of-the-art performance over previous advanced algorithms under various conditions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Neural Beam Filter for Real-time Multi-channel Speech Enhancement

Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these approaches. To handle these problems, this paper designs a causal neural beam filter that fully exploits the spatial-spectral information in the beam domain. Specifically, multiple beams are designed to steer towards all directions using a parameterized super-directive beamformer in the first stage. After that, the neural spatial filter is learned by simultaneously modeling the spatial and spectral discriminability of the speech and the interference, so as to extract the desired speech coarsely in the second stage. Finally, to further suppress the interference components especially at low frequencies, a residual estimation module is adopted to refine the output of the second stage. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art multi-channel methods on the generated multi-channel speech dataset based on the DNS-Challenge dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Efficient Joint DOA and TOA Estimation for Indoor Positioning with 5G Picocell Base Stations

The ubiquity, large bandwidth, and spatial diversity of the fifth generation (5G) cellular signal render it a promising candidate for accurate positioning in indoor environments where the global navigation satellite system (GNSS) signal is absent. In this paper, a joint angle and delay estimation (JADE) scheme is designed for 5G picocell base stations (gNBs) which addresses two crucial issues to make it both effective and efficient in realistic indoor environments. Firstly, the direction-dependence of the array modeling error for picocell gNB as well as its impact on JADE is revealed. This error is mitigated by fitting the array response measurements to a vector-valued function and pre-calibrating the ideal steering-vector with the fitted function. Secondly, based on the deployment reality that 5G picocell gNBs only have a small-scale antenna array but have a large signal bandwidth, the proposed scheme decouples the estimation of time-of-arrival (TOA) and direction-of-arrival (DOA) to reduce the huge complexity induced by two-dimensional joint processing. It employs the iterative-adaptive-approach (IAA) to resolve multipath signals in the TOA domain, followed by a conventional beamformer (CBF) to retrieve the desired line-of-sight DOA. By further exploiting a dimension-reducing pre-processing module and accelerating spectrum computing by fast Fourier transforms, an efficient implementation is achieved for real-time JADE. Numerical simulations demonstrate the superiority of the proposed method in terms of DOA estimation accuracy. Field tests show that a triangulation positioning error of 0.44 m is achieved for 90% cases using only DOAs estimated at two separated receiving points.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Enhancing Column Generation by a Machine-Learning-Based Pricing Heuristic for Graph Coloring

Column Generation (CG) is an effective method for solving large-scale optimization problems. CG starts by solving a sub-problem with a subset of columns (i.e., variables) and gradually includes new columns that can improve the solution of the current subproblem. The new columns are generated as needed by repeatedly solving a pricing problem, which is often NP-hard and is a bottleneck of the CG approach. To tackle this, we propose a Machine-Learning-based Pricing Heuristic (MLPH)that can generate many high-quality columns efficiently. In each iteration of CG, our MLPH leverages an ML model to predict the optimal solution of the pricing problem, which is then used to guide a sampling method to efficiently generate multiple high-quality columns. Using the graph coloring problem, we empirically show that MLPH significantly enhancesCG as compared to six state-of-the-art methods, and the improvement in CG can lead to substantially better performance of the branch-and-price exact method.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Hierarchical Deep Reinforcement Learning for VWAP Strategy Optimization

Designing an intelligent volume-weighted average price (VWAP) strategy is a critical concern for brokers, since traditional rule-based strategies are relatively static that cannot achieve a lower transaction cost in a dynamic market. Many studies have tried to minimize the cost via reinforcement learning, but there are bottlenecks in improvement, especially for long-duration strategies such as the VWAP strategy. To address this issue, we propose a deep learning and hierarchical reinforcement learning jointed architecture termed Macro-Meta-Micro Trader (M3T) to capture market patterns and execute orders from different temporal scales. The Macro Trader first allocates a parent order into tranches based on volume profiles as the traditional VWAP strategy does, but a long short-term memory neural network is used to improve the forecasting accuracy. Then the Meta Trader selects a short-term subgoal appropriate to instant liquidity within each tranche to form a mini-tranche. The Micro Trader consequently extracts the instant market state and fulfils the subgoal with the lowest transaction cost. Our experiments over stocks listed on the Shanghai stock exchange demonstrate that our approach outperforms baselines in terms of VWAP slippage, with an average cost saving of 1.16 base points compared to the optimal baseline.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Lock-in effect of over-tip shock waves and identification of the escaping vortex-shedding mode in pressure-driven tip leakage flow

