Skip to content
View zjysteven's full-sized avatar
104 followers · 23 following

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy BrainAchievement: Starstruckx2Achievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: Pair Extraordinairex2Achievement: Galaxy BrainAchievement: Starstruckx2Achievement: Pull Sharkx2Achievement: YOLO

Block or report zjysteven

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
zjysteven/README.md

Hi there 👋

I'm Jingyang (Steven) Zhang, a Research Scientist at Meta Superintelligence Labs (joined via Virtue AI acqui-hire), working on agent safety & security. Previously I got my Ph.D. from Duke University in 2024 (supervised by Prof. Yiran Chen and Prof. Hai (Helen) Li) and Bachelor degree from Tsinghua University in 2019.

See my personal webpage to know more about me.

Jingyang's GitHub stats

Pinned Loading

  1. Gen-Verse/OpenClaw-RL Gen-Verse/OpenClaw-RL Public

    OpenClaw-RL: Train any agent simply by talking

    Python 5.6k 608

  2. Jingkang50/OpenOOD Jingkang50/OpenOOD Public

    Benchmarking Generalized Out-of-Distribution Detection

    Python 1.1k 180

  3. lmms-finetune lmms-finetune Public

    A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

    Python 373 44

  4. VLM-Visualizer VLM-Visualizer Public

    Visualizing the attention of vision-language models

    Jupyter Notebook 304 26

  5. mink-plus-plus mink-plus-plus Public

    [ICLR'25 Spotlight] Min-K%++: Improved baseline for detecting pre-training data of LLMs

    Python 59 12

  6. DVERGE DVERGE Public

    [NeurIPS'20 Oral] DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles

    Python 55 13