I am a Postdoc Researcher at TU/e AMOR/e Lab, working with Prof. Joaquin Vanschoren on LLMs and MLLMs (funded by project OpenEuroLLM). Previously I was an ELLIS Ph.D. candidate at VISLAB, University of Amsterdam (UvA), supervised by Prof. Efstratios Gavves and Prof. Jan-Jakob Sonke. I did a fantastic internship at Meshcapade, advised by Dr. Yan Zhang, Dr. Yu Sun, and Prof. Michael J. Black. I also worked closely with Prof. Pan Zhou. 我目前是 TU/e AMOR/e Lab 的博士后研究员，与 Joaquin Vanschoren 教授合作研究 LLMs 与 MLLMs（由 OpenEuroLLM 资助）。 此前我在阿姆斯特丹大学（UvA）VISLAB 担任 ELLIS 博士生， 导师为 Efstratios Gavves 教授 和 Jan-Jakob Sonke 教授。 我曾在 Meshcapade 实习，由 Yan Zhang 博士、Yu Sun 博士 和 Michael J. Black 教授 指导。 此外，我与 Pan Zhou 教授有紧密合作。

I serve as a regular reviewer for CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, T-PAMI and IJCV. 我长期担任 CVPR、ICCV、ECCV、NeurIPS、ICLR、ICML、T-PAMI 和 IJCV 的审稿人。

My research aims to develop human-centered AI that augment human capabilities in perception, reasoning, and interaction with the world. To achieve this, I am focusing on the following topics: 我的研究旨在发展以人为中心的 AI，增强人类在感知、推理与交互方面的能力。为此我重点关注以下方向：

• Generalizable Perception: interactive segmentation, 3D scene understanding, multi-modal learning • 可泛化感知：交互式分割、3D 场景理解、多模态学习

• Generative Models: LLMs and MLLMs reasoning, interactive world models, vision-language models • 生成模型：LLMs 与 MLLMs 推理、交互式世界模型、视觉-语言模型

• Embodied Agents: embodied reasoning,human-scene interaction, multi-agent cooperation • 具身智能体：具身推理、人-场景交互、多智能体协作

I'm a sports enthusiast with a passion for snowboarding and badminton. I also hold a 2nd-degree black belt in Taekwondo. Whether on the slopes, the court, or in training, I love pushing my limits and shaping my skills. 我热爱运动，尤其喜欢滑雪板和羽毛球，并拥有跆拳道二段黑带。 无论在雪道、球场还是训练中，我都享受挑战自我、打磨技能。

• Preprint'26

  Selective Latent Thinking: Adaptive Compression of LLM Reasoning Chains 选择性潜在思考：LLM 推理链的自适应压缩
  Hui Xie, Jie Liu, Ziyue Qiao, Joaquin Vanschoren Hui Xie, Jie Liu, Ziyue Qiao, Joaquin Vanschoren
  arXiv, 2026 arXiv，2026
  

  LLM Reasoning LLM 推理 Latent Reasoning 潜在推理 Selective Thinking 选择性思考

  [Paper论文] [Code代码]
• Preprint'26

  Open-Vocabulary Functional 3D Human-Scene Interaction Generation 开放词汇的功能性三维人-场景交互生成
  Jie Liu, Yu Sun, Alpár Cseke, Yao Feng, Nicolas Hron, Michael J. Black, Yan Zhang Jie Liu, Yu Sun, Alpár Cseke, Yao Feng, Nicolas Hron, Michael J. Black, Yan Zhang
  arXiv, 2026 — work done as an intern at Meshcapade arXiv，2026 — 在 Meshcapade 实习期间完成
  

  Embodied Agent 具身智能体 Human-Scene Interaction 人-场景交互 Optimization 优化方法

  [Project项目] [Paper论文] [Video视频] [Code代码]
• ICML'26

  Towards Uniformity and Alignment for Multimodal Representation Learning 面向多模态表征学习的统一性与对齐
  Wenzhe Yin, Pan Zhou, Zehao Xiao, Jie Liu, Shujian Yu, Jan-Jakob Sonke, Efstratios Gavves Wenzhe Yin, Pan Zhou, Zehao Xiao, Jie Liu, Shujian Yu, Jan-Jakob Sonke, Efstratios Gavves
  International Conference on Machine Learning (ICML), 2026 国际机器学习大会（ICML），2026
  