Time-resolved schlieren visualization is used to investigate the unsteady flow structures of tip leakage flows in the clearance region. A common generic blade tip model is created and tested in a wind tunnel under operating conditions ranging from low-subsonic to transonic. A multi-cutoff superposition technique is developed to achieve better flow visualization. Quantitative image processing is performed to extract the flow structures and the instability modes. Additional numerical simulations are performed to help classify the observed flow structures. Unsteady flow structures such as over-tip shock oscillation, shear-layer flapping, and vortex shedding are revealed by Fourier analysis and dynamic mode decomposition. The results show that, under subsonic conditions, the trigger position of the shear layer instability is monotonically delayed as the blade loading increases; however, this pattern is reversed under transonic conditions. This implies that flow compressibility, flow acceleration, and the oscillation of over-tip shock waves are critical factors related to tip flow instabilities. The over-tip shock waves are observed to be locked-in by frequency and position with the shear-layer flapping mode. An intermittent flow mode, termed the escaping vortex-shedding mode, is also observed. These flow structures are key factors in the control of tip leakage flows. Based on the observed flow dynamics, a schematic drawing of tip leakage flow structures and related motions is proposed. Finally, an experimental dataset is obtained for the validation of future numerical simulations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer

It is highly desirable that speech enhancement algorithms can achieve good performance while keeping low latency for many applications, such as digital hearing aids, acoustically transparent hearing devices, and public address systems. To improve the performance of traditional low-latency speech enhancement algorithms, a deep filter-bank equalizer (FBE) framework was proposed, which integrated a deep learning-based subband noise reduction network with a deep learning-based shortened digital filter mapping network. In the first network, a deep learning model was trained with a controllable small frame shift to satisfy the low-latency demand, i.e., $\le$ 4 ms, so as to obtain (complex) subband gains, which could be regarded as an adaptive digital filter in each frame. In the second network, to reduce the latency, this adaptive digital filter was implicitly shortened by a deep learning-based framework, and was then applied to noisy speech to reconstruct the enhanced speech without the overlap-add method. Experimental results on the WSJ0-SI84 corpus indicated that the proposed deep FBE with only 4-ms latency achieved much better performance than traditional low-latency speech enhancement algorithms in terms of the indices such as PESQ, STOI, and the amount of noise reduction.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

MDNet: Learning Monaural Speech Enhancement from Deep Prior Gradient

While traditional statistical signal processing model-based methods can derive the optimal estimators relying on specific statistical assumptions, current learning-based methods further promote the performance upper bound via deep neural networks but at the expense of high encapsulation and lack adequate interpretability. Standing upon the intersection between traditional model-based methods and learning-based methods, we propose a model-driven approach based on the maximum a posteriori (MAP) framework, termed as MDNet, for single-channel speech enhancement. Specifically, the original problem is formulated into the joint posterior estimation w.r.t. speech and noise components. Different from the manual assumption toward the prior terms, we propose to model the prior distribution via networks and thus can learn from training data. The framework takes the unfolding structure and in each step, the target parameters can be progressively estimated through explicit gradient descent operations. Besides, another network serves as the fusion module to further refine the previous speech estimation. The experiments are conducted on the WSJ0-SI84 and Interspeech2020 DNS-Challenge datasets, and quantitative results show that the proposed approach outshines previous state-of-the-art baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Nonconvex Matrix Completion with Linearly Parameterized Factors

Techniques of matrix completion aim to impute a large portion of missing entries in a data matrix through a small portion of observed ones. In practice including collaborative filtering, prior information and special structures are usually employed in order to improve the accuracy of matrix completion. In this paper, we propose a unified nonconvex optimization framework for matrix completion with linearly parameterized factors. In particular, by introducing a condition referred to as Correlated Parametric Factorization, we can conduct a unified geometric analysis for the nonconvex objective by establishing uniform upper bounds for low-rank estimation resulting from any local minimum. Perhaps surprisingly, the condition of Correlated Parametric Factorization holds for important examples including subspace-constrained matrix completion and skew-symmetric matrix completion. The effectiveness of our unified nonconvex optimization method is also empirically illustrated by extensive numerical simulations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Observation of three superconducting transitions in the pressurized CDW-bearing compound TaTe2

