Peiming Li

Portrait of Peiming Li

News

  1. [2026-05]

    MSPNet is accepted by IEEE Transactions on Image Processing (TIP)!

  2. [2026-04]

    SkeletonLLM is accepted by ICML 2026!

  3. [2026-02]

    Superman is accepted by CVPR 2026!

  4. [2025-12]

    MP1 is accepted by AAAI 2026!

  5. [2025-06]

    ACTIVE and UST-SSM are accepted by ICCV 2025!

  6. [2024-07]

    ClickDiff is accepted by ACM MM 2024 as an oral presentation!

Publications

* indicates equal contribution, # indicates corresponding author.

SkeletonLLM rendered handstand motion

(SkeletonLLM) Universal Skeleton Understanding via Differentiable Rendering and MLLMs

Ziyi Wang*, Peiming Li*, Xinshun Wang*, Yang Tang, Kai-Kuang Ma, Mengyuan Liu#

International Conference on Machine Learning (ICML), 2026

arXiv / Code / Visualization
Physical privacy-preserving action recognition benchmark

Lens Privacy Sealing: A New Benchmark and Method for Physical Privacy-Preserving Action Recognition

Mengyuan Liu, Ziyi Wang#, Peiming Li#, Junsong Yuan

IEEE Transactions on Image Processing (TIP), 2026

arXiv / Code / Dataset
Superman project overview

Superman: Unifying Skeleton and Vision for Human Motion Perception and Generation

Xinshun Wang*, Peiming Li*, Ziyi Wang*, Zhongbin Fang, Zhichao Deng, Songtao Wu, Jason Li, Mengyuan Liu#

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

arXiv / Code
MP1 robot demonstrations under clutter and changing lighting

MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation

Juyi Sheng*, Ziyi Wang*, Peiming Li, Mengyuan Liu#

AAAI Conference on Artificial Intelligence, 2026

arXiv / Code
ACTIVE project overview

(ACTIVE) Recognizing Actions from Robotic View for Natural Human-Robot Interaction

Ziyi Wang, Peiming Li, Hong Liu, Zhichao Deng, Can Wang, Jun Liu, Junsong Yuan, Mengyuan Liu#

IEEE International Conference on Computer Vision (ICCV), 2025

arXiv / Project / Code
UST-SSM overview

UST-SSM: Unified Spatio-Temporal State Space Models for Point Cloud Video Modeling

Peiming Li, Ziyi Wang, Yulin Yuan, Hong Liu, Xiangming Meng, Junsong Yuan, Mengyuan Liu#

IEEE International Conference on Computer Vision (ICCV), 2025

arXiv / Code
ClickDiff overview

ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models

Peiming Li*, Ziyi Wang*, Mengyuan Liu#, Hong Liu, Chen Chen

ACM International Conference on Multimedia (ACM MM), 2024 (Oral Presentation)

arXiv / Code

© Peiming Li  ·  Template adapted from Jon Barron