  Multimodal Learning 多模态学习 Representation Learning 表征学习 Contrastive Learning 对比学习

  [Paper论文]
• ESWC'26

  Are a Thousand Words Better Than a Single Picture? Beyond Images - A Framework for Multi-Modal Knowledge Graph Dataset Enrichment 千言胜过一图？超越图像：用于多模态知识图谱数据集增强的框架
  Pengyu Zhang, Klim Zaporojets, Jie Liu, Jia-Hong Huang, Paul Groth Pengyu Zhang, Klim Zaporojets, Jie Liu, Jia-Hong Huang, Paul Groth
  European Semantic Web Conference (ESWC), 2026 欧洲语义网会议（ESWC），2026
  

  Multimodal Learning 多模态学习 Knowledge Graph 知识图谱 Dataset Enrichment 数据集增强

  [Paper论文] [Code代码]
• ICCV'25

  Probabilistic Prototype Calibration of Vision-language Models for Generalized Few-shot Semantic Segmentation 面向广义小样本语义分割的视觉-语言模型概率原型校准
  Jie Liu, Jiayi Shen, Pan Zhou, Jan-Jakob Sonke, Efstratios Gavves Jie Liu, Jiayi Shen, Pan Zhou, Jan-Jakob Sonke, Efstratios Gavves
  International Conference on Computer Vision (ICCV), 2025 国际计算机视觉大会（ICCV），2025
  

  Segmentation 分割 Vision-Language Model 视觉语言模型 Probabilistic Model 概率模型

  [Paper论文] [Code代码]
• ICML'25

  NPISeg3D: Probabilistic Interactive 3D Segmentation with Hierarchical Neural Processes NPISeg3D：层级神经过程的概率交互式 3D 分割
  Jie Liu, Pan Zhou, Zehao Xiao, Jiayi Shen, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves Jie Liu, Pan Zhou, Zehao Xiao, Jiayi Shen, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves
  International Conference on Machine Learning (ICML), 2025 国际机器学习大会（ICML），2025
  

  Segmentation 分割 3D Perception 3D 感知 Probabilistic Model 概率模型

  [Project项目] [Paper论文] [Code代码]
• ICLR'25

  CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-agent Cooperation CaPo：高效具身多智能体协作的协同计划优化
  Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees GM Snoek, Jan-Jakob Sonke, Efstratios Gavves Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees GM Snoek, Jan-Jakob Sonke, Efstratios Gavves
  International Conference on Learning Representations (ICLR), 2025 国际学习表征会议（ICLR），2025
  

  Embodied Agent 具身智能体 LLM Planning LLM 规划 Plan Optimization 计划优化

  [Paper论文] [Code代码]
• ECCV'24

  CPlot: Click Prompt Learning with Optimal Transport for Interactive Segmentation CPlot：面向交互式分割的最优传输点击提示学习
  Jie Liu, Haochen Wang, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves Jie Liu, Haochen Wang, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves
  European Conference on Computer Vision (ECCV), 2024 欧洲计算机视觉会议（ECCV），2024
  

  Segmentation 分割 Interactive Perception 交互式感知 Optimal Transport 最优传输

  [Project项目] [Paper论文] [Code代码]
• 3DV'24

  Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation 动态原型蒸馏的少样本点云分割
  Jie Liu, Wenzhe Yin, Haochen Wang, Yunlu Chen, Jan-Jakob Sonke, Efstratios Gavves Jie Liu, Wenzhe Yin, Haochen Wang, Yunlu Chen, Jan-Jakob Sonke, Efstratios Gavves
  International Conference on 3D Vision (3DV), 2024 国际 3D 视觉会议（3DV），2024
  

