Log inSign up
Shunlin Lu
17 posts
@ShunlinL

Shunlin Lu

@ShunlinL
First-year PhD student at CUHK(SZ), intern at IDEA now
Joined November 2021
62
Following
37
Followers
RepliesRepliesRepostsRepostsMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • @ShunlinL
    Shunlin Lu
    @ShunlinL
    Sep 18, 2025
    A unified learning paradigm is crucial for robotis. Check out our recent understanding of WBC.
    @weishuaizeng
    Weishuai Zeng
    @weishuaizeng
    Sep 18, 2025
    We are excited to re-introduce our Behavior Foundation Model for Humanoid Robots, built upon a unified perspective of diverse WBC tasks, as a promising step toward a foundation model for general humanoid control. 🔗Website: bfm4humanoid.github.io 📜Paper: arxiv.org/abs/2509.13780
    Image
    00:00
  • @ShunlinL
    Shunlin Lu
    @ShunlinL
    Mar 24, 2025
    MotionStreamer offers multi-round generation, long-term generation, and dynamic motion composition, which delivers a brand-new experience for animation users. Explore more at: arxiv.org/abs/2503.15451 and zju3dv.github.io/MotionStreamer/
    @_akhaliq
    AK
    @_akhaliq
    Mar 23, 2025
    MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
    Image
    00:00
  • @ShunlinL
    Shunlin Lu
    @ShunlinL
    Oct 25, 2024
    A simple but effective motion editing way through attention mechanisms.
    @Evan_THU
    Ling-Hao CHEN (on job market)
    @Evan_THU
    Oct 25, 2024
    💃 Introducing #MotionCLR: MotionCLR is a motion generation model, supporting versatile interactive training-free motion editing methods. 📖Paper: arxiv.org/pdf/2410.18977 🏠Page: lhchen.top/MotionCLR 🖊️Blogpost: huggingface.co/blog/EvanTHU/m… 💻Code: github.com/IDEA-Research/…
    Image
    00:00
  • @ShunlinL
    Shunlin Lu
    @ShunlinL
    May 31, 2024
    The initial attempt of human behavior in VLM, hope to expand it into an all-knowing and all-powerful VLA model in the future. Perception module provides spatial information, the understanding module is for reasoning and planning, and the action model is for guiding the controls.
    @Evan_THU
    Ling-Hao CHEN (on job market)
    @Evan_THU
    May 31, 2024
    🔥Today, we announce the #MotionLLM💃, an LLM-based motion/video model for human behavior understanding! 📖Paper: arxiv.org/pdf/2405.20340 🏠Project page: lhchen.top/MotionLLM 🤗Demo: demo.humotionx.com ✍️Blogpost: research.lhchen.top/blogpost/motio… 💻Code: github.com/IDEA-Research/…
    Image
    00:00
  • @ShunlinL
    Shunlin Lu
    @ShunlinL
    May 17, 2024
    Amazing work. Proud of the whole team of IDEA CVR.
    @_akhaliq
    AK
    @_akhaliq
    May 17, 2024
    Grounding DINO 1.5 Advance the "Edge" of Open-Set Object Detection This paper introduces Grounding DINO 1.5, a suite of advanced open-set object detection models developed by IDEA Research, which aims to advance the "Edge" of open-set object detection. The suite encompasses
    Image
Advertisement
Advertisement