Transition metal dichalcogenides host a wide variety of lattice and electronic structures, as well as corresponding exotic physical properties, especially under certain tuning conditions. Here, we are the first to report the observation of pressure-induced three superconducting transitions in TaTe2, a charge density wave (CDW) - bearing layered transition-metal dichalcogenide that is metallic but not superconducting at ambient pressure. We find that its CDW state can be easily suppressed upon increasing pressure up to ~ 1 GPa. A superconducting state then emerges from the suppressed CDW state and persists to the pressure about 7 GPa. Unexpectedly, another superconducting state appears at ~ 11 GPa within the same monoclinic (M) structure of its ambient-pressure one. Upon further compression to 21 GPa, a third superconducting state with higher Tc appears from a high-pressure (HP) phase. Our experimental results suggest that the pressure-induced three superconducting transitions in TaTe2 are respectively driven by the suppression of the CDW state, the change of the angle in the M phase and the transition of M-to-HP phase. These results demonstrate not only the versatile nature of this correlated electron system, but also the first experimental example that shows the pressure-induced evolution from a CDW state to three superconducting states driven by different mechanisms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Pseudo-labelling and Meta Reweighting Learning for Image Aesthetic Quality Assessment

In the tasks of image aesthetic quality evaluation, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets. To reduce the error in labeling and solve the problem of normal data distribution, we propose a new aesthetic mixed dataset with classification and regression called AMD-CR, and we train a meta reweighting network to reweight the loss of training data differently. In addition, we provide a training strategy acccording to different stages, based on pseudo labels of the binary classification task, and then we use it for aesthetic training acccording to different stages in classification and regression tasks. In the construction of the network structure, we construct an aesthetic adaptive block (AAB) structure that can adapt to any size of the input images. Besides, we also use the efficient channel attention (ECA) to strengthen the feature extracting ability of each task. The experimental result shows that our method improves 0.1112 compared with the conventional methods in SROCC. The method can also help to find best aesthetic path planning for unmanned aerial vehicles (UAV) and vehicles.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Quasi-uniaxial pressure induced superconductivity in stoichiometric compound UTe$_2$

The recent discovery of superconductivity in heavy Fermion compound UTe2, a candidate topological and triplet-paired superconductor, has aroused widespread interest. However, to date, there is no consensus on whether the stoichiometric sample of UTe2 is superconducting or not due to lack of reliable evidence to distinguish the difference between the nominal and real compositions of samples. Here, we are the first to clarify that the stoichiometric UT2 is non-superconducting at ambient pressure and under hydrostatic pressure up to 6 GPa, however we find that it can be compressed into superconductivity by application of quasi-uniaxial pressure. Measurements of resistivity, magnetoresistance and susceptibility reveal that the quasi-uniaxial pressure results in a suppression of the Kondo coherent state seen at ambient pressure, and then leads to a superconductivity initially emerged on the ab-plane at 1.5 GPa. At 4.8 GPa, the superconductivity is developed in three crystallographic directions. The superconducting state coexists with an exotic magnetic ordered state that develops just below the onset temperature of the superconducting transition. The discovery of the quasi-uniaxial-pressure-induced superconductivity with exotic magnetic state in the stoichiometric UTe2 not only provide new understandings on this compound, but also highlight the vital role of Te deficiency in developing the superconductivity at ambient pressures.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Ranking Constraint Relaxations for Mixed Integer Programs Using a Machine Learning Approach

