Log inSign up
Zinan Lin
132 posts
@lin_zinan

Zinan Lin

@lin_zinan
Principal Researcher at @MSFTResearch, PhD from @CarnegieMellon
United States
zinanlin.me
Joined March 2020
64
Following
225
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    @lin_zinan
    Zinan Lin
    @lin_zinan
    Sep 22, 2025
    @_akhaliq Thank you very much for featuring our work! We’re excited to share that it has just been accepted to NeurIPS 2025. The code & model are now open-sourced here: github.com/microsoft/late… The website for a quick summary of the work: zinanlin.me/blogs/latent_z…
    @_akhaliq
    AK
    @_akhaliq
    Sep 22, 2025
    Latent Zoning Network A Unified Principle for Generative Modeling, Representation Learning, and Classification
    Image
  • @lin_zinan
    Zinan Lin
    @lin_zinan
    Nov 15, 2025
    Check out our latest work on blue-teaming code agent! Led by @ChengquanGuo @NieYuzhou @ChulinXie @WenboGuo4 @uiuc_aisecure
    @MSFTResearch
    Microsoft Research
    Microsoft
    @MSFTResearch
    Nov 11, 2025
    BlueCodeAgent is an end-to-end blue-teaming framework built to boost code security using automated red-teaming processes, data, and safety rules to guide LLMs’ defensive decisions. Dynamic testing reduces false positives in vulnerability detection: msft.it/6014tMvnr
    Three white line icons on a blue-to-green gradient background: the first icon on the left shows a network with a central circle connected to smaller circles; the middle icon shows a microchip with a shield symbol in the center; the right icon depicts a flowchart with connected shapes.
  • @lin_zinan
    Zinan Lin
    @lin_zinan
    Nov 4, 2025
    Check out our latest work on red-teaming code agent! Led by @ChengquanGuo @ChulinXie @YuYang_i @ZRChen_AISafety @alxndrdavies @yaringal @dawnsongtweets @uiuc_aisecure
    @MSFTResearch
    Microsoft Research
    Microsoft
    @MSFTResearch
    Nov 4, 2025
    Code agents help streamline software development workflows, but may also introduce critical security risks. Learn how RedCodeAgent automates and improves “red-teaming” attack simulations to help uncover real-world threats that other methods overlook: msft.it/6013shouB
    Icons of a chat bubble, connected document, and shield with checkmark on a blue-green gradient background.
  • @lin_zinan
    Zinan Lin
    @lin_zinan
    Oct 2, 2025
    Super cool! Really innovative use of Private Evolution votes as the RL reward to fine-tune LLMs — a big step forward for DP synthetic data. Congrats, @hou_char!
    @hou_char
    Charlie Hou
    @hou_char
    Oct 2, 2025
    Gave a talk at @OpenAI on our work 🌸 POPri “Policy Optimization for Private Data”. POPri is a huge improvement in synthetic data generation under security+privacy constraints! Learn more:
    Image
  • @lin_zinan
    Zinan Lin
    @lin_zinan
    Apr 13, 2025
    🎉Excited to share that our team, imagination-research, has won the 𝟮𝗻𝗱 𝗽𝗹𝗮𝗰𝗲 in AI Mathematical Olympiad 2 (1st place on the public leaderboard), solving 31/50 problems at National Mathematical Olympiad level with a 14B LLM. W/ Yichen You, @FiNingm #AIMO #AIMO2 #kaggle
    Image
    1
Advertisement
Advertisement