Min Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Min Yu has a total of 84 co-authors. Here are the top co-authors by number of shared publications:
Jianguo Jiang
Chinese Academy of Sciences
22 shared publicationsWeiqing Huang
Chinese Academy of Sciences
21 shared publicationsChao Liu
Chinese Academy of Sciences
16 shared publicationsGang Li
Deakin University
9 shared publications- Gang Li
Deakin University
7 shared publications Xiang Meng
Chinese Academy of Sciences
5 shared publications
Latest Publications
- 25 August 2026
- Published by Springer Nature
- p. 286-301
How Far Can We Compress? Attention-Guided Dataset Distillation for TabPFN
- 25 August 2026
- Published by Springer Nature
- p. 286-301
How Far Can We Compress? Attention-Guided Dataset Distillation for TabPFN
- 17 July 2026
- Published by Springer Nature
- p. 420-435
Temporal Sparse Black-Box Adversarial Attack on Deepfake Video Detection Models
- 17 July 2026
- Published by Springer Nature
- p. 420-435
Temporal Sparse Black-Box Adversarial Attack on Deepfake Video Detection Models
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2133-2141
Thinking in High-Frequency: Practical Defense for Deepfake Detectors Against Black-box Adversarial Attacks
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2133-2141
Open AccessThinking in High-Frequency: Practical Defense for Deepfake Detectors Against Black-box Adversarial Attacks
- 2 January 2026
- Published by Springer Nature
- p. 27-42
Practical Benchmarks for Evaluating Deepfake Detectors
- 2 January 2026
- Published by Springer Nature
- p. 27-42
Practical Benchmarks for Evaluating Deepfake Detectors
- 2 January 2026
- Published by Springer Nature
- p. 77-94
Chat Log Analysis Using Large Language Models
- Open Access
SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In this paper, we tackle this issue by leveraging the synergy between audio and visual speech elements, embarking on a novel approach through audio-visual speech representation learning. Our work is motivated by the finding that audio signals, enriched with speech content, can provide precise information effectively reflecting facial movements. To this end, we first learn precise audio-visual speech representations on real videos via a self-supervised masked prediction task, which encodes both local and global semantic information simultaneously. Then, the derived model is directly transferred to the forgery detection task. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of cross-dataset generalization and robustness, without the participation of any fake video in model training. Code is available at https://github.com/Eleven4AI/SpeechForensics.
Open AccessSpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
Detection of face forgery videos remains a formidable challenge in the field of digital forensics, especially the generalization to unseen datasets and common perturbations. In this paper, we tackle this issue by leveraging the synergy between audio and visual speech elements, embarking on a novel approach through audio-visual speech representation learning. Our work is motivated by the finding that audio signals, enriched with speech content, can provide precise information effectively reflecting facial movements. To this end, we first learn precise audio-visual speech representations on real videos via a self-supervised masked prediction task, which encodes both local and global semantic information simultaneously. Then, the derived model is directly transferred to the forgery detection task. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods in terms of cross-dataset generalization and robustness, without the participation of any fake video in model training. Code is available at https://github.com/Eleven4AI/SpeechForensics.
- 25 May 2025
- Published by Springer Nature
- p. 296-311
SecureSem: Sensitive Text Classification Based on Semantic Feature Optimization
- 25 May 2025
- Published by Springer Nature
- p. 296-311
SecureSem: Sensitive Text Classification Based on Semantic Feature Optimization
- 27 March 2025
- Published by Elsevier in Information Processing & Management
- Vol. 62 (4)
Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering
- 27 March 2025
- Published by Elsevier in Information Processing & Management
- Vol. 62 (4)
Retriever-generator-verification: A novel approach to enhancing factual coherence in open-domain question answering
- Open Access
- 16 October 2024
- Published by IOS Press
- p. 3709-3716
GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER.
- 16 October 2024
- Published by IOS Press
- p. 3709-3716
Open AccessGLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization
Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER.