Skip to content
View wzrwzr23's full-sized avatar
7 followers · 25 following

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Block or report wzrwzr23

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.

Content in all repositories owned by your account will be closed.
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
wzrwzr23/README.md

Zhuoran Wang

AI engineer working on multimodal safety systems and evaluation at SUTD's Social AI Lab. I build benchmarks and eval harnesses — measuring what models and agents actually do, rather than iterating by trial and error.

Publications

  • HateClipSeg: A Segment-Level Annotated Dataset for Fine-Grained Hate Video Detection — ACM MM 2025
  • SafeLens: Segment-Level Hate Speech Detection in Online Videos — AAAI 2026 (Demo)

Currently

  • A benchmark for detecting harmful AI-generated children's video content — harm taxonomy, synthetic evaluation data, VLM fine-tuning and comparative evaluation
  • agentlab — multi-agent architectures compared on a 62-task benchmark with a real eval harness

Work with Python · PyTorch · Hugging Face · vision-language models · LoRA · Docker · Linux · GPU clusters

📫 zhuoranwang2@gmail.com · LinkedIn

Pinned Loading

  1. agentlab agentlab Public

    Python

  2. arxiv-search-engine arxiv-search-engine Public

    Jupyter Notebook