Boyan Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Boyan Xu has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
- Ruichu Cai
School of Computer Science, Guangdong University of Technology, Guangzhou, China
11 shared publications - Zhifeng Hao
Shantou University
5 shared publications Ruichu Cai
School of Computer Science Guangdong University of Technology
3 shared publications- Zijian Li
Guangdong University of Technology, China
3 shared publications Shaobin Shi
School of Computer Science Guangdong University of Technology
2 shared publications- Bingfeng Chen
School of Computer Science Guangdong University of Technology
1 shared publication
Latest Publications
- Open Access
- 5 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-30
Enhancing Robustness of Constant Curvature Graph Convolutional Network with Lipschitz Regularization
Non-Euclidean spaces inherently enable high-fidelity embeddings for hierarchical and cyclical data due to their geometric properties. Existing approaches unify hyperbolic and spherical embeddings within the framework of constant curvature spaces. However, current methods for Lipschitz regularization remain limited to non-positive curvature geometries, such as hyperbolic and Euclidean spaces, and cannot be naturally extended to the general constant curvature setting. In this article, we present a rigorous Lipschitz analysis for constant curvature graph convolutional networks ( \(\kappa\) -GCNs) and enhance their robustness through Lipschitz regularization. We derive upper bounds for the Lipschitz constants across constant curvature spaces, thereby standardizing the Lipschitz limits of the \(\kappa\) -stereographic model. Furthermore, we incorporate these bounds into a regularization framework for \(\kappa\) -GCNs to improve stability and robustness. Experimental results demonstrate that the proposed regularization method often strengthens the robustness of \(\kappa\) -GCNs across various curvature regimes, particularly under Gaussian feature noise.- 5 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-30
Open AccessEnhancing Robustness of Constant Curvature Graph Convolutional Network with Lipschitz Regularization
Non-Euclidean spaces inherently enable high-fidelity embeddings for hierarchical and cyclical data due to their geometric properties. Existing approaches unify hyperbolic and spherical embeddings within the framework of constant curvature spaces. However, current methods for Lipschitz regularization remain limited to non-positive curvature geometries, such as hyperbolic and Euclidean spaces, and cannot be naturally extended to the general constant curvature setting. In this article, we present a rigorous Lipschitz analysis for constant curvature graph convolutional networks ( \(\kappa\) -GCNs) and enhance their robustness through Lipschitz regularization. We derive upper bounds for the Lipschitz constants across constant curvature spaces, thereby standardizing the Lipschitz limits of the \(\kappa\) -stereographic model. Furthermore, we incorporate these bounds into a regularization framework for \(\kappa\) -GCNs to improve stability and robustness. Experimental results demonstrate that the proposed regularization method often strengthens the robustness of \(\kappa\) -GCNs across various curvature regimes, particularly under Gaussian feature noise. - Open Access
ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning
Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant verification and repetitive generation. While prior work typically constrains output length or optimizes correctness, such coarse supervision fails to guide models toward concise yet accurate inference. In this paper, we propose ENTRA, an entropy-based training framework that suppresses redundant reasoning while preserving performance. ENTRA first estimates the token-level importance using a lightweight Bidirectional Importance Estimation (BIE) method, which accounts for both prediction confidence and forward influence. It then computes a redundancy reward based on the entropy of low-importance tokens, normalized by its theoretical upper bound, and optimizes this reward via reinforcement learning. Experiments on mathematical reasoning benchmarks demonstrate that ENTRA reduces output length by 37% to 53% with no loss-and in some cases, gains-in accuracy. Our approach offers a principled and efficient solution to reduce overthinking in LRMs, and provides a generalizable path toward redundancy-aware reasoning optimization.
Open AccessENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning
Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead with limited performance gain, primarily due to redundant verification and repetitive generation. While prior work typically constrains output length or optimizes correctness, such coarse supervision fails to guide models toward concise yet accurate inference. In this paper, we propose ENTRA, an entropy-based training framework that suppresses redundant reasoning while preserving performance. ENTRA first estimates the token-level importance using a lightweight Bidirectional Importance Estimation (BIE) method, which accounts for both prediction confidence and forward influence. It then computes a redundancy reward based on the entropy of low-importance tokens, normalized by its theoretical upper bound, and optimizes this reward via reinforcement learning. Experiments on mathematical reasoning benchmarks demonstrate that ENTRA reduces output length by 37% to 53% with no loss-and in some cases, gains-in accuracy. Our approach offers a principled and efficient solution to reduce overthinking in LRMs, and provides a generalizable path toward redundancy-aware reasoning optimization.
