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
AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes
Frequency-Domain Model Fingerprinting for Image Autoregressive Models
Auditing Privacy Leakage in Tabular Foundation Model Embeddings
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
Xun Wang
Third-year Ph.D. student at TUM and CISPA, researching privacy-preserving adaptation and post-training, model provenance, and trustworthy world models.
Archive Layout with Content
Posts by Category
Posts by Collection
CV - Xun Wang
Curriculum Vitae of Xun Wang, third-year Ph.D. student at TUM and CISPA specializing in trustworthy and efficient machine learning.
Markdown
Page not in menu
Page Archive
Portfolio
Publications - Xun Wang
Research publications by Xun Wang on trustworthy machine learning.
Sitemap
Posts by Tags
Talk map
Talks and presentations
Teaching
Terms and Privacy Policy
Blog posts
Publication teasers
Jupyter notebook markdown generator
AgentProv web assets
FreqIAR web assets
Camera-ready figure assets
Posts
Future Blog Post
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
,
Blog Post number 4
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
,
Blog Post number 3
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
,
Blog Post number 2
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
,
Blog Post number 1
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
,
portfolio
Structurally Prune Anything (SPA)
A universal structured pruning framework for neural networks that works across any architecture, framework, and training stage
Privacy-Preserving Soft Prompt Transfer (POST)
Efficient and privacy-preserving framework for transferring soft prompts between large language models with differential privacy guarantees
publications
Structurally Prune Anything: Any Architecture, Any Framework, Any Time
A versatile structured pruning framework that works across any neural network architecture, framework, and training stage, introducing OBSPA for post-training pruning without fine-tuning.
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
A novel framework for transferring soft prompts between LLMs while preserving privacy through differential privacy and knowledge distillation techniques.
Frequency-Domain Model Fingerprinting for Image Autoregressive Models
FreqIAR: A frequency-domain approach for fingerprinting image autoregressive models.
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
A systematic benchmark investigating privacy risks under differentially private adaptations of LLMs using state-of-the-art attacks such as robust membership inference and canary data extraction.
AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes
AgentProv audits the identity of agentic LLM APIs through their tool-selection behavior, using action-based fingerprints and an MMD permutation test.
Auditing Privacy Leakage in Tabular Foundation Model Embeddings
Cascade Probing audits sensitive-attribute leakage from tabular foundation-model embeddings and reveals a privacy cliff when additional attributes are known.
Provenance Tracing for World Models: Was this Agent Trained in my World Model?
Provenance tracing for agents trained in world models.
talks
Talk 1 on Relevant Topic in Your Field
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
UC San Francisco, Department of Testing ,
Tutorial 1 on Relevant Topic in Your Field
UC-Berkeley Institute for Testing Science ,
Talk 2 on Relevant Topic in Your Field
London School of Testing ,
Conference Proceeding talk 3 on Relevant Topic in Your Field
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Testing Institute of America 2014 Annual Conference ,
teaching
Machine Learning
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
University 1, Department ,