arXiv subjects

Liming Wang

Publications and source records attributed to Liming Wang.

At least 19 recordsLinked to original sources

arXiv2026

Unsupervised Speech Recognition at the Syllable Level

Training speech recognizers with unpaired speech and text -- known as unsupervised speech recognition (UASR) -- is a crucial step toward extending ASR to low-resource languages in the long-tail distribution and enabling multimodal learning from non-parallel data. However, existing approaches based on phones often rely on costly resources such as grapheme-to-phoneme converters (G2Ps) and struggle to generalize to languages with ambiguous phoneme boundaries due to training instability. In this paper, we address both challenges by introducing a syllable-level UASR framework based on masked language modeling, which avoids the need for G2P and the instability of GAN-based methods. Our approach achieves up to a 40\% relative reduction in character error rate (CER) on LibriSpeech and generalizes effectively to low-resource languages that have remained particularly difficult for prior methods. Code is publicly available\footnote{https://github.com/cactuswiththoughts/SylCipher}.

eess.AS↗

arXiv2026

Do Multimodal Large Language Models Need Reasoning to Classify Dementia from Speech?

Multimodal large language models (MLLMs) have emerged as a promising approach for improving the accuracy, transferability, and explainability of automatic dementia classification (ADC) systems from voice recordings. Yet it remains unclear whether their reasoning capabilities are beneficial for ADC, and how such capabilities should be leveraged. In this paper, we conduct a careful evaluation of reasoning MLLMs for ADC and show that naive strategies, such as relying on text-based rationales, can lead to hallucinated and inconsistent rationales for diagnosis and yield inferior ADC performance compared with LLM-free baselines. To overcome this limitation, we propose \textbf{De}mentia \textbf{T}hinker with Nonlinear \textbf{A}daptor and Re\textbf{i}nforcement \textbf{L}earning (DeTAiL), an adaptor-based framework that exploits the internal representations of reasoning MLLMs for improved dementia classification. Across two dementia datasets with distinct test formats and label granularities, DeTAiL consistently outperforms strong baselines and methods that rely on text-based rationales. Code and demo will be released upon acceptance.

eess.AS↗

arXiv2026

DDPO-VC: Speaker De-Identification via Diffusion Denoising Policy Optimization

A key challenge of speaker de-identification is the balance between privacy and utility. Many utility variables, such as the cognitive health status of the speaker, are correlated with the privacy variable, such as the speaker identity, violating the independence assumption held by the disentanglement-based approaches, causing leakage of private information and the loss of useful information for downstream tasks. To tackle this challenge, we propose a general framework, DDPO-VC, for speaker de-identification through reinforcement learning-based post-training with diffusion models. Learning from reward signals combining knowledge from privacy-focused and utility-focused teachers, our method outperforms various strong \deid/ methods in both privacy preservation and cognitive utility on two commonly used dementia speech benchmarks. Please check out our code\footnote{\href{https://github.com/cactuswiththoughts/DDPO-VC}{https://github.com/cactuswiththoughts/DDPO-VC}} and demo\footnote{\href{https://cactuswiththoughts.github.io/SpeakerDeID-Demo/}{https://cactuswiththoughts.github.io/SpeakerDeID-Demo/}}.

eess.AS↗

arXiv2026

CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models

Large audio-language models (LALMs) exhibit strong zero-shot capabilities in multiple downstream tasks, such as audio question answering (AQA) and abstract reasoning; however, these models still lag behind specialized models for certain discriminative tasks (e.g., audio classification). Recent studies show that sparse subsets of attention heads within an LALM can serve as strong discriminative feature extractors for downstream tasks such as classification via simple voting schemes. However, these methods assign uniform weights to all selected heads, implicitly assuming that each head contributes equally across all semantic categories. In this work, we propose Class-Conditional Sparse Attention Vectors for Large Audio-Language Models, a few-shot classification method that learns class-dependent importance weights over attention heads. This formulation allows individual heads to specialize in distinct semantic categories and to contribute to ensemble predictions proportionally to their estimated reliability. Experiments on multiple few-shot audio and audiovisual classification benchmarks and tasks demonstrate that our method consistently outperforms state-of-the-art uniform voting-based approaches by up to 14.52%, 1.53%, 8.35% absolute gains for audio classification, audio-visual classification, and spoofing detection respectively.