- 19 December 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (1) , 13
CMCTS: A Constrained Monte Carlo Tree Search framework for mathematical reasoning in large language model
- 19 December 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 56 (1) , 13
CMCTS: A Constrained Monte Carlo Tree Search framework for mathematical reasoning in large language model
- Open Access
Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Models (LLMs). However, when applied to complex enterprise databases, such methods struggle to maintain coherent reasoning due to limited context capacity, unreliable schema linking, and weak grounding in database semantics. To overcome these issues, we introduce DSR-SQL, a \textbf{D}ual-\textbf{S}tate \textbf{R}easoning framework that models Text-to-SQL as an interaction between an adaptive context state and a progressive generation state. The first constructs a compact, semantically faithful environment by refining large schemas and selecting relevant structures, while the second formalizes SQL synthesis as feedback-guided state transitions, enabling the model to self-correct and align with user intent. Without any post-training or in-context examples, DSR-SQL achieves competitive performance, reaching 35.28\% execution accuracy on Spider 2.0-Snow and 68.32\% on BIRD development set. Our implementation will be open-sourced at: https://github.com/DMIRLAB-Group/DSR-SQL.
Open AccessText-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Models (LLMs). However, when applied to complex enterprise databases, such methods struggle to maintain coherent reasoning due to limited context capacity, unreliable schema linking, and weak grounding in database semantics. To overcome these issues, we introduce DSR-SQL, a \textbf{D}ual-\textbf{S}tate \textbf{R}easoning framework that models Text-to-SQL as an interaction between an adaptive context state and a progressive generation state. The first constructs a compact, semantically faithful environment by refining large schemas and selecting relevant structures, while the second formalizes SQL synthesis as feedback-guided state transitions, enabling the model to self-correct and align with user intent. Without any post-training or in-context examples, DSR-SQL achieves competitive performance, reaching 35.28\% execution accuracy on Spider 2.0-Snow and 68.32\% on BIRD development set. Our implementation will be open-sourced at: https://github.com/DMIRLAB-Group/DSR-SQL.
- 1 October 2025
- Published by Springer Nature
- p. 108-119
Integrating Multi-modal Contrastive Learning and Multi-scale Feature Extractor for Liver Cancer Classification
- 1 October 2025
- Published by Springer Nature
- p. 108-119
Integrating Multi-modal Contrastive Learning and Multi-scale Feature Extractor for Liver Cancer Classification
- 8 January 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (5-6) , 3663-3679
SDGNN: Structure-aware Dual Graph Neural Network for Code Summarization
- 8 January 2025
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (5-6) , 3663-3679
SDGNN: Structure-aware Dual Graph Neural Network for Code Summarization
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 29880-29893
GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL
Zhifeng Hao, Junqi Huang, Shaobin Shi, Ruichu Cai, Boyan Xu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 29880-29893
Open AccessGenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQL
Zhifeng Hao, Junqi Huang, Shaobin Shi, Ruichu Cai, Boyan Xu. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6799-6806
𝒮2IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
Bingfeng Chen, Chenjie Qiu, Yifeng Xie, Boyan Xu, Ruichu Cai, Zhifeng Hao. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 6799-6806
Open Access𝒮2IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
Bingfeng Chen, Chenjie Qiu, Yifeng Xie, Boyan Xu, Ruichu Cai, Zhifeng Hao. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10690-10708
Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
Bingfeng Chen, Shaobin Shi, Yongqi Luo, Boyan Xu, Ruichu Cai, Zhifeng Hao. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10690-10708
Open AccessTrack-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
Bingfeng Chen, Shaobin Shi, Yongqi Luo, Boyan Xu, Ruichu Cai, Zhifeng Hao. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10790-10802
Handling Missing Entities in Zero-Shot Named Entity Recognition: Integrated Recall and Retrieval Augmentation
Ruichu Cai, Junhao Lu, Zhongjie Chen, Boyan Xu, Zhifeng Hao. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10790-10802
Open AccessHandling Missing Entities in Zero-Shot Named Entity Recognition: Integrated Recall and Retrieval Augmentation
Ruichu Cai, Junhao Lu, Zhongjie Chen, Boyan Xu, Zhifeng Hao. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.