8000 choiszt (Shuai Liu) ยท GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View choiszt's full-sized avatar
๐ŸŽฏ
Focusing
๐ŸŽฏ
Focusing

Highlights

  • Pro

Block or report choiszt

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this userโ€™s behavior. Learn more about reporting abuse.

Report abuse
choiszt/README.md

My name is Liu Shuai, and I am a MPhil student at MMLab@NTU, Singapore.

๐Ÿ” My research focus on Multimodality and Egocentric AI.
As a member of LMMs-Lab , I am on an exciting journey towards LMMs and feeling the AGI.

Besides, I'm on my way to becoming a full-stack developer (with VibeCoding ๐Ÿคฃ), and spend 2% of my free time developing webgames.

๐Ÿš€ Previous Projects:

โœจStay Tuned for more wonderful research. โœจ

๐Ÿš€ Introducing Aero-1-Audio โ€” a compact yet mighty audio model.

  • โšก Trained in <24h on just 16ร—H100
  • ๐ŸŽง Handles 15+ min audio seamlessly
  • ๐Ÿ’ก Outperforms Whisper, Qwen-2-Audio, and ElevenLabs/Scribe

In the journey towards creating ๐Ÿ‘“ egocentric life-long intelligence, I gained experience curating and training egocentric MLLMs with multimodal inputs (audio, video, IMU, etc.).

Gained experience in utilizing VLMs for embodied code execution.

Also worked as a temporary ๐Ÿฅท game hacker (for research purpose), compiling C# plugins for GTA-V and TypeScript for Minecraft.

There, I learned the principles of ๐Ÿ•ธ๏ธLMMs Evaluation and was the main contributor in customizing new LMMs, implementing multi-node model inference and multiprocessing.

๐Ÿ“ˆ GitHub Stats

๐Ÿ“ฌ Get in Touch

Feel free to reach out for collaboration or just chat!

Pinned Loading

  1. EvolvingLMMs-Lab/EgoLife EvolvingLMMs-Lab/EgoLife Public

    [CVPR 2025] EgoLife: Towards Egocentric Life Assistant

    Python 281 17

  2. EvolvingLMMs-Lab/lmms-eval EvolvingLMMs-Lab/lmms-eval Public

    Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

    Python 2.5k 279

  3. dongyh20/Octopus dongyh20/Octopus Public

    [ECCV2024] ๐Ÿ™Octopus, an embodied vision-language model trained with RLEF, emerging superior in embodied visual planning and programming.

    Python 287 18

  4. Jingkang50/PSG4D Jingkang50/PSG4D Public

    4D Panoptic Scene Graph Generation (NeurIPS'23 Spotlight)

    Python 109 3

  5. circlemind-ai/fast-graphrag circlemind-ai/fast-graphrag Public

    RAG that intelligently adapts to your use case, data, and queries

    Python 3.3k 184

0