edit direction

Author: wuchuanjie

content/_index.md

@@ -42,23 +42,30 @@ sections:
       title: 研究方向
       subtitle:
       text: |
+       
         课题组的研究主要聚焦于大模型和自然语言处理领域，目前的研究方向包括：</br>
-        * [**RAG**](publication/#rag)：对于此方向文字描述
+         {{% callout note %}}
+        点击方向名即可跳转到相应的论文列表
+        {{% /callout %}}
+        * [**基于大模型的自然语言处理研究**](publication/#rag)：
+          - 多模态机器翻译研究，包括图到文机器翻译，图到图机器翻译和文本到图像生成
+          - 语音分析和处理研究，包括语音识别、翻译和合成
+          - 信息抽取研究，主要聚焦实体识别，关系抽取和情感分析
         </br> </br>
-        * **大模型训练**：对于此方向文字描述
+        * **大模型基础技术研究**：
+          - 数据体系建设，负责训练数据的采集以及评测基准的构建工作
+          - 模型架构创新​​，致力于探索更为高效且扩展性强的模型结构
+          - 训练算法优化，专注于预训练与微调阶段的训练算法设计工作
+          - 推理加速方案，通过运用解码策略实现高效推理
         </br> </br>
-        * **大模型推理**：对于此方向文字描述
-        </br> </br>
-        * **大模型架构**：对于此方向文字描述
-        </br> </br>
-        * **多模态机器翻译**：对于此方向文字描述
-        </br> </br>
-        * **语音机器翻译**：对于此方向文字描述
-        </br> </br>
-        * **信息抽取**：对于此方向文字描述
-        </br> </br>
-        * **AI for Science**：对于此方向文字描述
+        * **基于大模型的应用技术研究**：
+          - 智能体研究，包括工具调用机制、任务规划方法及多智能体协作框架
+          - 代码生成研究，包括代码补全与代码修复，提升大模型在软件开发中的实用能力。
         </br> </br>
+        * **AI for Science**：
+          - 文本分子跨模态检索
+          - 分子类药性预测
+        
         
         
 

content/authors/Guoqi Ma/_index.md

@@ -0,0 +1,48 @@
+---
+# 中文名称
+title: 马国棋
+
+#英文名，是展示在论文里面的名字
+englishname: Guoqi Ma
+
+# Full name (for SEO)
+first_name: 马
+last_name: 国棋
+
+# 同学们填20**级硕士研究生/博士研究生
+role: 2025级硕士研究生
+
+# 这里放跟自己相关的一些页面的链接，我预定义了三个：分别是邮箱、Google-scholar主页和github主页
+# 对于不想放上去或者自己没有的链接，直接删除即可。
+# 邮箱的格式是'mailto:你的邮箱',其他的放相应链接即可。
+# 如果想添加其他链接，可以到 https://docs.hugoblox.com/getting-started/page-builder/#icons 上去找图标，或者直接放在下面的详细介绍上
+social:
+  - icon: envelope
+    icon_pack: fas
+    link: 'mailto:guoqima@stu.xmu.edu.cn'
+  - icon: github
+    icon_pack: fab
+    link: https://github.com/Swing1wingS
+  # - icon: google-scholar
+  #   icon_pack: ai
+  #   link: https://scholar.google.co.uk/citations?user=sIwtMXoAAAAJ
+
+#  硕士填Master Students ，博士填Ph.D. Students
+user_groups:
+  - Master Students
+
+#接着下面是markdown格式的文本，是md文件的具体内容，同学们可以自行进行修改、删减和添加
+---
+<!-- 以下内容一定要遵循markdown语法 -->
+<!-- ###代表的是以三级标题的形式展示后面的文本，* 代表以列表的形式展示后面的文本-->
+
+<!-- 这里可以先放一段简要自我介绍或者是自己想要放上去的一些链接 ，不想放的话也可以删了-->
+<!-- (这里写自我介绍，如果不想写就直接把括号内容删了即可) -->
+
+### 研究方向
+* 大语言模型
+* 跨文档关系抽取
+
+<!-- 可以放校内外的一些荣誉，包括荣誉称号、奖学金、企业未来之星等等 -->
+<!-- *  -->
+<!-- * 荣誉2 -->

content/authors/Guoqi Ma/avatar.jpg

@@ -16,7 +16,7 @@ publishDate: "2017-01-01T00:00:00Z"
 # Publication type.
 # Accepts a single type but formatted as a YAML list (for Hugo requirements).
 # Enter a publication type from the CSL standard.
-publication_types: ["article-journal"]
+publication_types: [rag]
 
 # Publication name and optional abbreviated publication name.
 publication: "**Neural Networks.**(CCF-B类)"

content/publication/journal-article/index.md

@@ -11,7 +11,7 @@ publishDate: "2017-01-01T00:00:00Z"
 # Publication type.
 # Accepts a single type but formatted as a YAML list (for Hugo requirements).
 # Enter a publication type from the CSL standard.
-publication_types: ["article"]
+publication_types: [rag]
 
 # Publication name and optional abbreviated publication name.
 publication: ""
@@ -27,8 +27,8 @@ tags:
 featured: false
 
 links:
-- name: Custom Link
-  url: http://example.org
+- name: arXiv
+  url: https://arxiv.org/abs/2402.10178v2
 url_pdf: http://arxiv.org/pdf/1512.04133v1
 url_code: 'https://github.com/HugoBlox/hugo-blox-builder'
 url_dataset: '#'

content/publication/preprint/index.md

@@ -24,20 +24,12 @@ publication_types: [rag]
 # Publication name and optional abbreviated publication name.
 publication: "**Neural Networks.(CCF-B类)**"
 
-abstract: The emergence of Large Language Models (LLMs) like ChatGPT has inspired the development of LLM-based agents capable of addressing complex, real-world tasks. However, these agents often struggle during task execution due to methodological constraints, such as error propagation and limited adaptability. To address this issue, we propose a multi-agent framework based on dynamic Task Decomposition and Agent Generation (TDAG). This framework dynamically decomposes complex tasks into smaller subtasks and assigns each to a specifically generated subagent, thereby enhancing adaptability in diverse and unpredictable real-world tasks. Simultaneously, existing benchmarks often lack the granularity needed to evaluate incremental progress in complex, multi-step tasks. In response, we introduce ItineraryBench in the context of travel planning, featuring interconnected, progressively complex tasks with a fine-grained evaluation system. ItineraryBench is designed to assess agents' abilities in memory, planning, and tool usage across tasks of varying complexity. Our experimental results reveal that TDAG significantly outperforms established baselines, showcasing its superior adaptability and context awareness in complex task scenarios.
 
+links:
+- name: arXiv
+  url: https://arxiv.org/abs/2402.10178v2
+url_code: https://github.com
 
-# links:
-# - name: ""
-#   url: ""
-url_pdf: https://arxiv.org/pdf/2402.10178v2
-url_code: 
-url_dataset: ''
-url_poster: ''
-url_project: ''
-url_slides: ''
-url_arXiv: https://arxiv.org/abs/2402.10178
-url_video: ''
 
 
 # Featured image
@@ -70,4 +62,4 @@ Click the *Cite* button above to demo the feature to enable visitors to import p
 Create your slides in Markdown - click the *Slides* button to check out the example.
 {{% /callout %}}
 
-Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/).
+Add the publication's **full text** or **supplementary notes** here. You can use rich formatting such as including [code, math, and images](https://docs.hugoblox.com/content/writing-markdown-latex/).