NET Wiki

Seminar on Internet Technologies (Winter 2026/2027): Difference between revisions

Hxu4 (talk | contribs)
20 edits
Created page with "== Details == {{CourseDetails |credits=5 ECTS (BSc/MSc AI); 5 (ITIS) |module=M.Inf.1124 |lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu];[http://www.net.informatik.uni-goettingen.de/?q=people/tingting-yuan Tingting Yuan] |ta =[http://www.net.informatik.uni-goettingen.de/?q=people/jiaquan-zhang MSc. Jiaquan Zhang]; |'''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?u..."
 
Lenke1 (talk | contribs)
11 edits
No edit summary
 
(7 intermediate revisions by one other user not shown)
Line 5: Line 5:
|credits=5 ECTS (BSc/MSc AI); 5 (ITIS)
|credits=5 ECTS (BSc/MSc AI); 5 (ITIS)
|module=M.Inf.1124
|module=M.Inf.1124
|lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu];[http://www.net.informatik.uni-goettingen.de/?q=people/tingting-yuan Tingting Yuan]
|lecturer=[http://user.informatik.uni-goettingen.de/~fu Prof. Xiaoming Fu]
|ta =[http://www.net.informatik.uni-goettingen.de/?q=people/jiaquan-zhang MSc. Jiaquan Zhang];
|'''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|'''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|ta = Dongkuo Wu[dongkuo.wu@cs.uni-goettingen.de];
|ta = Hao Xu [hao.xu@cs.uni-goettingen.de];
|time='''Please read this introduction slide [https://docs.google.com/presentation/d/13hmKYBmB4tbTFNeK1GvBAs1qZntMYo75o8ycb1NgYXI/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|time='''Please read this introduction slide [https://docs.google.com/presentation/d/1hFDLS7unEDby6t-pkBrlzwk_LXvm0H3osiAkNd2GmNc/edit?usp=sharing]. If there is any question, please contact teaching assistants.'''
|univz=[https://studip-ecampus.uni-goettingen.de/dispatch.php/course/details/index/4f4ce922cd439f8a00f299fec776c727]
<!--|univz=[https://studip-ecampus.uni-goettingen.de/dispatch.php/course/details/index/4f4ce922cd439f8a00f299fec776c727]-->
}}
}}


Line 40: Line 39:


==Schedule==
==Schedule==
* '''31.01.2026''': Deadline for registration to attend the final presentation
* '''31.01.2027''': Deadline for registration to attend the final presentation
* '''10.02.2026''' : Final Presentations (Offline)
* '''10.02.20267''' : Final Presentations (Offline)
* '''27.02.2026(23:59) ''': Deadline for submission of the report (should be sent to the topic adviser!).
* '''27.02.2027(23:59) ''': Deadline for submission of the report (should be sent to the topic adviser!).


