Skip to content
View wuyoscar's full-sized avatar
🧑‍🍳
🧑‍🍳

Highlights

  • Pro

Block or report wuyoscar

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 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
wuyoscar/README.md

header


👋 About Me

class OscarWu:
    def __init__(self):
        self.role = "PhD Student"
        self.location = "🌏"

        # Focus
        self.current_focus = "Exploring interesting ideas"
        self.passion = ["Tools", "Software", "LLM robustness"]

    def say_hi(self):
        return "Thanks for stopping by."

    def today(self):
        return {
            "status": "Trapped in a paper that somehow gets less interesting with every page."
        }

footer

Pinned Loading

  1. ISC-Bench ISC-Bench Public

    Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.

    Python 783 120

  2. gpt_image_2_skill gpt_image_2_skill Public

    GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

    Python 447 41

  3. PaperAsk PaperAsk Public

    [WWW'26] A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading

    1

  4. heretic heretic Public

    Forked from p-e-w/heretic

    Fully automatic censorship removal for language models

    Python 1 1

  5. UltraBreak UltraBreak Public

    Forked from kaiyuanCui/UltraBreak

    [ICLR2026] Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models

    Python

  6. XSafeClaw XSafeClaw Public

    Forked from XSafeAI/XSafeClaw

    Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

    Python