Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Jiangping Huang
Academic homepage of Jiangping Huang
Page not in menu
This is a page not in th emain menu
Posts
Building AI Automation Toolchains: Let Humans Focus on Thinking and AI Handle Implementation
Published:
A good AI automation toolchain should move implementation details into reliable workflows while keeping human attention on goals, judgment, and thinking.
构建 AI 自动工具链：让人沉浸于思考，让 AI 负责实现
Published:
好的 AI 自动工具链，应当把重复实现细节沉淀为可靠流程，同时让人的注意力回到目标、判断和真正需要思考的问题上。
Codex, Claude Code, and AI Coding Tools: How Software Development Is Changing
Published:
AI coding tools are changing software development from manual editing toward intent expression, review, testing, and repair.
Codex、Claude Code 与 AI 编程工具：软件开发方式正在改变
Published:
AI 编程工具正在把软件开发从手工编辑代码，推向意图表达、结果审查、测试验证和持续修复的人机协作过程。
OpenClaw and Our Agent Research: From Tool Use to Task Execution
Published:
Agent research should move beyond isolated tool calls toward reliable task execution with goals, memory, evidence, and feedback.
OpenClaw 与我们的智能体研究：从工具使用到任务执行
Published:
智能体研究不能停留在单次工具调用，而应走向带有目标、记忆、证据、反馈和验证机制的可靠任务执行。
Great People Do Not Need to Be Managed, Because They Manage Themselves
Published:
A reflection on why strong students and researchers grow fastest when they learn to manage their own goals, standards, and feedback loops.
优秀的人不需要管理，因为他们会自我管理
Published:
真正优秀的学生和研究者，不是靠外部压力不断推进，而是逐渐学会管理自己的目标、标准、证据和反馈循环。
Talent Requires Cultivation, but It Also Requires Selection
Published:
A reflection on why research groups should cultivate students carefully while also selecting those who are willing to grow through responsibility, initiative, and long-term effort.
人才需要培养，同样离不开筛选
Published:
人才成长既需要耐心培养，也需要在真实任务中不断筛选。好的研究组不是简单地管理所有人，而是把有限资源投入到真正愿意成长、能够承担责任并持续进步的学生身上。
A Flash of Insight: How Cognitive Leaps Ignite Innovation and Reform
Published:
A flash of insight is not a random emotional impulse, but a cognitive leap formed through long-term accumulation, deep thinking, and structural reorganization of knowledge. True innovation and reform often begin when the human mind breaks through an old framework.
灵光闪现：认知跃迁如何点燃创新改革
Published:
灵光闪现并不是偶然的情绪冲动，而是长期积累、持续思考与认知重组之后形成的跃迁时刻。真正的创新改革，往往始于人类认知系统对旧有框架的一次突破。
From Defensive Thinking to Growth-Oriented Thinking: Building a Constructive Supervisor–Student Relationship
Published:
Online narratives can easily shape students’ perceptions of supervisor–student relationships before real communication begins. From a cognitive perspective, graduate students need to move beyond defensive thinking and learn to build constructive, growth-oriented relationships with their supervisors.
从防御性认知走向成长型认知：理性建构研究生与导师关系
Published:
网络叙事容易在真实沟通开始之前塑造学生对导师关系的预期。从认知角度看，研究生应从防御性认知走向成长型认知，以理性、开放和建设性的方式建构导师关系，并为自己的学业与人生发展负责。
portfolio
publications
A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning
Published in Neural Processing Letters, 2024
Federated learning, resource allocation.
Recommended citation: "A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning." Neural Processing Letters, 2024.
FUMMER: A fine-grained self-supervised momentum distillation framework for multimodal recommendation
Published in Information Processing & Management, 2024
Multimodal recommendation, self-supervised learning.
Recommended citation: "FUMMER: A fine-grained self-supervised momentum distillation framework for multimodal recommendation." Information Processing & Management, 2024.
StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information
Published in LREC-COLING 2024, 2024
Address matching, semantic understanding, structure-aware information.
Recommended citation: Zhang, Zhaoqi; Balsebre, Pasquale; Luo, Siqiang; Hai, Zhen; Huang, Jiangping; and others. "StructAM: Enhancing Address Matching through Semantic Understanding of Structure-aware Information." Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, Torino, Italy, 2024-05.
Envisioning Intelligent Requirements Engineering via Knowledge-Guided Multi-Agent Collaboration
Published in ASE 2025, 2025
Intelligent requirements engineering, knowledge-guided multi-agent collaboration.
Recommended citation: Jiangping Huang, Dongmin Jin, Weisong Sun, Yang Liu, and Zhi Jin. "Envisioning Intelligent Requirements Engineering via Knowledge-Guided Multi-Agent Collaboration." ASE 2025.
Structure-guided function-level code generation with LLMs via UML activity diagrams
Published in Neurocomputing, 2026
LLM-based code generation, UML activity diagrams, structure-guided generation.
Recommended citation: "Structure-guided function-level code generation with LLMs via UML activity diagrams." Neurocomputing, 2026.
TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code
Published in ICSE 2026, 2026
LLM-generated code debugging, trace-driven multi-agent repair.
Recommended citation: Jiangping Huang, Wenguang Ye, Weisong Sun, Jian Zhang, Mingyue Zhang, and Yang Liu. "TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code." ICSE 2026.