== Topics ==
== Topics ==
Line 54: Line 53:
|{{Hl2}} |'''Readings'''
|{{Hl2}} |'''Readings'''
|{{Hl2}} |'''Available'''
|{{Hl2}} |'''Available'''
|-
| Social Media Comments Network Analysis (Intern/Project/Thesis possible)
| In this topic, student will study methods to crawl the dataset from social networks(e.g. Tiktok, X, YouTube) and utilize social network analysis in any topic you are interested in (science/education/language…) to find out the network structure and compare the difference among different topics.
| Python(Data crawling, cleaning, statistical data analysis, modeling and visualization), basic graph knowledge would be a plus
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|
| No
|-
|-
| Traffic prediction with GNN (Intern/Project/Thesis possible)
| In this topic, student will study how to use XGNN to predict traffic volumn.
| Python(Modeling and Visualization). Graph and XAI knowledge.
| [Zhengze Li, zhengze.li@cs.uni-goettingen.de]
|
| No
|-
|-
| Self-supervised Learning and Foundation Models for Remote Sensing Applications
| In this topic, you will study (and if desired, also apply) self-supervised learning methods and Foundation Models for remote sensing applications (e.g. semantic segmentation of satellite images, super-resolution, estimation of socioeconomic indicators by utilizing satellite images, change detection, disaster monitoring, etc.).
| Basic machine learning knowledge
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
|
| Yes
|-
|-
|-
|-
Line 84: Line 60:
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
| [Fabian Wölk, fabian.woelk@cs.uni-goettingen.de]
|
|
| Yes
| No
|-
|-
|-
|-
Line 95: Line 71:
|-
|-
|-
|-
| Personalized chatbot based on ChatGPT
| In this topic, you will learn about ChatGPT and learn to use OpenAI ChatGPT API to create a personalized chatbot.
| NLP & ChatGPT
| [Wenfang Wu, wenfang.wu@cs.uni-goettingen.de]
|
| Yes
|-
|-
|-
|-
| Multimodal Large Language Model Evaluation for Multimodal Tasks
| Sign language translation
| This topic focuses on assessing the performance and effectiveness of large language models in handling tasks that involve multiple modalities, such as text, images, and audio. It involves the evaluation of these large models using specialized multimodal datasets, considering both quantitative metrics and qualitative analysis. In this topic, you will gain insights into various large models, including GPT-4, and acquire knowledge about a wide range of multimodal tasks. Additionally, you will become proficient in implementing evaluations related to these tasks.
| This topic focuses on assessing the performance and effectiveness of large language models in handling sign language translation tasks, which involve converting between sign language (visual modality) and spoken language (text or audio). In this topic, you will gain insights into various sign language translation models and multimodal frameworks, and acquire knowledge about a wide range of tasks, including sign language recognition and natural language generation. Additionally, you will become proficient in implementing evaluations related to these tasks.
| Large Language Model & multimodal setting
| Large Language Model & multimodal setting
| [Wenfang Wu, wenfang.wu@cs.uni-goettingen.de]
| [Wenfang Wu, wenfang.wu@cs.uni-goettingen.de]
Line 111: Line 81:
|-
|-
|-
|-
| Emotional Support Conversation Generation
| Long-Video Understanding and Video Question Answering
| Does the large language model have emotions? Can it provide emotional support to users? In this topic, you will learn about techniques of large language models, such as prompt engineering and instruction fine-tuning, and use the above approaches to implement the emotional support conversation.
| In this topic, you will study methods for understanding long videos and for answering questions based on video content. This includes long-range temporal modeling, multimodal video understanding, and question answering over complex video sequences.
| Large Language Model & Emotional Support
| Vision-language models & Large language model
| [Jing Li, jing.li@cs.uni-goettingen.de]
| [Haihan Zhang, haihan.zhang@cs.uni-goettingen.de]
|  
|  
| Yes
| Yes
|-
|-
|-
|-
| Rumor control and detection
| CoT Compression for Efficient Reasoning
| This topic focuses on how to analyze social networks, study information propagation models and design rumor control strategies. At the same time, you will consider automatically identifying and preventing the spread of false or misleading information in social networks to help reduce the spread of rumor information.
| In this topic, you will study methods to improve the efficiency of Chain-of-Thought (CoT) reasoning in large language models by reducing redundant or verbose reasoning steps. This includes techniques such as summarization-based compression, iterative reasoning, and latent reasoning representations. You will explore how compression affects reasoning accuracy, computational cost, and attention mechanisms, and implement approaches to balance efficiency and performance.
| Information Propagation  & GCN.
| Large Language Models & NLP (familiarity with Transformer architecture is recommended)
| [Fei Gao, fei.gao@cs.uni-goettingen.de]
| [Hao Xu, hao.xu@cs.uni-goettingen.de]
|  
|  
| Yes
| Yes
|-
|-
|-
|-
|Task Offloading and Resource Allocation Optimization
| Adaptive Compression for Collaborative SLAM
|This topic presents efficient joint task offloading and auction-based resource allocation mechanisms in edge computing, which not only expand the computational capabilities of mobile devices but also enhance the Quality of Service of IoT applications by significantly reducing latency.
| In this topic, you will study (adaptive) compression approaches for data exchange in collaborative SLAM settings. The work involves an examination of how existing compression methods for C-SLAM can be adapted, tuned or evaluated under constrained network conditions by tracing data through multiple stages of the pipeline and analyzing how compression choices affect system behavior and downstream SLAM performance.
|Edge computing & Basic optimization algorithms.
| Prior experience with SLAM, compression and systems programming; programming skills in C++ and Python; familiarity with ROS is recommended
|[dongkuo.wu@cs.uni-goettingen.de]
| [Jan Lenke, jan.lenke@cs.uni-goettingen.de]
|
|  
|Yes
| Yes
|-
|-
|-
|-
Retrieved from "https://wiki.net.informatik.uni-goettingen.de/wiki/Seminar_on_Internet_Technologies_(Winter_2026/2027)"