FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Original HTTPS Page]

Nexround (Runyu Wang) · GitHub

Overview Repositories 33 Projects Packages Stars 173
4 followers · 3 following
  • Nantong University
  • Nantong

Achievements

Achievements

Highlights

  • Pro

Block or report Nexround

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.

Close all issues, pull requests, and discussions opened by this user Content in all repositories owned by your account will be closed.
Add an optional note
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
Nexround/README.md

Hi, I'm Runyu Wang (王润瑀) 👋

About Me

I am a master's student in Information and Communication Engineering at Nantong University, focusing on explainable AI (XAI) and large language model post-training. I am currently seeking Ph.D. opportunities.

Research Interests

Publications

LoKI: Low-damage Knowledge Implanting of Large Language Models

AAAI 2026 Oral
Authors: Runyu Wang, Peng Ping, Zhengyu Guo, Xiaoye Zhang, Quan Shi, Liting Zhou, Tianbo Ji
[Paper] [Code]

LoKI is a low-damage fine-tuning approach grounded in mechanistic interpretability. It combines knowledge-vector attribution with layer-wise balancing to identify critical parameters, improving downstream performance while substantially mitigating catastrophic forgetting.

Catastrophic Forgetting · Parameter-Efficient Fine-Tuning · Knowledge Localization · Mechanistic Interpretability

RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons

EMNLP 2026 Main
Authors: Runyu Wang, Bo Liu, Xiaxin Zhang, Yu Han, Jiawei Cao, Xiaoye Zhang, Zhe Zhang, Yifan Yang, Peng Ping
[Paper] [Code]

RACE efficiently identifies LLM neurons that exhibit functional consistency within representative corpus domains. By analyzing model residuals, it provides a scalable and cost-effective tool for large-scale model auditing.

Knowledge Localization · Mechanistic Interpretability · Model Auditing · Residual Analysis

Popular repositories Loading

  1. LoKI LoKI Public

    AAAI-26 Oral | Implementation of "LoKI: Low-damage Knowledge Implanting of Large Language Models"

    Python 24 1

  2. Raspberrypi-DS3231 Raspberrypi-DS3231 Public

    A Raspberry Pi C Library for DS3231 Real-Time Clocks

    C 1

  3. linux-wifi-hotspot linux-wifi-hotspot Public

    Forked from lakinduakash/linux-wifi-hotspot

    Feature-rich wifi hotspot creator for Linux which provides both GUI and command-line interface. It is also able to create a hotspot using the same wifi card which is connected to an AP already ( Si…

    Shell 1

  4. obsidian-text-lens obsidian-text-lens Public

    Obsidian plugin: run PaddleX OCR on images in your notes and insert recognized text inline

    TypeScript 1

  5. RACE RACE Public

    EMNLP-26 Main | Implementation of "RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons"

    1

  6. httpserver.h httpserver.h Public

    Forked from jeremycw/httpserver.h

    Single header library for writing non-blocking HTTP servers in C

    C

Back | FazBrowse Home | New Git URL