Bo Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Bo Peng has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Zhen Fang
University of Technology Sydney
3 shared publications - Guangquan Zhang
University of Technology Sydney
2 shared publications - Jie Lu
University of Technology Sydney
2 shared publications - Kuo Shi1 shared publication
- Wenjie Zhu1 shared publication
- Xuefeng Du
Department of Computer Science, University of Wisconsin–Madison, Madison, WI, USA
1 shared publication
Latest Publications
- 10 September 2026
- Published by Springer Nature
- p. 605-624
MoE-KD: Your Teacher Model is Worth Mixture-of-Experts for Knowledge Distillation
- 10 September 2026
- Published by Springer Nature
- p. 605-624
MoE-KD: Your Teacher Model is Worth Mixture-of-Experts for Knowledge Distillation
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2897-2898
Detecting Distribution Shifts In the Wild: Techniques and Future Perspectives
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2897-2898
Open AccessDetecting Distribution Shifts In the Wild: Techniques and Future Perspectives
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2906-2907
Toward Trustworthy Vision-language Models in the Wild: Theory, Algorithm and Application
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2906-2907
Open AccessToward Trustworthy Vision-language Models in the Wild: Theory, Algorithm and Application
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1171-1181
Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of post-hoc OOD detection with pre-trained vision-language models (VLMs), where a popular pipeline is to detect OOD inputs by examining their affinities between ID labels and negative labels, i.e., those semantically different from ID labels. Due to the unavailability of target OOD labels, existing works predominantly rely on heuristic rules to mine negative labels from unlabeled wild corpus data. Despite the empirical success, we argue that the power of VLM-based OOD detection has yet to be fully unleashed since the notorious false negative problem is far from addressed in the literature. With this motivation, we are interested in addressing the challenge of mining true negative labels for OOD scoring. To this end, we develop a theoretical framework for correcting the sampling bias of negatives labels by indirectly approximating the distribution of negative labels. Perhaps surprisingly, we show that the debiased negative mining can be naturally converted into Monte-Carlo sampling based on ID labels and the unlabeled wild corpus data. Extensive experiments empirically manifest that our method establishes a new state-of-the-art in a variety of OOD detection setups.
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1171-1181
Open AccessDebiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
Aiming at identifying unexpected inputs from unknown classes, out-of-distribution (OOD) detection has emerged as a pivotal approach to enhancing the reliability of machine learning models. This paper focuses on the burgeoning paradigm of post-hoc OOD detection with pre-trained vision-language models (VLMs), where a popular pipeline is to detect OOD inputs by examining their affinities between ID labels and negative labels, i.e., those semantically different from ID labels. Due to the unavailability of target OOD labels, existing works predominantly rely on heuristic rules to mine negative labels from unlabeled wild corpus data. Despite the empirical success, we argue that the power of VLM-based OOD detection has yet to be fully unleashed since the notorious false negative problem is far from addressed in the literature. With this motivation, we are interested in addressing the challenge of mining true negative labels for OOD scoring. To this end, we develop a theoretical framework for correcting the sampling bias of negatives labels by indirectly approximating the distribution of negative labels. Perhaps surprisingly, we show that the debiased negative mining can be naturally converted into Monte-Carlo sampling based on ID labels and the unlabeled wild corpus data. Extensive experiments empirically manifest that our method establishes a new state-of-the-art in a variety of OOD detection setups.
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1104-1114
Distributional Prototype Learning for Out-of-distribution Detection
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1104-1114
Open AccessDistributional Prototype Learning for Out-of-distribution Detection