Peiye Liu
Peiye Liu has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Bei Liu
Microsoft Research Asia, Beijing, China
4 shared publications - Bo Wu
MIT-IBM Watson AI Lab, Cambridge, MA, USA
4 shared publications - Jia Wang
Guangdong Pharmaceutical University, Guangzhou, China
4 shared publications - Jiebo Luo
University of Rochester, Rochester, New York, USA
4 shared publications - Qiushi Huang
University of Surrey, Guildford, United Kingdom
4 shared publications - Wen-Huang Cheng
National Taiwan University, Taipei, Taiwan
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17572-17576
SMP Challenge - Social Media Popularity Prediction for Images and Videos
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 17572-17576
Open AccessSMP Challenge - Social Media Popularity Prediction for Images and Videos
- 19 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (7) , 3772-3786
Inner-Probe: Discovering Copyright-Related Data Generation in LLM Architecture
Large Language Models (LLMs) utilize extensiveknowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises concerns about copyright infringements in generated texts. Current research often employs prompt engineering or semantic classifiers to identify copyrighted content, but these approaches have two significant limitations: (1) Challenging to identify which specific sub-dataset (e.g., works from particular authors) influences an LLM’s output. (2) Treating the entire training database as copyrighted, hence overlooking the inclusion of non–copyrighted training data. We propose Inner–Probe, a lightweight framework designed to evaluate the influence of copyrighted sub-datasets on LLM–generated texts. Unlike traditional methods relying solely on text, we discover that the results of multi-head attention (MHA) during LLM output generation provide more effective information. Thus, Inner–Probe performs sub–dataset contribution analysis using a lightweight LSTM-based network trained on MHA results in a supervised manner. Harnessing such a prior, Inner-Probe enables non–copyrighted text detection through a concatenated global projector trained with unsupervised contrastive learning. Inner–Probe demonstrates 3+ improved efficiency compared to semantic model training in sub–dataset contribution analysis on Books3, achieves 15.04%–58.7% higher accuracy over baselines on the Pile, and delivers a 0.104 increase in AUC for non-copyrighted data filtering.
- 19 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (7) , 3772-3786
Inner-Probe: Discovering Copyright-Related Data Generation in LLM Architecture
Large Language Models (LLMs) utilize extensiveknowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises concerns about copyright infringements in generated texts. Current research often employs prompt engineering or semantic classifiers to identify copyrighted content, but these approaches have two significant limitations: (1) Challenging to identify which specific sub-dataset (e.g., works from particular authors) influences an LLM’s output. (2) Treating the entire training database as copyrighted, hence overlooking the inclusion of non–copyrighted training data. We propose Inner–Probe, a lightweight framework designed to evaluate the influence of copyrighted sub-datasets on LLM–generated texts. Unlike traditional methods relying solely on text, we discover that the results of multi-head attention (MHA) during LLM output generation provide more effective information. Thus, Inner–Probe performs sub–dataset contribution analysis using a lightweight LSTM-based network trained on MHA results in a supervised manner. Harnessing such a prior, Inner-Probe enables non–copyrighted text detection through a concatenated global projector trained with unsupervised contrastive learning. Inner–Probe demonstrates 3+ improved efficiency compared to semantic model training in sub–dataset contribution analysis on Books3, achieves 15.04%–58.7% higher accuracy over baselines on the Pile, and delivers a 0.104 increase in AUC for non-copyrighted data filtering.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8626-8635
Unicorn: Unified Neural Image Compression with One Number Reconstruction
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8626-8635
Open AccessUnicorn: Unified Neural Image Compression with One Number Reconstruction
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14055-14057
SMPV: Social Media Prediction for Videos
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 14055-14057
Open AccessSMPV: Social Media Prediction for Videos
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11442-11444
SMP Challenge Summary: Social Media Prediction Challenge
SMP Challenge is an annual challenge that seeks top research teams to develop innovative forecasting methods that can enhance social and business applications. We define and introduce the Social Media Popularity Prediction (SMPP) task that predicting the future popularity of a post made by a specific user at a given time on social media. This task is pivotal in various applications and scenarios, such as online advertising, social recommendations, post ranking, and demand forecasting, etc. To motivate diverse perspectives of social media prediction researches, we built a large-scale benchmark Social Media Prediction Dataset (SMPD) that includes approximately 500K posts, along with associated 756 tags, visual-language data, and spatial-temporal information, and sourced from around 70K users and their profiles. With participation and contribution from top teams worldwide, the challenge has seen continuous performance improvements in recent years, driven by technological advancements. For the latest information, leaderboard or online evaluation, please visit the SMP Challenge Homepage: www.smp-challenge.com.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 11442-11444
Open AccessSMP Challenge Summary: Social Media Prediction Challenge
SMP Challenge is an annual challenge that seeks top research teams to develop innovative forecasting methods that can enhance social and business applications. We define and introduce the Social Media Popularity Prediction (SMPP) task that predicting the future popularity of a post made by a specific user at a given time on social media. This task is pivotal in various applications and scenarios, such as online advertising, social recommendations, post ranking, and demand forecasting, etc. To motivate diverse perspectives of social media prediction researches, we built a large-scale benchmark Social Media Prediction Dataset (SMPD) that includes approximately 500K posts, along with associated 756 tags, visual-language data, and spatial-temporal information, and sourced from around 70K users and their profiles. With participation and contribution from top teams worldwide, the challenge has seen continuous performance improvements in recent years, driven by technological advancements. For the latest information, leaderboard or online evaluation, please visit the SMP Challenge Homepage: www.smp-challenge.com.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9651-9655
SMP Challenge: An Overview and Analysis of Social Media Prediction Challenge
Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts of multimodal data available on social media platforms. Studying and investigating social media popularity becomes central to various online applications and requires novel methods of comprehensive analysis, multimodal comprehension, and accurate prediction. SMP Challenge is an annual research activity that has spurred academic exploration in this area. This paper summarizes the challenging task, data, and research progress. As a critical resource for evaluating and benchmarking predictive models, we have released a large-scale SMPD benchmark encompassing approximately half a million posts authored by around 70K users. The research progress analysis provides an overall analysis of the solutions and trends in recent years. The SMP Challenge website (www.smp-challenge.com) provides the latest information and news.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 9651-9655
Open AccessSMP Challenge: An Overview and Analysis of Social Media Prediction Challenge
Social Media Popularity Prediction (SMPP) is a crucial task that involves automatically predicting future popularity values of online posts, leveraging vast amounts of multimodal data available on social media platforms. Studying and investigating social media popularity becomes central to various online applications and requires novel methods of comprehensive analysis, multimodal comprehension, and accurate prediction. SMP Challenge is an annual research activity that has spurred academic exploration in this area. This paper summarizes the challenging task, data, and research progress. As a critical resource for evaluating and benchmarking predictive models, we have released a large-scale SMPD benchmark encompassing approximately half a million posts authored by around 70K users. The research progress analysis provides an overall analysis of the solutions and trends in recent years. The SMP Challenge website (www.smp-challenge.com) provides the latest information and news.