  Segmentation 分割 3D Perception 3D 感知 Prototype Learning 原型学习

  [Paper论文] [Code代码]
• BMVC'22

  Few-shot Semantic Segmentation with Support-Induced Graph Convolutional Network 支持诱导图卷积的少样本语义分割
  Jie Liu, Yanqi Bao, Haochen Wang, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves Jie Liu, Yanqi Bao, Haochen Wang, Wenzhe Yin, Jan-Jakob Sonke, Efstratios Gavves
  British Machine Vision Conference (BMVC), 2022 英国机器视觉会议（BMVC），2022
  

  Segmentation 分割 Few-shot Learning 小样本学习 Graph Neural Network 图神经网络

  [Paper论文] [Code代码]
• CVPR'22

  Dynamic Prototype Convolution Network for Few-shot Semantic Segmentation 动态原型卷积网络用于少样本语义分割
  Jie Liu, Yanqi Bao, Guosen Xie, Huan Xiong, Jan-Jakob Sonke, E Gavves Jie Liu, Yanqi Bao, Guosen Xie, Huan Xiong, Jan-Jakob Sonke, E Gavves
  Conference on Computer Vision and Pattern Recognition (CVPR), 2022 计算机视觉与模式识别会议（CVPR），2022
  

  Segmentation 分割 Few-shot Learning 小样本学习 Prototype Learning 原型学习

  [Paper论文] [Code代码]
• UAI'24

  Domain Adaptation with Cauchy-Schwarz Divergence 基于柯西-施瓦茨散度的领域自适应
  Wenzhe Yin, Shujian Yu, Yicong Lin, Jie Liu, Jan-Jakob Sonke, Efstratios Gavves Wenzhe Yin, Shujian Yu, Yicong Lin, Jie Liu, Jan-Jakob Sonke, Efstratios Gavves
  Conference on Uncertainty in Artificial Intelligence (UAI), 2024 不确定性人工智能会议（UAI），2024
  

  Domain Adaptation 领域自适应 Representation Learning 表征学习 Divergence Learning 散度学习

  [Paper论文] [Code代码]
• TMM'23

  PiClick: Picking the Desired Mask in Click-based Interactive Segmentation PiClick：点击交互分割中的目标掩码选择
  Cilin Yan, Haochen Wang, Jie Liu, Xiaolong Jiang, Yao Hu, Xu Tang, Guoliang Kang, Efstratios Gavves Cilin Yan, Haochen Wang, Jie Liu, Xiaolong Jiang, Yao Hu, Xu Tang, Guoliang Kang, Efstratios Gavves
  IEEE Transactions on Multimedia (TMM), 2023 IEEE 多媒体汇刊（TMM），2023
  

  Segmentation 分割 Interactive Perception 交互式感知 Mask Selection 掩码选择

  [Paper论文] [Code代码]
• ACM MM'22

  Dynamic Transformer for Few-shot Instance Segmentation 动态 Transformer 用于少样本实例分割
  Haochen Wang, Jie Liu, Yongtuo Liu, Subhransu Maji, Jan-Jakob Sonke, Efstratios Gavves Haochen Wang, Jie Liu, Yongtuo Liu, Subhransu Maji, Jan-Jakob Sonke, Efstratios Gavves
  Proceedings of the 30th ACM International Conference on Multimedia (ACM MM), 2022 第 30 届 ACM 国际多媒体会议（ACM MM），2022
  

  Segmentation 分割 Few-shot Learning 小样本学习 Dynamic Transformer 动态 Transformer

  [Paper论文] [Code代码]
• CVPR'21

  Scale-aware Graph Neural Network for Few-shot Semantic Segmentation 尺度感知图神经网络用于少样本语义分割
  Guo-senXie*, Jie Liu*, HuanXiong, LingShao Guo-senXie*, Jie Liu*, HuanXiong, LingShao
  Conference on Computer Vision and Pattern Recognition (CVPR), 2021 计算机视觉与模式识别会议（CVPR），2021
  

  Segmentation 分割 Few-shot Learning 小样本学习 Graph Neural Network 图神经网络

  [Paper论文] [Code代码]