BEIHANG UNIVERSITY

Yiming Jiang 姜一铭

Ph.D. Student Beijing, China

I am a Ph.D. student at Beihang University, in the State Key Laboratory of Virtual Reality Technology and Systems, advised by Prof. Aimin Hao.

I am a research intern at Tongyi Lab, Alibaba, working on embodied intelligence and human reconstruction. My research interests span Embodied AI, Human Data, and 3D Vision. I explore how robots can learn generalizable mobile manipulation skills from human data.

I expect to graduate in 2027 and am seeking researcher positions in embodied AI. Please feel free to get in touch!

News

Research updates

2026HiReFF is accepted to ECCV 2026.
2026DECON appears in AAAI 2026.
2025HFHuman is published online in IEEE TVCG.

Experience

Research internships

Tongyi Lab, Alibaba

Feb 2026 – Present

Research Intern · Multimodal Group

Embodied AI & Human Reconstruction

Xiaohongshu

Nov 2025 – Feb 2026

Algorithm Intern · Effects & Rendering

Feedforward 3D Gaussian Reconstruction

Tsinghua University

Apr 2025 – Nov 2025

Research Intern · Prof. Yebin Liu’s Group

Dynamic 3D Human Reconstruction

Publications

Google Scholar

EgoAlign converts human demonstrations into humanoid action and state supervision

arXiv 2026

EgoAlign: Bridging the Human-Humanoid Gap for Long-Range Loco-Manipulation

Yiming Jiang, Chen Jin, Chongyang Xu, Yilun Chen, Aimin Hao, Yisheng He

Adapting egocentric human demonstrations for zero-shot humanoid learning and long-range loco-manipulation.

† Work done during an internship at Alibaba Token Hub (ATH), Alibaba Group.

Project Paper PDF

EgoHumanoid-V2 transfers human whole-body skills to humanoid robots

arXiv 2026

EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation

Jin Chen, Yiming Jiang, Chongyang Xu, Modi Shi, Shijia Peng, Li Chen, Tianyu Li, Mu Xu, Yilun Chen, Steven Hoi, Hongyang Li

Transferring coordinated whole-body skills from human demonstrations to humanoids through action and visual alignment.

† Work done during an internship at Alibaba Token Hub (ATH), Alibaba Group.

Project Paper PDF

FA-LAM uses image and UV features to reconstruct animatable Gaussian heads

NeurIPS 2026

FA-LAM: Focus-Aware Large Avatar Model for One-Shot 4D Animatable Gaussian Head

Yingdong Hu, Yisheng He, Yiming Jiang, Zehong Lin, Steven Hoi, Jun Zhang

Reconstructing animatable Gaussian heads from a single image, with support for multi-view input and streaming 4D reconstruction.

† Work done during an internship at Alibaba Token Hub (ATH), Alibaba Group.

Paper PDF

HiReFF reconstructs high-resolution 3D humans from sparse camera views

ECCV 2026

HiReFF: High-Resolution Feedforward Human Reconstruction from Uncalibrated Sparse-View Video

Yiming Jiang, Hanzhang Tu, Wenfeng Song, Siyou Lin, Liang An, Shuai Li, Aimin Hao, Yebin Liu

Feedforward 2K human reconstruction from just four uncalibrated video views.

† Work done during an internship at Tsinghua University.

Project Paper Code

DECON reconstructs separate clothed 3D people from an image of human interaction

AAAI 2026

DECON: Reconstruction of Clothed-Geometric Multiple Humans from a Single Image via Geometry-Guided Decoupling

Yiming Jiang, Wenfeng Song, Shuai Li, Aimin Hao

Reconstructing interacting people with detailed clothing and consistent spatial relationships.

SIGGRAPH Asia 2025 · Invited Poster
China3DV 2026 · Invited Poster

Paper Code

HFHuman combines normal, depth and geometry information for detailed human reconstruction

IEEE TVCG 2026 · Online 2025

HFHuman: High-Fidelity Human Reconstruction from Single Image with Multi-Modality Fusion

Yiming Jiang, Wenfeng Song, Shuai Li, Aimin Hao

Fusing depth, surface normals, and body geometry to recover detailed 3D humans.

SIGGRAPH Asia 2025 · Invited Poster

Paper Code

Expressive 3D facial animation with local-to-global latent diffusion

IEEE TVCG 2024

Expressive 3D Facial Animation Generation Based on Local-to-Global Latent Diffusion

Wenfeng Song, Xuan Wang, Yiming Jiang, Shuai Li, Aimin Hao, Xia Hou, Hong Qin

Audio-driven facial animation that combines synchronized lip movements with expressive facial detail.

Paper Code

The Frequency-Guided Network pipeline for dental plaque segmentation

IEEE BIBM 2024

Frequency-Guided Network for Low-contrast Staining-free Dental Plaque Segmentation

Yiming Jiang, Wenfeng Song, Shuai Li, Yuming Yang, Bin Xia, Aimin Hao, Hong Qin

Using image frequency to locate low-contrast dental plaque without staining.

Project Paper Code