Solving large-scale Mixed Integer Programs (MIP) can be difficult without advanced algorithms such as decomposition based techniques. Even if a decomposition technique might be appropriate, there are still many possible decompositions for any large MIP and it may not be obvious which will be the most effective. This paper presents a comprehensive analysis of the predictive capabilities of a Machine Learning ranking (ML) function for predicting the quality of Mixed Integer Programming (MIP) decompositions created via constraint relaxation. In this analysis, the role of instance similarity and ML prediction quality is explored, as well as the benchmarking of a ML ranking function against existing heuristic functions. For this analysis, a new dataset consisting of over 40000 unique decompositions sampled from across 24 instances from the MIPLIB2017 library has been established. These decompostions have been created by both a greedy relaxation algorithm as well as a population based multi-objective algorithm, which has previously been shown to produce high quality decompositions. In this paper, we demonstrate that a ML ranking function is able to provide state-of-the-art predictions when benchmarked against existing heuristic ranking functions. Additionally, we demonstrate that by only considering a small set of features related to the relaxed constraints in each decomposition, a ML ranking function is still able to be competitive with heuristic techniques. Such a finding is promising for future constraint relaxation approaches, as these features can be used to guide decomposition creation. Finally, we highlight where a ML ranking function would be beneficial in a decomposition creation framework.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Searching for multiple populations in star clusters using the China Space Station Telescope

Multiple stellar populations (MPs) in most star clusters older than 2 Gyr, as seen by lots of spectroscopic and photometric studies, have led to a significant challenge to the traditional view of star formation. In this field, space-based instruments, in particular the Hubble Space Telescope (HST), have made a breakthrough as they significantly improved the efficiency of detecting MPs in crowding stellar fields by images. The China Space Station Telescope (CSST) and the HST are sensitive to a similar wavelength interval, but it covers a field of view which is about 5-8 times wider than that of HST. One of its instruments, the Multi-Channel Imager (MCI), will have multiple filters covering a wide wavelength range from NUV to NIR, making the CSST a potentially powerful tool for studying MPs in clusters. In this work, we evaluate the efficiency of the designed filters for the MCI/CSST in revealing MPs in different color-magnitude diagrams (CMDs). We find that CMDs made with MCI/CSST photometry in appropriate UV filters are powerful tools to disentangle stellar populations with different abundances of He, C, N, O and Mg. On the contrary, the traditional CMDs are blind to multiple populations in globular clusters (GCs). We show that CSST has the potential of being the spearhead instrument for investigating MPs in GCs in the next decades.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

TaylorBeamformer: Learning All-Neural Beamformer for Multi-Channel Speech Enhancement from Taylor's Approximation Theory

While existing end-to-end beamformers achieve impressive performance in various front-end speech processing tasks, they usually encapsulate the whole process into a black box and thus lack adequate interpretability. As an attempt to fill the blank, we propose a novel neural beamformer inspired by Taylor's approximation theory called TaylorBeamformer for multi-channel speech enhancement. The core idea is that the recovery process can be formulated as the spatial filtering in the neighborhood of the input mixture. Based on that, we decompose it into the superimposition of the 0th-order non-derivative and high-order derivative terms, where the former serves as the spatial filter and the latter is viewed as the residual noise canceller to further improve the speech quality. To enable end-to-end training, we replace the derivative operations with trainable networks and thus can learn from training data. Extensive experiments are conducted on the synthesized dataset based on LibriSpeech and results show that the proposed approach performs favorably against the previous advanced baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A low phase noise microwave source for high performance CPT Rb atomic clock

Phase noise of the frequency synthesizer is one of the main limitations to the short-term stability of microwave atomic clocks. In this work, we demonstrated a low-noise, simple-architecture microwave frequency synthesizer for a coherent population trapping (CPT) clock. The synthesizer is mainly composed of a 100 MHz oven controlled crystal oscillator (OCXO), a microwave comb generator and a direct digital synthesizer (DDS). The absolute phase noises of 3.417 GHz signal are measured to be -55 dBc/Hz, -81 dBc/Hz, -111 dBc/Hz and -134 dBc/Hz, respectively, for 1 Hz, 10 Hz, 100 Hz and 1 kHz offset frequencies, which shows only 1 dB deterioration at the second harmonic of the modulation frequency of the atomic clock. The estimated frequency stability of intermodulation effect is 4.7*10^{-14} at 1s averaging time, which is about half order of magnitude lower than that of the state-of-the-art CPT Rb clock. Our work offers an alternative microwave synthesizer for high-performance CPT Rb atomic clock.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