cs.SD↗

arXiv2026

Measuring the State of Open Science in Transportation Using Large Language Models

Open science initiatives have strengthened scientific integrity and accelerated research progress across many fields, but the state of their practice within transportation research remains under-investigated. Key features of open science, defined here as data and code availability, are difficult to extract due to the inherent complexity of the field. Previous work has either been limited to small-scale studies due to the labor-intensive nature of manual analysis or has relied on large-scale bibliometric approaches that sacrifice contextual richness. This paper introduces an automatic and scalable feature-extraction pipeline to measure code and data availability in transportation research. We employ Large Language Models (LLMs) for this task and validate their performance against a manually curated dataset and through an inter-rater agreement analysis. We applied this pipeline to examine 10,724 research articles published in the Transportation Research Part series of journals between 2019 and 2024. Our analysis found that only 5% of quantitative papers shared a code repository, 4% of quantitative papers shared a data repository, and about 3% of papers shared both, with trends differing across journals, topics, and geographic regions. We found no significant difference in citation counts or review duration between papers that provided data and code and those that did not, suggesting a misalignment between open science efforts and traditional academic metrics. Consequently, encouraging these practices will likely require structural interventions from journals and funding agencies to supplement the lack of direct author incentives. The pipeline developed in this study can be readily scaled to other journals, representing a critical step toward the automated measurement and monitoring of open science practices in transportation research.

cs.DL↗

arXiv2026

Enhancing few-shot time series forecasting with LLM-guided diffusion

Time series forecasting in specialized domains is often constrained by limited data availability, where conventional models typically require large-scale datasets to effectively capture underlying temporal dynamics. To tackle this few-shot challenge, we propose LTSM-DIFF (Large-scale Temporal Sequential Memory with Diffusion), a novel learning framework that integrates the expressive power of large language models with the generative capability of diffusion models. Specifically, the LTSM module is fine-tuned and employed as a temporal memory mechanism, extracting rich sequential representations even under data-scarce conditions. These representations are then utilized as conditional guidance for a joint probability diffusion process, enabling refined modeling of complex temporal patterns. This design allows knowledge transfer from the language domain to time series tasks, substantially enhancing both generalization and robustness. Extensive experiments across diverse benchmarks demonstrate that LTSM-DIFF consistently achieves state-of-the-art performance in data-rich scenarios, while also delivering significant improvements in few-shot forecasting. Our work establishes a new paradigm for time series analysis under data scarcity.

cs.LG↗

arXiv2026

Radio Labeling of Strong Prismatic Network With Star

The rapid development of wireless communication has made efficient spectrum assignment a crucial factor in enhancing network performance. As a combinatorial optimization model for channel assignment, the radio labeling is recognized as an NP-hard problem. Therefore, converting the spectrum assignment problem into the radio labeling of graphs and studying the radio labeling of specific graph classes is of great significance. For $G$, a radio labeling $\varphi: V(G) \to \{0, 1, 2, \ldots\}$ is required to satisfy $|\varphi(u) - \varphi(v)| \geq \text{diam}(G) + 1 -d_G(u, v)$, where ${diam(G)}$ and $d_G(u, v)$ are diameter and distance between $u$ and $v$. For a radio labeling $\varphi$, its $\text{span}$ is defined as the largest integer assigned by $\varphi$ to the vertices of $G$; the radio labeling specifically denotes the labeling with the minimal span among possible radio labeling. The strong product is a crucial tool for constructing regular networks, and studying its radio labeling is necessary for the design of optimal channel assignment in wireless networks. Within this manuscript, we discuss the radio labeling of strong prismatic network with star, present the relevant theorems and examples, and propose a parallel algorithm to improve computational efficiency in large-scale network scenarios.

