Junliang Ye | 叶俊良
I am a third-year master's student in the Department of
Computer Science at Tsinghua University ,
advised by Prof. Jun Zhu.
In 2022, I obtained my B.S. in the School of Mathematical Sciences at Peking University.
My research interests lie in computer vision (e.g., 3D AIGC and video generation), multimodal large models (e.g., native large models), and reinforcement learning from human feedback (DPO, GRPO).
My email:yejl23@mails.tsinghua.edu.cn
Email  / 
CV  / 
Google Scholar  / 
Github
|
|
News
2025-09: One papers on 3D-MLLM are accepted by NeurIPS 2025.
2025-09: One papers on 3D Vision are accepted by TPAMI 2025.
2025-06: One papers on 3D Vision are accepted by ICCV 2025.
2024-07: Two papers on 3D AIGC are accepted by ECCV 2024.
|
Preprints
*equal contribution     †Project leader
|
|
DeepMesh-v2: Auto-Regressive Artist-Mesh Creation With Reinforcement Learning
Junliang Ye*,
Ruowen Zhao*,
Zhengyi Wang*,
et. al
Arxiv, 2025
[arXiv]
[Code]
[Project Page]
We propose DeepMesh-v2, which generates meshes with intricate details and precise topology,
surpassing state-of-the-art methods in both precision and quality.
|
|
Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
Chunshi Wang*,
Junliang Ye†*,
Yunhan Yang*,
et. al
Arxiv, 2025
[arXiv]
[Code]
[Project Page]
We introduce Part-X-MLLM, a native 3D multimodal large language model that unifies diverse 3D tasks by formulating them as programs in a structured, executable grammar.
|
|
NANO3D: A Training-Free Approach for Efficient 3D Editing Without Masks
Junliang Ye*,
Shenghao Xie*,
Ruowen Zhao,
Zhengyi Wang,
Hongyu Yan,
et. al
Arxiv, 2025
[arXiv]
[Code]
[Project Page]
we propose Nano3D, a training-free framework for precise and coherent 3D object editing without masks.
|
|
ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding
Junliang Ye*,
Zhengyi Wang*,
Ruowen Zhao*,
Shenghao Xie,
Jun Zhu
NeurIPS, 2025   (Spotlight)
[arXiv]
[Code]
[Project Page]
We propose ShapeLLM-Omni, a multimodal large model that integrates 3D generation, understanding, and editing capabilities.
|
|
DeepMesh: Auto-Regressive Artist-Mesh Creation With Reinforcement Learning
Ruowen Zhao*,
Junliang Ye*,
Zhengyi Wang*,
et. al
ICCV, 2025
[arXiv]
[Code]
[Project Page]
We propose DeepMesh, which generates meshes with intricate details and precise topology,
surpassing state-of-the-art methods in both precision and quality.
|
|
DreamReward-X: Boosting High-Quality 3D Generation with Human Preference Alignment
Fangfu Liu,
Junliang Ye,
et. al
TPAMI, 2025
[arXiv]
[Code]
[Project Page]
We present a comprehensive framework, coined DreamReward++, where we introduce a reward-aware noise sampling strategy
to unleash text-driven diversity during the generation process while ensuring human preference alignment. Grounded
by theoretical proof and extensive experiment comparisons, our method successfully generates high-fidelity and
diverse 3D results with significant boosts in prompt alignment with human intention.
Our results demonstrate the great potential for learning from human feedback to improve 3D generation.
|
|
DreamReward: Aligning Human Preference in Text-to-3D Generation
Junliang Ye*,
Fangfu Liu*,
Qixiu Li,
Zhengyi Wang,
et. al
ECCV, 2024
[arXiv]
[Code]
[Project Page]
We present a comprehensive framework, coined DreamReward, to
learn and improve text-to-3D models from human preference feedback.
|
|
AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation
and Reconstruction with Canonical Score Distillation
Xinzhou Wang,
Yikai Wang,
Junliang Ye,
et. al
ECCV, 2024
[arXiv]
[Code]
[Project Page]
We propose ANIMATABLEDREAMER, a framework with the capability to generate generic categories of non-rigid 3D models.
|
|
ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model
Fangfu Liu*,
Wenqiang Sun*,
Hanyang Wang*,
Yikai Wang,
Sun Haowen,
Junliang Ye,
Jun Zhang,
Yueqi Duan
Arxiv, 2024
[arXiv]
[Code]
[Project Page]
In this paper, we propose ReconX, a novel 3D scene reconstruction paradigm that reframes
the ambiguous reconstruction challenge as a temporal generation task. The key insight is to
unleash the strong generative prior of large pre-trained video diffusion models
for sparse-view reconstruction.
|
|
PKU_WICT at TRECVID 2022: Disaster Scene Description and Indexing Task
Yanzhe Chen,
HsiaoYuan Hsu,
Junliang Ye,
Zhiwen Yang,
Zishuo Wang,
Xiangteng He,
Yuxin Peng
Virtual, Online
[arXiv]
[Code]
[Project Page]
We achieved first place in the TRECVID 2022 competition.
|
Academic Services
Review for CVPR 2023.
|
© Junliang Ye | Last updated: 29 Sep, 2025
|