Skip to content
View Thecommonirin's full-sized avatar
12 followers · 20 following
  • Zhejiang University

Block or report Thecommonirin

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Thecommonirin/README.md

TheCommonIrin ✨

I am a Ph.D. candidate at the Visual Intelligence and Pattern Analysis (VIPA) Lab, Zhejiang University, advised by Prof. Zunlei Feng and Prof. Mingli Song. My research focuses on building Trustworthy Machine Learning systems, with an emphasis on the safety and alignment of Large Language Models.

Currently, I am a Visiting Student at Nanyang Technological University, under the esteemed supervision of Prof. Tianwei Zhang.

🏠 thecommonirin.github.io

πŸ“š Activities

  • πŸŽ‰ [ICLR 2026] "Safety at One Shot: Patching Fine-Tuned LLMs with A Single Instance" was accepted.
  • πŸ“ [PR 2026] "Self-Improved Holistic Alignment for Preference Enhancement" was accepted by Pattern Recognition.
  • πŸ‘¨β€πŸ’» Serving as a Program Committee / Reviewer for ICML, ICLR, ECCV, TIFS, NeurIPS, CVPR, ICCV, ACL, EMNLP, etc.

Pinned Loading

  1. Qresafe Qresafe Public

    Q-resafe:Assessing Safety Risks and Quantization-aware Safety Patching for Quantized Large Language Models (ICML'2025)

    Python 15 2

  2. LLM_Prompt_Recovery LLM_Prompt_Recovery Public

    Jupyter Notebook 2

  3. CASPO CASPO Public

    Step-level Confidence-aware Optimization for Large Reasoning Models

    Python

  4. SHAPE SHAPE Public

    SHAPE: Self-Improved Holistic Alignment for Preference Enhancement (Pattern Recognition'2026)

    Python