Skip to content

Author

Yu-Pei Li

We have 6 of 36 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Oct 2026

Defending against deepfake speech attacks via feature dropout and dropin regularization in large audio language models

Deepfakes have raised widespread concern owing to their threats to privacy, security, and societal trust, driving growing research interest in effective detection methods. Audio deepfake detection has moved from handcrafted-feature classifiers to end-to-end deep learning architectures and, more recently, to self-superv...

Yu-Pei Li, Yi-Xiong Fang, Jia-Hao Xue et al. · 0 citations
#natural language process... Preprint Oct 2026

DeBERTa-ConPara: Attack-Aware and Deployment-Realistic Detection of AI-Generated Text

Robust detection of AI-generated text under deployment conditions is challenging: distribution shifts across domains and generators, adversarial perturbations of the input surface, and the absence of target-domain labels for threshold calibration all degrade detectors that perform well in-domain. We present DeBERTa-Con...

Mohamed Mady, Yu-Pei Li, Johannes Reschke et al. · 1 citation · ⚡1
Preprint Sep 2026

Beyond Accuracy: ARIA-Rubrics for Evaluating Audio Reasoning in Large Audio Language Models

This work proposes ARIA-Rubrics (Audio Reasoning Integrity Assessment), a lightweight, annotation-free gold reasoning chains, automatic and transparent framework comprising six complementary metrics that evaluate audio reasoning quality across perceptual grounding, reasoning coherence, and answer consistency.

Yu-Pei Li, Qi-Yang Sun, Mohamed Mady et al. · 0 citations
#natural language process... Preprint Sep 2026

CLASH: Counterfactual Auditing of Lexical and Prosodic Reliance in Spoken Sarcasm Detection

Spoken sarcasm detectors may exploit lexical content, prosody, or their interaction, yet conventional evaluation cannot reveal which cues drive their predictions. We introduce CLASH (Controlled Lexical-Acoustic Separation Harness), a bilingual counterfactual diagnostic framework that evaluates each utterance under orig...

Qi-Yang Sun, Xu-Dong Li, Yu-Pei Li et al. · 1 citation
#artificial intelligence Preprint Sep 2026

A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrolled Mandarin Kinship Speech Dataset

This work proposes CONVTRAP-TN, a new architecture for audio-based kinship verification, and is the first to apply the successful transformer architecture to the task of audio-based kinship verification, and collects a custom speech dataset, ARKIN, which accurately reflects everyday recording conditions.

Qi-Yang Sun, Lan Zhang, Yu-Pei Li et al. · 0 citations

TopoAlign: A Framework for Aligning Code to Math via Topological Decomposition

TopoAlign is proposed, a framework that unlocks widely available code repositories as training resources for Math LLMs and decomposes code into docstrings, main functions, and dependency functions, and reassembles these components into analogues that structurally mirror formal statements.

Yu-Pei Li, Philipp Borchert, Gerasimos Lampouras · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.