物理AI与具身智能团队

发布时间:2026-09-22浏览次数:223

团队介绍

        物理AI与具身智能团队面向人工智能理解物理世界、参与环境交互的发展需求,结合王长波教授、宋思程副教授在计算机图形学、物理仿真、可视化理解与人机交互等方面的研究基础,探索物理机理与数据驱动相结合的智能建模方法,推动虚拟环境中的感知、理解与交互研究向具身智能应用拓展。

        团队以可控生成与理解、物理建模与数据驱动仿真、虚实交互与具身智能应用为研究主线,探索三维空间中的语义关系与内容生成、视觉信息的理解及可靠性评估、复杂材料和动态环境的建模方法,以及增强现实和具身智能环境中的交互与分析。面向物理AI与具身智能,团队进一步探索环境建模、感知理解、交互仿真与可视评估之间的协同,为智能系统参与物理世界交互积累方法与工具。

物理AI与具身智能团队概览

团队发表论文

物理建模与数据驱动仿真方向

Z. Tu, C. Li, Z. Zhao, L. Liu, C. Wang, C. Wang, H. Qin, "A Unified MPM Framework Supporting Phase-field Models and Elastic-viscoplastic Phase Transition", ACM TOG, 43(2), Article 19, 2024. (CCF A)

J. Shu, H. Liu, D. Miao, W. Song, M. Yuan, W. Liu, C. Chen, Y. Li, C. Wang, "VfxDB: A Visual Effects Volume Dataset and Benchmark for VDB-Native Generative Modeling", SIGGRAPH, Article 195, 11 pages, 2026. (CCF A)

W. Liu, Z. Liu, J. Shu, C. Wang, Y. Li, "GT2-GS: Geometry-aware Texture Transfer for Gaussian Splatting", AAAI, 2026. (CCF A)

Z. Guo, Z. Wang, J. Shu, Y. Li, C. Wang, L. Chen, "h-Flow: Flexible Flow-Based Image Editing via Doob's h-Transform", ECCV, 542-558, 2026. (CCF B)

Y. Xie, C. Li, S. Qiu, Z.-J. Wang, C. Li, Y. Zhao, Z. Gao, C. Wang, "FluidGS: Physics Informed Gaussian Splatting for Dynamic Fluid Reconstruction from Sparse Views", ACM MM, 2025. (CCF A)

C. Chen, J. Shu, G. He, C. Wang, Y. Li, "Motion-Zero: A Zero-Shot Trajectory Control Framework of Moving Object for Diffusion-Based Video Generation", AAAI, 2025. (CCF A)

T. Liang, J. Liu, Y. Huang, S. Jiang, J. Shi, C. Wang, C. Li, "TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation", ICML, 2025. (CCF A)

J. Hu, Y. He, T. Liang, C. Wang, C. Li, "Music2Palette: Emotion-aligned Color Palette Generation via Cross-Modal Representation Learning", ACM MM, 6615-6624, 2025. (CCF A)

Y. Quan, C. Li, Y. Li, C. Wang, H. Qin, "Detail-preserving shape completion of point cloud models with articulated structure", CAGD, 120, 102456, 2025. (CCF B)

X. Li, J. Lin, B. Zhang, Y. Qi, C. Wang, G. He, "EmoDiffGes: Emotion-Aware Co-Speech Holistic Gesture Generation with Progressive Synergistic Diffusion", CGF, 44(7), 2025. (CCF B)

S. Liu, M. Tao, Y. Huang, C. Wang, C. Li, "Image-Driven Harmonious Color Palette Generation for Diverse Information Visualization", IEEE TVCG, 30(7), 3089-3103, 2024. (CCF A)

C. Chen, L. Yang, X. Yang, L. Chen, G. He, C. Wang, Y. Li, "FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models", ACM MM, 6735-6744, 2024. (CCF A)

P. Zhou, D. Lu, C. Li, J. Zhang, L. Liu, C. Wang, "Unsupervised Textured Terrain Generation via Differentiable Rendering", ACM MM, 2654–2662, 2022. (CCF A)

C. Li, P. Zhang, C. Wang, "Harmonious Textual Layout Generation Over Natural Images via Deep Aesthetics Learning", IEEE TMM, 24, 3416-3428, 2022. (CCF A)

C. Li, S. Qiu, C. Wang, H. Qin, "Learning Physical Parameters and Detail Enhancement for Gaseous Scene Design Based on Data Guidance", IEEE TVCG, 27(10): 3867–3880, 2021. (CCF A)