A Robust Maximum Likelihood Distortionless Response Beamformer based on a Complex Generalized Gaussian Distribution

For multichannel speech enhancement, this letter derives a robust maximum likelihood distortionless response beamformer by modeling speech sparse priors with a complex generalized Gaussian distribution, where we refer to as the CGGD-MLDR beamformer. The proposed beamformer can be regarded as a generalization of the minimum power distortionless response beamformer and its improved variations. For narrowband applications, we also reveal that the proposed beamformer reduces to the minimum dispersion distortionless response beamformer, which has been derived with the ${{\ell}_{p}}$-norm minimization. The mechanisms of the proposed beamformer in improving the robustness are clearly pointed out and experimental results show its better performance in PESQ improvement.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

ICASSP 2021 Deep Noise Suppression Challenge: Decoupling Magnitude and Phase Optimization with a Two-Stage Deep Network

It remains a tough challenge to recover the speech signals contaminated by various noises under real acoustic environments. To this end, we propose a novel system for denoising in the complicated applications, which is mainly comprised of two pipelines, namely a two-stage network and a post-processing module. The first pipeline is proposed to decouple the optimization problem w:r:t: magnitude and phase, i.e., only the magnitude is estimated in the first stage and both of them are further refined in the second stage. The second pipeline aims to further suppress the remaining unnatural distorted noise, which is demonstrated to sufficiently improve the subjective quality. In the ICASSP 2021 Deep Noise Suppression (DNS) Challenge, our submitted system ranked top-1 for the real-time track 1 in terms of Mean Opinion Score (MOS) with ITU-T P.808 framework.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Universal quantum transition from superconducting to insulating states in pressurized Bi2Sr2CaCu2O8+δ superconductors

Copper oxide superconductors have continually fascinated the communities of condensed matter physics and material sciences because they host the highest ambient-pressure superconducting transition temperature (Tc) and mysterious physics. Searching for the universal correlation between the superconducting state and its normal state or neighboring ground state is believed to be an effective way for finding clues to elucidate the underlying mechanism of the superconductivity. One of the common pictures for the copper oxide superconductors is that a well-behaved metallic phase will present after the superconductivity is entirely suppressed by chemical doping or application of the magnetic field. Here, we report a different observation of universal quantum transition from superconducting state to insulating-like state under pressure in the under-, optimally- and over-doped Bi2212 superconductors with two CuO2 planes in a unit cell. The same phenomenon has been also found in the Bi2201 superconductor with one CuO2 plane and the Bi2223 superconductor with three CuO2 planes in a unit cell. These results not only provide fresh information but also pose a new challenge for achieving a unified understanding on the underlying physics of the high-Tc superconductivity.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Recursive Network with Dynamic Attention for Monaural Speech Enhancement

A person tends to generate dynamic attention towards speech under complicated environments. Based on this phenomenon, we propose a framework combining dynamic attention and recursive learning together for monaural speech enhancement. Apart from a major noise reduction network, we design a separated sub-network, which adaptively generates the attention distribution to control the information flow throughout the major network. To effectively decrease the number of trainable parameters, recursive learning is introduced, which means that the network is reused for multiple stages, where the intermediate output in each stage is correlated with a memory mechanism. As a result, a more flexible and better estimation can be obtained. We conduct experiments on TIMIT corpus. Experimental results show that the proposed architecture obtains consistently better performance than recent state-of-the-art models in terms of both PESQ and STOI scores.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Convolutional Recurrent Neural Network Based Progressive Learning for Monaural Speech Enhancement

Recently, progressive learning has shown its capacity to improve speech quality and speech intelligibility when it is combined with deep neural network (DNN) and long short-term memory (LSTM) based monaural speech enhancement algorithms, especially in low signal-to-noise ratio (SNR) conditions. Nevertheless, due to a large number of parameters and high computational complexity, it is hard to implement in current resource-limited micro-controllers and thus, it is essential to significantly reduce both the number of parameters and the computational load for practical applications. For this purpose, we propose a novel progressive learning framework with causal convolutional recurrent neural networks called PL-CRNN, which takes advantage of both convolutional neural networks and recurrent neural networks to drastically reduce the number of parameters and simultaneously improve speech quality and speech intelligibility. Numerous experiments verify the effectiveness of the proposed PL-CRNN model and indicate that it yields consistent better performance than the PL-DNN and PL-LSTM algorithms and also it gets results close even better than the CRNN in terms of objective measurements. Compared with PL-DNN, PL-LSTM, and CRNN, the proposed PL-CRNN algorithm can reduce the number of parameters up to 93%, 97%, and 92%, respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Dynamic Attention Based Generative Adversarial Network with Phase Post-Processing for Speech Enhancement

