Institution profile

Northwestern Polytechnical University

Academic institutionasia · cn
Official website
Research library919linked papers
Opportunities0open roles
Selected work

Representative Papers

Multi-class Support Vector Machine with Maximizing Minimum Margin

Dec 11, 2023AAAI Conference on Artificial Intelligence

To address the challenges of implicit margin optimization and insufficient decision-boundary robustness in multiclass SVMs, this paper proposes a novel unified multiclass SVM framework. It explicitly incorporates the maximum-margin principle into the modeling process for the first time, jointly optimizing pairwise losses across all class pairs via structured optimization and introducing margin-driven regularization. Theoretically, the framework unifies margin maximization with multiclass loss minimization; practically, it can be seamlessly integrated into deep networks as a drop-in replacement or enhancement for the softmax layer. Extensive experiments on multiple benchmark datasets demonstrate that the proposed method significantly outperforms one-vs-one (OvO), one-vs-rest (OvR), and state-of-the-art multiclass SVM approaches, achieving consistent improvements in both generalization performance and adversarial robustness.

10 citationsRead paper

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

Jun 14, 2024arXiv.org

Prior studies report contradictory findings on how over-parameterization affects neural network adversarial robustness, partly due to inconsistent attack evaluation protocols. Method: We propose a unified empirical framework that jointly assesses both the reliability of mainstream adversarial attacks (e.g., PGD, FGSM) and model robustness under controlled experimental conditions, incorporating attack effectiveness diagnostics and rigorous ablation via controlled variables. Contribution/Results: Our analysis reveals—empirically for the first time—that prior conclusions attributing reduced robustness to over-parameterization are partially confounded by unreliable attacks. When validated, effective attacks are employed, over-parameterized networks consistently exhibit significantly enhanced adversarial robustness, with statistically significant and reproducible gains across diverse settings. This work resolves a key conceptual controversy and establishes a robust empirical foundation confirming over-parameterization as a genuine robustness-enhancing factor.

2 citationsRead paper

LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech

Jan 26, 2026

This work addresses the limitations of existing forced alignment methods, which exhibit strong language dependency and suffer from cumulative temporal drift in long-form speech. To overcome these issues, the authors propose a non-autoregressive alignment paradigm based on slot filling, reframing the alignment task as discrete timestamp index prediction. By leveraging a speech large language model equipped with causal attention masking and a dynamic slot insertion mechanism, the method enables efficient and flexible alignment at arbitrary positions. This approach inherently supports multilingual and cross-lingual scenarios as well as long utterances, effectively mitigating hallucination while significantly improving inference efficiency. Experimental results demonstrate a 69%–78% reduction in cumulative mean offset compared to current methods under multilingual and long-speech settings.

1 citationsRead paper

NMRGym: A Comprehensive Benchmark for Nuclear Magnetic Resonance Based Molecular Structure Elucidation

Jan 22, 2026

This work addresses the critical limitations in current NMR-based molecular structure elucidation research, which heavily relies on synthetic data, leading to severe domain shift when applied to real spectra, and suffers from a lack of standardized evaluation protocols and rigorous data splitting that often results in data leakage and unfair comparisons. To this end, we introduce NMRGym, the largest and most comprehensive benchmark to date, built upon high-quality experimental NMR data encompassing 269,999 molecules with high-fidelity ¹H and ¹³C spectra. The dataset features stringent quality control, uniform formatting, and a scaffold-aware data partitioning strategy, along with the first-ever atom-to-peak level fine-grained annotations. We further establish a multitask evaluation framework and an open-source automated leaderboard supporting tasks such as structure elucidation, functional group identification, toxicity prediction, and spectral simulation, significantly advancing standardization and reproducibility in NMR research.

1 citationsRead paper

WenetSpeech-Wu: Datasets, Benchmarks, and Models for a Unified Chinese Wu Dialect Speech Processing Ecosystem

Jan 16, 2026

This work addresses the underdevelopment of robust speech technologies for low-resource dialects such as Wu Chinese, hindered by the scarcity of large-scale datasets, standardized evaluation benchmarks, and open-source models. To bridge this gap, we present WenetSpeech-Wu, the first large-scale, multi-dimensionally annotated open-source Wu Chinese speech corpus comprising approximately 8,000 hours of audio. Building upon this resource, we introduce WenetSpeech-Wu-Bench, the first standardized multi-task benchmark for Wu Chinese, encompassing six core tasks: automatic speech recognition (ASR), Wu-to-Mandarin translation, speaker attribute prediction, emotion recognition, text-to-speech synthesis (TTS), and intent-driven TTS. We also release a suite of strong open-source baseline models trained on this corpus, significantly advancing the Wu Chinese speech processing ecosystem and establishing the first systematic foundation for research in this domain.

1 citationsRead paper
Recent publications

Latest Papers