S. Qiu, C. Li, C. Wang, H. Qin, "A Rapid, End-to-end, Generative Model for Gaseous Phenomena from Limited Views", CGF, 40(6): 242–257, 2021. (CCF B)

Y. Huang, S. Qiu, C. Wang, C. Li, "Learning Representations for High-Dynamic-Range Image Color Transfer in a Self-Supervised Way", IEEE TMM, 23, 176-188, 2021. (CCF A)

Y. Huang, C. Li, X. Guo, J. Liao, C. Zhang, C. Wang, "DeSmoothGAN: Recovering Details of Smoothed Images via Spatial Feature-wise Transformation and Full Attention", ACM MM, 2655-2663, 2020. (CCF A)

Z. Zhao, K. Huang, C. Li, C. Wang, H. Qin, "A Novel Plastic Phase-Field Method for Ductile Fracture with GPU Optimization", CGF, 39(7): 105–117, 2020. (CCF B)

M. Chen, Q. Zou, C. Wang, L. Liu, "EdgeNet: Deep metric learning for 3D shapes", CAGD, 72, 19-33, 2019. (CCF B)

M. Chen, C. Wang, H. Qin, "Jointly learning shape descriptors and their correspondence via deep triplet CNNs", CAGD, 62, 192-205, 2018. (CCF B)

可控生成与智能理解方向

S. Jiang, T. Liang, H. Ye, C. Wang, C. Li, "MPJudge: Towards Perceptual Assessment of Music-Induced Paintings", AAAI, 5424-5431, 2026. (CCF A)

Z. Chen, Y. Zeng, S. Song, Y. Lin, X. Xu, H. Qu, M. Xia, "VizQStudio: Iterative Visualization Literacy MCQs Design with Simulated Students", IEEE TVCG, 2026. (CCF A)

B. Zhang, X. Wang, C. Wang, G. He, "Dynamic Stereotype Theory Induced Micro-expression Recognition with Oriented Deformation", CVPR, 10701-10711, 2025. (CCF A)

H. Ye, S. Zhang, S. Jiang, J. Liao, S. Gu, D. Zheng, C. Wang, C. Li, "Robust Message Embedding via Attention Flow-Based Steganography", CVPR, 12840-12849, 2025. (CCF A)

L. You, W. Huang, X. Xie, X. Wei, B. Li, S. Lin, Y. Li, C. Wang, "TimeSoccer: An End-to-End Multimodal Large Language Model for Soccer Commentary Generation", ACM MM, 3418-3427, 2025. (CCF A)

B. Zhang, H. Xu, J. Lin, C. Wang, G. He, "Regulatory Focus Theory Induced Micro-Expression Analysis with Structured Representation Learning", ACM MM, 5863-5872, 2025. (CCF A)

S. Jiang, X. Li, X. Mao, C. Wang, C. Li, "PPJudge: Towards Human-Aligned Assessment of Artistic Painting Process", ACM MM, 6625-6633, 2025. (CCF A)

J. Li, Z. Chen, R. Jiang, T. Chen, C. Wang, G. Zhai, "Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark", ACM MM, 7729-7738, 2025. (CCF A)

L. Chen, Y. Song, Y. Cai, J. Lu, Y. Li, Y. Xie, C. Wang, G. He, "Multi-Prototype Space Learning for Commonsense-Based Scene Graph Generation", AAAI, 38(2): 1129–1137, 2024. (CCF A)

L. Chen, Y. Song, S. Lin, C. Wang, G. He, "Kumaraswamy Wavelet for Heterophilic Scene Graph Generation", AAAI, 1138-1146, 2024. (CCF A)

S. Jiang, N. Li, C. Shi, L. Guo, C. Wang, C. Li, "AACP: Aesthetics Assessment of Children's Paintings Based on Self-Supervised Learning", AAAI, 2534-2542, 2024. (CCF A)

L. Chen, X. Wang, J. Lu, S. Lin, C. Wang, G. He, "CLIP-Driven Open-Vocabulary 3D Scene Graph Generation via Cross-Modality Contrastive Learning", CVPR, 27863-27873, 2024. (CCF A)

Y. Cai, L. Chen, H. Guan, S. Lin, C. Lu, C. Wang, G. He, "Explicit Invariant Feature Induced Cross-Domain Crowd Counting", AAAI, 259-267, 2023. (CCF A)