cs.DC↗

arXiv2025

Schrodinger Audio-Visual Editor: Object-Level Audiovisual Removal

Joint editing of audio and visual content is crucial for precise and controllable content creation. This new task poses challenges due to the limitations of paired audio-visual data before and after targeted edits, and the heterogeneity across modalities. To address the data and modeling challenges in joint audio-visual editing, we introduce SAVEBench, a paired audiovisual dataset with text and mask conditions to enable object-grounded source-to-target learning. With SAVEBench, we train the Schrodinger Audio-Visual Editor (SAVE), an end-to-end flow-matching model that edits audio and video in parallel while keeping them aligned throughout processing. SAVE incorporates a Schrodinger Bridge that learns a direct transport from source to target audiovisual mixtures. Our evaluation demonstrates that the proposed SAVE model is able to remove the target objects in audio and visual content while preserving the remaining content, with stronger temporal synchronization and audiovisual semantic correspondence compared with pairwise combinations of an audio editor and a video editor.

cs.CV↗

arXiv2025

Aixel: A Unified, Adaptive and Extensible System for AI-powered Data Analysis

A growing trend in modern data analysis is the integration of data management with learning, guided by accuracy, latency, and cost requirements. In practice, applications draw data of different formats from many sources. In the meanwhile, the objectives and budgets change over time. Existing systems handle these applications across databases, analysis libraries, and tuning services. Such fragmentation leads to complex user interaction, limited adaptability, suboptimal performance, and poor extensibility across components. To address these challenges, we present Aixel, a unified, adaptive, and extensible system for AI-powered data analysis. The system organizes work across four layers: application, task, model, and data. The task layer provides a declarative interface to capture user intent, which is parsed into an executable operator plan. An optimizer compiles and schedules this plan to meet specified goals in accuracy, latency, and cost. The task layer coordinates the execution of data and model operators, with built-in support for reuse and caching to improve efficiency. The model layer offers versioned storage for index, metadata, tensors, and model artifacts. It supports adaptive construction, task-aligned drift detection, and safe updates that reuse shared components. The data layer provides unified data management capabilities, including indexing, constraint-aware discovery, task-aligned selection, and comprehensive feature management. With the above designed layers, Aixel delivers a user friendly, adaptive, efficient, and extensible system.

cs.DB↗

arXiv2025

Towards Unsupervised Speech Recognition at the Syllable-Level

Training speech recognizers with unpaired speech and text -- known as unsupervised speech recognition (UASR) -- is a crucial step toward extending ASR to low-resource languages in the long-tail distribution and enabling multimodal learning from non-parallel data. However, existing approaches based on phones often rely on costly resources such as grapheme-to-phoneme converters (G2Ps) and struggle to generalize to languages with ambiguous phoneme boundaries due to training instability. In this paper, we address both challenges by introducing a syllable-level UASR framework based on masked language modeling, which avoids the need for G2P and the instability of GAN-based methods. Our approach achieves up to a 40\% relative reduction in character error rate (CER) on LibriSpeech and generalizes effectively to Mandarin, a language that has remained particularly difficult for prior methods. Code will be released upon acceptance.

cs.CL↗

arXiv2025

Accelerating Edge Inference for Distributed MoE Models with Latency-Optimized Expert Placement

The emergence of Mixture-of-Experts (MoE) has transformed the scaling of large language models by enabling vast model capacity through sparse activation. Yet, converting these performance gains into practical edge deployment remains difficult, as the massive memory footprint and communication demands often overwhelm resource-limited environments. While centralized cloud-based solutions are available, they are frequently plagued by prohibitive infrastructure costs, latency issues, and privacy concerns. Moreover, existing edge-oriented optimizations largely overlook the complexities of heterogeneous hardware, focusing instead on isolated or uniform device setups. In response, this paper proposes Prism, an inference framework engineered for collaborative MoE serving across diverse GPU-equipped edge servers. By leveraging the intrinsic sparsity and input locality of MoE workloads, Prism minimizes inter-server communication and optimizes expert placement within diverse resource constraints. The framework integrates an activation-aware placement strategy that balances local request coverage with memory utilization, supplemented by a runtime migration mechanism to adapt expert distribution to dynamic workload changes. Experiments on contemporary MoE models and datasets demonstrate that Prism reduces inference latency by up to 30.6% and significantly lowers communication costs compared to state-of-the-art baselines, confirming the effectiveness of cooperative edge-based MoE serving.

