Publications

You can also find my articles on my Google Scholar profile.

Journal Articles

Generalizable Geometric Image Caption Synthesis

Published in NeurIPS Datasets and Benchmarks Track (Under Review), 2025

A reinforcement learning-based framework for generating semantically aligned geometry image-caption pairs, creating the first dataset with full modality equivalence for geometric reasoning.

Recommended citation: Wenyuan Wang*, Yue Xin*, Rui Pan*, BingXu Meng*, Renjie Pi, Tong Zhang. "Generalizable Geometric Image Caption Synthesis." Submitted to NeurIPS Datasets and Benchmarks Track.
Download Paper | Download Slides | Download Bibtex

Probabilistic Residual User Clustering

Published in IJCAI2025 Workshop / Submitted to TMLR, 2024

A causal Bayesian framework that clusters users and models residuals between predicted and true ratings to enhance recommendation accuracy.

Recommended citation: Wenyuan Wang, Yusong Zhao, Zihao Xu, Hengyi Wang, Shreya Venugopal, Desmond Lobo, Chengzhi Mao, Qi Xu, Zhigang Hua, Yan Xie, Bo Long, Shuang Yang, Hao Wang. "Probabilistic Residual User Clustering." IJCAI2025 Workshop / Submitted to TMLR.
Download Paper | Download Slides

Multi-tailed vision transformer for efficient inference

Published in Neural Networks, 2024

A novel architecture that uses multiple tails to generate visual sequences of different lengths for efficient vision transformer inference.

Recommended citation: Yunke Wang, Bo Du, Wenyuan Wang, Chang Xu. "Multi-tailed vision transformer for efficient inference." Neural Networks, 2024, 174: 106235.
Download Paper

Continual Learning of Large Language Models: A Comprehensive Survey

Published in ACM Computing Surveys, 2024

A comprehensive survey on continual learning approaches for large language models, covering methodologies, challenges, and future directions.

Recommended citation: Haizhou Shi, Zihao Xu, Hengyi Wang, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Sayna Ebrahimi, Hao Wang. "Continual Learning of Large Language Models: A Comprehensive Survey." ACM Computing Surveys.
Download Paper

Conference Papers

Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models

Published in NAACL 2025 Main, 2025

A comprehensive benchmark for evaluating the long-context capabilities of multimodal large language models.

Recommended citation: Hengyi Wang, Haizhou Shi, Shiwei Tan, Weiyi Qin, Wenyuan Wang, Tunyu Zhang, Akshay Nambi, Tanuja Ganu, Hao Wang. "Multimodal Needle in a Haystack: Benchmarking Long-Context Capability of Multimodal Large Language Models." NAACL 2025 Main.
Download Paper | Download Slides