Rui Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rui Guo has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Aijia Sun
Northeastern University, Seattle, USA
1 shared publication - Jinghan Cao
San Francisco State University
1 shared publication - Weinan Dai
Zhejiang University, Hangzhou, China
1 shared publication - Xiong Luo
Uppsala University, Uppsala, Sweden
1 shared publication - Ying Xie
San Francisco Bay University, Fremont, USA
1 shared publication - Yukun Zhang
Columbia University, New York, USA
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 580-590
Do Large Language Models have Lateral Thinking in Puzzle-Solving Games?
- 6 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 580-590
Open AccessDo Large Language Models have Lateral Thinking in Puzzle-Solving Games?
- Open Access
- 24 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 359-364
A Reflexion-Driven, Document-Constrained Multi-Expert Framework for Reliable Program Synthesis in Graph-Based QA
- 24 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 359-364
Open AccessA Reflexion-Driven, Document-Constrained Multi-Expert Framework for Reliable Program Synthesis in Graph-Based QA
- Open Access
- 21 October 2025
- Published by MDPI AG in Preprints.org
Structure-Aware Multi-Stage Adaptation of Qwen-72B for Code Generation
Large language models show strong abilities in code generation. They still face problems in semantic understanding, structural consistency, controllability, and generalization. Existing methods often focus on one aspect, like instruction following or structural accuracy. They do not offer a unified framework that balances correctness, readability, and adaptability. This work presents CodeFusion-Qwen72B, a multi-stage structure-aware tuning framework for Qwen-72B. It includes progressive low-rank adaptation, hybrid instruction optimization, multi-context fusion, structure-preserving hybrid loss, controllable generation decoding, and adaptive prompt retrieval. By improving semantic comprehension, structural alignment, and controlled code generation, the framework increases the robustness and versatility of large-scale models for software engineering tasks. This study shows that multi-stage optimization and structure-aware learning are effective ways to advance code generation with ultra-large models.
- 21 October 2025
- Published by MDPI AG in Preprints.org
Open AccessStructure-Aware Multi-Stage Adaptation of Qwen-72B for Code Generation
Large language models show strong abilities in code generation. They still face problems in semantic understanding, structural consistency, controllability, and generalization. Existing methods often focus on one aspect, like instruction following or structural accuracy. They do not offer a unified framework that balances correctness, readability, and adaptability. This work presents CodeFusion-Qwen72B, a multi-stage structure-aware tuning framework for Qwen-72B. It includes progressive low-rank adaptation, hybrid instruction optimization, multi-context fusion, structure-preserving hybrid loss, controllable generation decoding, and adaptive prompt retrieval. By improving semantic comprehension, structural alignment, and controlled code generation, the framework increases the robustness and versatility of large-scale models for software engineering tasks. This study shows that multi-stage optimization and structure-aware learning are effective ways to advance code generation with ultra-large models.
- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 411-417
Structure-Aware Multi-Stage Adaptation of Qwen-72B for Code Generation
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 411-417
Open AccessStructure-Aware Multi-Stage Adaptation of Qwen-72B for Code Generation
- Open Access
- 16 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 417-422
Execution-Aware Hierarchical Code Generation with Qwen-72B and Retrieval Augmentation
- 16 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 417-422
Open AccessExecution-Aware Hierarchical Code Generation with Qwen-72B and Retrieval Augmentation
- Open Access
- 28 September 2025
- Published by MDPI AG in Preprints.org
Multi-Modal Hierarchical Spatio-Temporal Network with Gradient-Boosting Integration for Cloud Resource Prediction
Resource prediction in heterogeneous cloud environments is hard because of diverse node configurations, monitoring metrics, execution logs, and injected failures. Neural models can capture temporal patterns but miss sparse discrete features. Tree-based models can model categorical data but cannot handle complex spatio-temporal patterns. We propose MHST-GB, a Multi-Modal Hierarchical Spatio-Temporal Ensemble Network with Gradient Boosting Integration. The framework uses modality-specific neural encoders with correlation-guided attention for fusion. It combines a dual-path design of deep spatio-temporal networks and LightGBM for complementary feature spaces. It also adds a feedback-driven training method that adjusts attention weights based on feature importance. With curriculum learning, FMSE loss, Mixup, and DropConnect, MHST-GB gains robustness and generalization for accurate multi-resource prediction in heterogeneous cloud environments.
- 28 September 2025
- Published by MDPI AG in Preprints.org
Open AccessMulti-Modal Hierarchical Spatio-Temporal Network with Gradient-Boosting Integration for Cloud Resource Prediction
Resource prediction in heterogeneous cloud environments is hard because of diverse node configurations, monitoring metrics, execution logs, and injected failures. Neural models can capture temporal patterns but miss sparse discrete features. Tree-based models can model categorical data but cannot handle complex spatio-temporal patterns. We propose MHST-GB, a Multi-Modal Hierarchical Spatio-Temporal Ensemble Network with Gradient Boosting Integration. The framework uses modality-specific neural encoders with correlation-guided attention for fusion. It combines a dual-path design of deep spatio-temporal networks and LightGBM for complementary feature spaces. It also adds a feedback-driven training method that adjusts attention weights based on feature importance. With curriculum learning, FMSE loss, Mixup, and DropConnect, MHST-GB gains robustness and generalization for accurate multi-resource prediction in heterogeneous cloud environments.