cs.DC↗

arXiv2025

Recognizing Dementia from Neuropsychological Tests with State Space Models

Early detection of dementia is critical for timely medical intervention and improved patient outcomes. Neuropsychological tests are widely used for cognitive assessment but have traditionally relied on manual scoring. Automatic dementia classification (ADC) systems aim to infer cognitive decline directly from speech recordings of such tests. We propose Demenba, a novel ADC framework based on state space models, which scale linearly in memory and computation with sequence length. Trained on over 1,000 hours of cognitive assessments administered to Framingham Heart Study participants, some of whom were diagnosed with dementia through adjudicated review, our method outperforms prior approaches in fine-grained dementia classification by 21\%, while using fewer parameters. We further analyze its scaling behavior and demonstrate that our model gains additional improvement when fused with large language models, paving the way for more transparent and scalable dementia assessment tools. Code: https://anonymous.4open.science/r/Demenba-0861

cs.LG↗

arXiv2025

Meta-SurDiff: Classification Diffusion Model Optimized by Meta Learning is Reliable for Online Surgical Phase Recognition

Online surgical phase recognition has drawn great attention most recently due to its potential downstream applications closely related to human life and health. Despite deep models have made significant advances in capturing the discriminative long-term dependency of surgical videos to achieve improved recognition, they rarely account for exploring and modeling the uncertainty in surgical videos, which should be crucial for reliable online surgical phase recognition. We categorize the sources of uncertainty into two types, frame ambiguity in videos and unbalanced distribution among surgical phases, which are inevitable in surgical videos. To address this pivot issue, we introduce a meta-learning-optimized classification diffusion model (Meta-SurDiff), to take full advantage of the deep generative model and meta-learning in achieving precise frame-level distribution estimation for reliable online surgical phase recognition. For coarse recognition caused by ambiguous video frames, we employ a classification diffusion model to assess the confidence of recognition results at a finer-grained frame-level instance. For coarse recognition caused by unbalanced phase distribution, we use a meta-learning based objective to learn the diffusion model, thus enhancing the robustness of classification boundaries for different surgical phases.We establish effectiveness of Meta-SurDiff in online surgical phase recognition through extensive experiments on five widely used datasets using more than four practical metrics. The datasets include Cholec80, AutoLaparo, M2Cai16, OphNet, and NurViD, where OphNet comes from ophthalmic surgeries, NurViD is the daily care dataset, while the others come from laparoscopic surgeries. We will release the code upon acceptance.

cs.CV↗

arXiv2025

Few-shot Semantic Encoding and Decoding for Video Surveillance

With the continuous increase in the number and resolution of video surveillance cameras, the burden of transmitting and storing surveillance video is growing. Traditional communication methods based on Shannon's theory are facing optimization bottlenecks. Semantic communication, as an emerging communication method, is expected to break through this bottleneck and reduce the storage and transmission consumption of video. Existing semantic decoding methods often require many samples to train the neural network for each scene, which is time-consuming and labor-intensive. In this study, a semantic encoding and decoding method for surveillance video is proposed. First, the sketch was extracted as semantic information, and a sketch compression method was proposed to reduce the bit rate of semantic information. Then, an image translation network was proposed to translate the sketch into a video frame with a reference frame. Finally, a few-shot sketch decoding network was proposed to reconstruct video from sketch. Experimental results showed that the proposed method achieved significantly better video reconstruction performance than baseline methods. The sketch compression method could effectively reduce the storage and transmission consumption of semantic information with little compromise on video quality. The proposed method provides a novel semantic encoding and decoding method that only needs a few training samples for each surveillance scene, thus improving the practicality of the semantic communication system.

cs.CV↗

arXiv2025

Can Diffusion Models Disentangle? A Theoretical Perspective

This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations. Within this framework, we establish identifiability conditions for general disentangled latent variable models, analyze training dynamics, and derive sample complexity bounds for disentangled latent subspace models. To validate our theory, we conduct disentanglement experiments across diverse tasks and modalities, including subspace recovery in latent subspace Gaussian mixture models, image colorization, image denoising, and voice conversion for speech classification. Additionally, our experiments show that training strategies inspired by our theory, such as style guidance regularization, consistently enhance disentanglement performance.

cs.LG↗

arXiv2025

A Spatial-temporal Deep Probabilistic Diffusion Model for Reliable Hail Nowcasting with Radar Echo Extrapolation