The generative adversarial networks (GANs) have facilitated the development of speech enhancement recently. Nevertheless, the performance advantage is still limited when compared with state-of-the-art models. In this paper, we propose a powerful Dynamic Attention Recursive GAN called DARGAN for noise reduction in the time-frequency domain. Different from previous works, we have several innovations. First, recursive learning, an iterative training protocol, is used in the generator, which consists of multiple steps. By reusing the network in each step, the noise components are progressively reduced in a step-wise manner. Second, the dynamic attention mechanism is deployed, which helps to re-adjust the feature distribution in the noise reduction module. Third, we exploit the deep Griffin-Lim algorithm as the module for phase postprocessing, which facilitates further improvement in speech quality. Experimental results on Voice Bank corpus show that the proposed GAN achieves state-of-the-art performance than previous GAN- and non-GAN-based models

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Generalization of Machine Learning for Problem Reduction: A Case Study on Travelling Salesman Problems

Combinatorial optimization plays an important role in real-world problem solving. In the big data era, the dimensionality of a combinatorial optimization problem is usually very large, which poses a significant challenge to existing solution methods. In this paper, we examine the generalization capability of a machine learning model for problem reduction on the classic travelling salesman problems (TSP). We demonstrate that our method can greedily remove decision variables from an optimization problem that are predicted not to be part of an optimal solution. More specifically, we investigate our model's capability to generalize on test instances that have not been seen during the training phase. We consider three scenarios where training and test instances are different in terms of: 1) problem characteristics; 2) problem sizes; and 3) problem types. Our experiments show that this machine learning based technique can generalize reasonably well over a wide range of TSP test instances with different characteristics or sizes. While the accuracy of predicting unused variables naturally deteriorates as a test instance is further away from the training set, we observe that even when tested on a different TSP problem variant, the machine learning model still makes useful predictions about which variables can be eliminated without significantly impacting solution quality.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Mott Transition and Superconductivity in Quantum Spin Liquid Candidate NaYbSe$_2$

The Mott transition is one of the fundamental issues in condensed matter physics, especially in the system with antiferromagnetic long-range order. However the Mott transition in quantum spin liquid (QSL) systems without long-range order is rare. Here we report the observation of the pressure-induced insulator to metal transition followed by the emergence of superconductivity in the QSL candidate NaYbSe2 with triangular lattice of 4f Yb$_3^+$ ions. Detail analysis of transport properties at metallic state shows an evolution from non-Fermi liquid to Fermi liquid behavior when approaching the vicinity of superconductivity. An irreversible structure phase transition occurs around 11 GPa is revealed by the X-ray diffraction. These results shed light on the Mott transition and superconductivity in the QSL systems.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Non-superconducting electronic ground state in pressurized BaFe$_2$S$_3$ and BaFe$_2$S$_{2.5}$Se$_{0.5}$