L. Chen, J. Lu, Y. Song, C. Wang, G. He, "Beware of Overcorrection: Scene-induced Commonsense Graph for Scene Graph Generation", ACM MM, 2888-2897, 2023. (CCF A)

J. Lu, L. Chen, Y. Song, S. Lin, C. Wang, G. He, "Prior Knowledge-driven Dynamic Scene Graph Generation with Causal Inference", ACM MM, 4877-4885, 2023. (CCF A)

Y. Cai, Z. Ma, C. Lu, C. Wang, G. He, "Global Representation Guided Adaptive Fusion Network for Stable Video Crowd Counting", IEEE TMM, 25, 5222-5233, 2023. (CCF A)

L. Chen, J. Lu, Y. Cai, C. Wang, G. He, "Exploring Contextual Relationships in 3D Cloud Points by Semantic Knowledge Mining", CGF, 41(7): 75–86, 2022. (CCF B)

C. Chen, C. Li, J. Chen, C. Wang, "VFDP: Visual Analysis of Flight Delay and Propagation on a Geographical Map", IEEE TITS, 23(4), 3510-3521, 2022. (CCF B)

可视分析与虚实交互方向

S. Song, Y. Zhang, Z. Chen, H. Qu, C. Wang, C. Li, "VizDefender: Unmasking Visualization Tampering Through Proactive Localization and Intent Inference", IEEE TVCG, 32(6): 4720–4730, 2026. (CCF A)

J. Bu, M. Jiang, S. Liu, T. Lyu, L. Wu, S. Jiang, B. Huangfu, C. Wang, C. Li, "NewsVis: GenAI-Based Visual Storytelling for Corporate Financial News", IEEE TVCG, 32(7): 5501–5517, 2026. (CCF A)

H. Ye, J. Chen, S. Zhang, Y. Zhang, C. Wang, C. Li, "VisGuard: Securing Visualization Dissemination through Tamper-Resistant Data Retrieval", IEEE TVCG, 32(1): 1295–1305, 2026. (CCF A)

C. Shi, Y. Shen, J. Chen, F. Liu, C. Li, C. Wang, "Enhancing trust through a human-center evaluation framework from an accessibility perspective: The case of graph anomaly detection", IJHCS, 211, 103781, 2026. (CCF A)

J. Chen, H. Ye, H. Zhu, S. Fu, C. Wang, C. Li, "RelMap: Reliable Spatiotemporal Sensor Data Visualization via Imputative Spatial Interpolation", IEEE TVCG, 32(1), 101-111, 2026. (CCF A)

S. Song, Y. Zhang, Y. Lin, H. Qu, C. Wang, C. Li, "GVVST: Image-Driven Style Extraction from Graph Visualizations for Visual Style Transfer", IEEE TVCG, 31(9), 2025. (CCF A)

L. Liu, J. Ren, Z. Fan, C. Li, G. He, C. Wang, Y. Gao, C. Li, "SandTouch: Empowering Virtual Sand Art in VR with AI Guidance and Emotional Relief", CHI, Article 663, 2025. (CCF A)

S. Song, C. Li, Y. Sun, C. Wang, "GraphDecoder: Recovering Diverse Network Graphs from Visualization Images via Attention-Aware Learning", IEEE TVCG, 30(7), 2024. (CCF A)

J. Chen, H. Huang, H. Ye, Z. Peng, C. Li, C. Wang, "SalienTime: User-driven Selection of Salient Time Steps for Large-Scale Geospatial Data Visualization", CHI, 2024. (CCF A)

S. Liu, J. Bu, H. Ye, J. Chen, S. Jiang, M. Tao, L. Guo, C. Wang, C. Li, "DoodleTunes: Interactive Visual Analysis of Music-Inspired Children Doodles with Automated Feature Annotation", CHI, 2024. (CCF A)

H. Ye, C. Li, Y. Li, C. Wang, "InvVis: Large-Scale Data Embedding for Invertible Visualization", IEEE TVCG, 30(1), 1139-1149, 2024. (CCF A)

J. Chen, Q. Huang, C. Wang, C. Li, "SenseMap: Urban Performance Visualization and Analytics Via Semantic Textual Similarity", IEEE TVCG, 30(9), 6275-6290, 2024. (CCF A)

S. Song, J. Chen, C. Li, C. Wang, "GVQA: Learning to Answer Questions about Graphs with Visualizations via Knowledge Base", CHI, 2023. (CCF A)