Hail nowcasting is a considerable contributor to meteorological disasters and there is a great need to mitigate its socioeconomic effects through precise forecast that has high resolution, long lead times and local details with large landscapes. Existing medium-range weather forecasting methods primarily rely on changes in upper air currents and cloud layers to predict precipitation events, such as heavy rainfall, which are unsuitable for hail nowcasting since it is mainly caused by low-altitude local strong convection associated with terrains. Additionally, radar captures the status of low cloud layers, such as water vapor, droplets, and ice crystals, providing rich signals suitable for hail nowcasting. To this end, we introduce a Spatial-Temporal gEnerAtive Model called SteamCast for hail nowcasting with radar echo extrapolation, it is a deep probabilistic diffusion model based on spatial-temporal representations including radar echoes as well as their position/time embeddings, which we trained on historical reanalysis archive from Yan'an Meteorological Bureau in China, where the crop yield like apple suffers greatly from hail damage. Considering the short-term nature of hail, SteamCast provides 30-minute nowcasts at 6-minute intervals for a single radar reflectivity variable, across 9 different vertical angles, on a latitude-longitude grid with approximately 1 km * 1 km resolution per pixel in Yan'an City, China. By successfully fusing the spatial-temporal features of radar echoes, SteamCast delivers competitive, and in some cases superior, results compared to other deep learning-based models such as PredRNN and VMRNN.

cs.LG↗

arXiv2024

Semiconductive and Ferromagnetic Lanthanide MXenes Derived from Carbon Intercalated Two-dimensional Halides

Two-dimensional (2D) magnetic semiconductors are a key focus in developing next-generation information storage technologies. MXenes, as emerging 2D early transition metal carbides and nitrides, offer versatile compositions and tunable chemical structures. Incorporating lanthanide metals, with their unique role of 4f-electrons in engineering physical properties, into MXenes holds potential for advancing technological applications. However, the scarcity of lanthanide-containing ternary MAX phase precursors and the propensity of lanthanides to oxidize pose significant challenges to obtain lanthanide MXenes (Ln2CT2) via the top-down etching method. Here, we propose a general bottom-up methodology for lanthanide MXenes, that derive from carbon intercalated van der Waals building blocks of 2D halides. Compared to conventional MXenes conductors, the synthesized Ln2CT2 exhibit tunable band gaps spanning 0.32 eV to 1.22 eV that cover typical semiconductors such as Si (1.12 eV) and Ge (0.67 eV). Additionally, the presence of unpaired f-electrons endows Ln2CT2 with intrinsic ferromagnetism, with Curie temperatures ranging between 36 K and 60 K. Theoretical calculations reveal that, in contrast to traditional MXenes, the number of d-electrons states around the Fermi level are largely diminishes in bare Ln2C MXenes, and the halogen terminals can further exhaust these electrons to open band gaps. Meanwhile, the Ln-4f electrons in Ln2CT2 are highly localized and stay away from the Fermi level, contributing to the spin splitting for the observed ferromagnetic behavior. Lanthanide MXenes hold immense promise for revolutionizing future applications in spintronic devices.

cond-mat.mtrl-sci↗

arXiv2024

Contextual Bandit with Herding Effects: Algorithms and Recommendation Applications

Contextual bandits serve as a fundamental algorithmic framework for optimizing recommendation decisions online. Though extensive attention has been paid to tailoring contextual bandits for recommendation applications, the "herding effects" in user feedback have been ignored. These herding effects bias user feedback toward historical ratings, breaking down the assumption of unbiased feedback inherent in contextual bandits. This paper develops a novel variant of the contextual bandit that is tailored to address the feedback bias caused by the herding effects. A user feedback model is formulated to capture this feedback bias. We design the TS-Conf (Thompson Sampling under Conformity) algorithm, which employs posterior sampling to balance the exploration and exploitation tradeoff. We prove an upper bound for the regret of the algorithm, revealing the impact of herding effects on learning speed. Extensive experiments on datasets demonstrate that TS-Conf outperforms four benchmark algorithms. Analysis reveals that TS-Conf effectively mitigates the negative impact of herding effects, resulting in faster learning and improved recommendation accuracy.

cs.LG↗