We report a comprehensive study of the spin ladder compound BaFe$_2$S$_{2.5}$Se$_{0.5}$ using neutron diffraction, inelastic neutron scattering, high pressure synchrotron diffraction, and high pressure transport techniques. We find that BaFe$_2$S$_{2.5}$Se$_{0.5}$ possesses the same $Cmcm$ structure and stripe antiferromagnetic order as does BaFe$_2$S$_3$, but with a reduced N{é}el temperature of $T_N=98$ K compared to 120 K for the undoped system, and a slightly increased ordered moment of 1.40$μ_B$ per iron. The low-energy spin excitations in BaFe$_2$S$_{2.5}$Se$_{0.5}$ are likewise similar to those observed in BaFe$_2$S$_{3}$. However, unlike the reports of superconductivity in BaFe$_2$S$_3$ below $T_c \sim 14$~K under pressures of 10~GPa or more, we observe no superconductivity in BaFe$_2$S$_{2.5}$Se$_{0.5}$ at any pressure up to 19.7~GPa. In contrast, the resistivity exhibits an upturn at low temperature under pressure. Furthermore, we show that additional high-quality samples of BaFe$_2$S$_3$ synthesized for this study likewise fail to become superconducting under pressure, instead displaying a similar upturn in resistivity at low temperature. These results demonstrate that microscopic, sample-specific details play an important role in determining the ultimate electronic ground state in this spin ladder system. We suggest that the upturn in resistivity at low temperature in both BaFe$_2$S$_3$ and BaFe$_2$S$_{2.5}$Se$_{0.5}$ may result from Anderson localization induced by S vacancies and random Se substitutions, enhanced by the quasi-one-dimensional ladder structure.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Nonconvex Rectangular Matrix Completion via Gradient Descent without $\ell_{2,\infty}$ Regularization

The analysis of nonconvex matrix completion has recently attracted much attention in the community of machine learning thanks to its computational convenience. Existing analysis on this problem, however, usually relies on $\ell_{2,\infty}$ projection or regularization that involves unknown model parameters, although they are observed to be unnecessary in numerical simulations, see, e.g., Zheng and Lafferty [2016]. In this paper, we extend the analysis of the vanilla gradient descent for positive semidefinite matrix completion proposed in Ma et al. [2017] to the rectangular case, and more significantly, improve the required sampling rate from $O(\operatorname{poly}(κ)μ^3 r^3 \log^3 n/n )$ to $O(μ^2 r^2 κ^{14} \log n/n )$. Our technical ideas and contributions are potentially useful in improving the leave-one-out analysis in other related problems.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Polyacrylonitrile/Graphene Nanocomposite: Towards the Next Generation of Carbon Fibers

Carbon Fibers (CFs) are the key solution for the future lightweight vehicle with enhanced fuel efficiency and reduced emissions owing to their ultrahigh strength to weight ratio. However, the high cost of the current dominant PAN-based CFs hinders their application. The use of low-cost alternative precursors may overcome this issue. Unfortunately, low-cost CFs derived from cheaper single component precursors suffer from poor mechanical properties. Developing composite CFs by adding nanoadditives is very promising for low-cost CFs. Therefore, a fundamental understanding of carbonization condition impacts and polymer/additives conversion mechanisms during whole CF production are essential to develop low-cost CFs. In this work, we have demonstrated how the carbonization temperature affects the PAN/graphene CFs properties by performing a series of ReaxFF based molecular dynamics simulations. We found that graphene edges along with the nitrogen and oxygen functional groups have a catalytic role and act as seeds for the graphitic structure growth. Our MD simulations unveil that the addition of the graphene to PAN precursor modifies all-carbon membered rings in CFs and enhances the alignments of 6-member carbon rings in carbonization which leads to superior mechanical properties compare to PAN-based CFs. These ReaxFF simulation results are validates by experimental structural and mechanical characterizations. Interestingly, mechanical characterizations indicate that PAN/graphene CFs carbonized at 1250 C demonstrate 90.9% increase in strength and 101.9% enhancement in Young's modulus compare to the PAN-based CFs carbonized at 1500 C. The superior mechanical properties of PAN/graphene CFs at lower carbonization temperatures offers a path to both energy savings and cost reduction by decreasing the carbonization temperature and could provide key insights for the development of low-cost CFs.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

The IOA System for Deep Noise Suppression Challenge using a Framework Combining Dynamic Attention and Recursive Learning

This technical report describes our system that is submitted to the Deep Noise Suppression Challenge and presents the results for the non-real-time track. To refine the estimation results stage by stage, we utilize recursive learning, a type of training protocol which aggravates the information through multiple stages with a memory mechanism. The attention generator network is designed to dynamically control the feature distribution of the noise reduction network. To improve the phase recovery accuracy, we take the complex spectral mapping procedure by decoding both real and imaginary spectra. For the final blind test set, the average MOS improvements of the submitted system in noreverb, reverb, and realrec categories are 0.49, 0.24, and 0.36, respectively.

0 citations0 reviewsNo code linkedOpen access