S. Song, C. Li, D. Li, J. Chen, C. Wang, "VividGraph: Learning to Extract and Redesign Network Graphs from Visualization Images", IEEE TVCG, 29(7), 2023. (CCF A)

J. Chen, C. Li, S. Song, C. Wang, "iARVis: Mobile AR Based Declarative Information Visualization Authoring, Exploring and Sharing", IEEE VR, 11–21, 2023. (CCF A)

H. Tian, C. Song, C. Wang, X. Zhang, J. Pan, "Sampling-Based Planning for Retrieving Near-Cylindrical Objects in Cluttered Scenes Using Hierarchical Graphs", IEEE T-RO, 39(1), 165-182, 2023. (CCF B)

C. Li, G. Baciu, Y. Wang, J. Chen, C. Wang, "DDLVis: Real-time Visual Query of Spatiotemporal Data Distribution via Density Dictionary Learning", IEEE TVCG, 28(1), 1062-1072, 2022. (CCF A)

P. Zhang, C. Li, C. Wang, "VisCode: Embedding Information in Visualization Images using Encoder-Decoder Network", IEEE TVCG, 27(2), 326-336, 2021. (CCF A)

C. Chen, C. Wang, X. Bai, P. Zhang, C. Li, "GenerativeMap: Visualization and Exploration of Dynamic Density Maps via Generative Learning Model", IEEE TVCG, 26(1), 216-226, 2020. (CCF A)

H. Tian, C. Wang, D. Manocha, X. Zhang, "Realtime Hand-Object Interaction Using Learned Grasp Space for Virtual Environments", IEEE TVCG, 25(8), 2623-2635, 2019. (CCF A)

M. Chen, C. Wang, L. Liu, "Deep Video-Based Performance Synthesis from Sparse Multi-View Capture", CGF, 38(7), 543-554, 2019. (CCF B)

H. Tian, C. Wang, D. Manocha, X. Zhang, "Transferring Grasp Configurations using Active Learning and Local Replanning", ICRA, 1622-1628, 2019. (CCF B)

团队项目

物理建模与数据驱动仿真

  • 国家自然科学基金面上项目 (62472178),多模态数据与物理模型混合驱动的大尺度流体灾害场景仿真,2025.1-2028.12,在研,主持

  • 国家自然科学基金面上项目 (61672237),数据与物理混合驱动的高速流体快速仿真与细节增强,2017.1-2020.12,已结题,主持

  • 国家自然科学基金面上项目 (61272199),大尺度流体流固耦合与形变破坏的快速仿真研究,2013.1-2016.12,已结题,主持

  • 教育部博士点基金项目 (20130076110008),局部细节保持的大尺度流体快速仿真研究,2014.1-2016.12,已结题,主持

  • 国家自然科学基金面上项目 (61070128),多相流灾害现象的多尺度建模与交互可视化研究,2011.1-2013.12,已结题,主持

可控生成与智能理解

  • 国家自然科学基金青年C类(62602202),多维约束下语义拓扑图可视化的理解与生成方法研究,2027.1-2029.12,在研,主持

  • 国家社科基金艺术学重大项目课题,面向中国网络审美的智能可视化与评估分析,2022.7-2025.12,在研,主持

  • 上海市科委人工智能专项重点项目 (22511104600),融合多模态知识的视觉认知理解理论与方法,2022.9-2024.8,已结题,主持

  • 国家自然科学基金重点项目子课题,基于多源数据的可视模型与环境构建及其动态仿真,2016.1-2020.12,已结题,主持

  • 上海市教委科研创新项目重点项目 (12ZZ042),模型驱动的多尺度表达与交互可视化研究,2012.1-2014.12,已结题,主持

虚实交互与具身智能应用

  • 上海市科委元宇宙专项重点项目 (25511107200),面向智慧教育的轻量化元宇宙关键技术研究、平台建设及其示范应用,2025.12-2027.11,在研,主持

  • 国家自然科学基金面上项目 (62072183),多源数据混合驱动的城市街景多尺度特征学习与轻量化仿真,2021.1-2024.12,已结题,主持

  • 企业合作项目,风暴潮灾害评估辅助决策系统的三维可视化展示(上海彩虹鱼海洋科技股份有限公司),2020.1-2021.12,已结题,主持

  • 国家自然科学基金青年基金项目 (60603076),海洋造型与视景仿真关键技术研究,2007.1-2009.12,已结题,主持

  • 上海市科委青年科技启明星项目 (08QA14025),数字海洋虚拟环境与三维展示系统研究,2008.7-2010.6,已结题,主持