Update research paper and desc

Author: oyb98

src/assets/paper_table.json

@@ -574,7 +574,20 @@
                     "tag": "l11_tag",
                     "desc": "l11_desc",
                     "content": [
-                        
+                        {
+                            "content": [
+                                {
+                                    "title": "",
+                                    "papers": [
+                                        "Yihang Wang, Yuying Qiu, Peng Chen, Kai Zhao, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo. Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer. ICML 2025.",
+                                        "Yihang Wang, Yuying Qiu, Peng Chen, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo. LightGTS: A Lightweight General Time Series Forecasting Model. ICML 2025.",
+                                        "Qichao Shentu, Beibu Li, Kai Zhao, Yang Shu, Zhongwen Rao, Lujia Pan, Bin Yang, Chenjuan Guo. Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders. ICLR 2025.",
+                                        "Yuxuan Chen, Shanshan Huang, Yunyao Cheng, Peng Chen, Zhongwen Rao, Yang Shu, Bin Yang, Lujia Pan, Chenjuan Guo. AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification. ICDE 2025."
+                                    ]
+                                }
+                            ],
+                            "subsection": ""
+                        }
                     ],
                     "section": "l11",
                     "id":"11"
@@ -583,7 +596,17 @@
                     "tag": "l12_tag",
                     "desc": "l12_desc",
                     "content": [
-                        
+                        {
+                            "content": [
+                                {
+                                    "title": "",
+                                    "papers": [
+                                        "Zhe Li, Xiangfei Qiu, Peng Chen, Yihang Wang, Hanyin Cheng, Yang Shu, Jilin Hu, Chenjuan Guo, Aoying Zhou, Christian S. Jensen, Bin Yang. FM4TS-Bench: A Comprehensive and Unified Benchmark of Foundation Models for Time Series Forecasting. KDD 2025."
+                                    ]
+                                }
+                            ],
+                            "subsection": ""
+                        }
                     ],
                     "section": "l12",
                     "id":"12"

src/i18n/en-US/index.js

@@ -61,9 +61,9 @@ export default {
     "",
   l10_desc: "Transfer Learning and Model Generalization",
   l11_tag: "",
-  l11_desc: "",
+  l11_desc: "The research on foundation models for time series aims to build time series analysis models that possess generality across different tasks and transferability across various domains by training on large-scale time series data. This approach reduces the cost of data collection and model training for specific downstream tasks, enhances the usability of time series analysis technologies, and empowers intelligent analysis, decision-making, and digital transformation in areas such as intelligent operations and maintenance, smart cities, and digital energy. The research covers pretraining techniques for time series foundation models, model architecture design, large-scale time series datasets, and applications of foundation models in typical analysis tasks such as forecasting, anomaly detection, and classification.",
   l12_tag: "",
-  l12_desc: "",
+  l12_desc: "The research on foundation model evaluation aims to systematically assess and compare various large models—such as large language models and time series foundation models—from the perspectives of accuracy, efficiency, and generalization. It involves both qualitative and quantitative analyses of the strengths and limitations of different models, providing guidance for model optimization and serving as a reference for model selection. The research includes the construction of evaluation datasets, the design of evaluation frameworks, and the development of evaluation systems for large models.",
   l13_tag: "",
   l13_desc: 
     "Multi-agent systems, by simulating complex social interactions and autonomous decision-making, can effectively analyze collective behavior and system dynamics. Our research focuses on leveraging multi-agent simulation technologies to empower areas such as education policy evaluation, traffic scheduling, and resource allocation. Specifically, the research encompasses the construction of social simulators (e.g., forecasting the macro-level impact of education policies), collaborative decision-making algorithms (e.g., ride-hailing supply-demand matching and route optimization), and multi-agent reinforcement learning (e.g., dynamic scheduling of water reservoir usage), drawing on methodologies from game theory, distributed optimization, reinforcement learning, and mechanism design. The research outcomes will be applied in domestic education policy simulation platforms and smart city projects. For example: 1) The developed education policy simulator uses multi-agent modeling to quantify the impact of resource allocation on regional education equity, providing decision support for the National Institute of Education Policy Research; 2) The designed collaborative ride-hailing scheduling algorithm will be implemented in the dispatching system of one of China's top ten ride-hailing platforms; 3) The proposed multi-agent water resource allocation framework will be applied to address saline tide challenges at the Yangtze River water source in Shanghai.",

src/i18n/zh-CN/index.js

@@ -66,9 +66,9 @@ export default {
   l10_tag: "",
   l10_desc: "迁移学习与模型泛化性",
   l11_tag: "",
-  l11_desc: "",
+  l11_desc: "时序大模型的研究旨在通过大规模时序数据的训练，构建在不同任务上具有通用性，在不同领域间具有泛化性的时间序列分析模型，从而减小模型在具体下游任务中的数据收集、模型训练成本，提升时间序列分析技术在各领域的易用性，赋能智能运维、智慧城市、数字能源等领域的智能分析决策与数字化转型。研究内容涵盖时序大模型预训练技术、时序大模型架构设计、大规模时序数据集、时序大模型在预测、异常检测、分类等典型分析任务上的应用等方面。",
   l12_tag: "",
-  l12_desc: "",
+  l12_desc: "大模型评测的研究旨在对大语言模型、时序大模型等各类大模型从精度、效率、通用性等角度进行系统性评测对比，对不同模型的优势与存在的问题进行定性与定量的分析，为大模型的优化提供方向，为大模型的选型提供参考。研究内容涵盖大模型评测集构建、大模型评测框架与系统设计等。",
   l13_tag: "",
   l13_desc: 
     "多智能体系统通过模拟复杂社会交互和自主决策，能有效分析群体行为与系统动态。我们的研究聚焦于利用多智能体仿真技术，赋能教育政策评估、交通调度和资源分配等领域。具体而言，研究涵盖社会模拟器构建（如教育政策宏观影响预测）、协同决策算法（如网约车供需匹配与路径优化）以及多智能体强化学习（如水库用水动态调度），涉及博弈论、分布式优化、强化学习与机制设计等方法。研究成果将应用于国内教育政策仿真平台与智慧城市项目，例如：1）开发的教育政策模拟器通过多智能体建模量化了资源分配对区域教育公平的影响，为国家宏观教育政策研究院提供决策支持；2）设计的网约车协同调度算法，并将落地与国内前十的网约车出行平台调度系统中；3）提出的水资源多智能体分配框架将应用于上海市长江水源地咸潮应对中。",