5 papers
ReMath: Benchmarking Theorem Retrieval in Research-Level Mathematics
Zicheng Lyu, Wenjie Yang, Shengzhong Zhang +1
Large language models are increasingly capable at closed-world mathematical reasoning, but research assistance also requires source-grounded use of the literature. When a proof rea…
Poivre: Self-Refining Visual Pointing with Reinforcement Learning
Wenjie Yang, Zengfeng Huang
Visual pointing, which aims to localize a target by predicting its coordinates on an image, has emerged as an important problem in the realm of vision-language models (VLMs). Despi…
Right Is Not Enough: The Pitfalls of Outcome Supervision in Training LLMs for Math Reasoning
Jiaxing Guo, Wenjie Yang, Shengzhong Zhang +4
Outcome-rewarded Large Language Models (LLMs) have demonstrated remarkable success in mathematical problem-solving. However, this success often masks a critical issue: models frequ…
Your Graph Recommender is Provably a Single-view Graph Contrastive Learning
Wenjie Yang, Shengzhong Zhang, Jiaxing Guo +1
Graph recommender (GR) is a type of graph neural network (GNNs) encoder that is customized for extracting information from the user-item interaction graph. Due to its strong perfor…
StructComp: Substituting Propagation with Structural Compression in Training Graph Contrastive Learning
Shengzhong Zhang, Wenjie Yang, Xinyuan Cao +2
Graph contrastive learning (GCL) has become a powerful tool for learning graph data, but its scalability remains a significant challenge. In this work, we propose a simple yet effe…