王一凯
基本信息
职称：副教授（博士生导师、硕士生导师）
研究方向：多模态感知、视频生成与3D生成、多模态大模型、具身智能
电子邮箱：yikaiw@bnu.edu.cn
个人简介
王一凯，人工智能学院副教授，博士生导师。2017年6月获得西安交通大学电气工程及其自动化专业学士学位；2022年6月获得清华大学计算机科学与技术专业博士学位，师从孙富春教授。研究方向包括深度多模态融合感知、多模态生成、具身智能等科研领域，学术论文发表于TPAMI、NeurIPS、ICLR、CVPR等国际顶级期刊和会议50余篇，以第一作者/通讯作者在国际顶级期刊TPAMI上发表3篇。申请国家（国际）发明专利公开20项，授权8项。系列工作GitHub开源代码累计获得8000余星。主持国自然面上基金、青年基金、博士后基金、华为学术基金项目，入选中国人工智能学会博士学位论文激励计划、北京市青年人才托举工程和中国自动化学会青年人才托举工程。
教育背景
2017年—2022年 清华大学计算机科学与技术系 博士
2013年—2017年 西安交通大学大学电气工程学院 学士
工作经历
2024年至今 北京师范大学人工智能学院 副教授
2022年—2024年 清华大学计算机科学与技术系 博士后
主持和参加的科研项目
国家自然科学基金面上项目《空间智能场景可控三维生成与三维交互方法研究》（主持） 2026.01—2029.12
国家自然科学基金青年科学基金项目《复杂场景下的时序多模态融合方法研究》（主持） 2024.01—2025.12
中国博士后科学基金面上项目《基于时序多模态融合感知的三维信息重构方法研究》（主持）2024.01—2025.12
中国人工智能学会-华为MindSpore学术奖励基金项目《机器人操作场景的多模态感知融合》（主持） 2022.01—2023.12
主要学术成果
* 表示共同第一作者，#表示通讯作者
2026年
Yuyang Yin, Hao-Xiang Guo, Fangfu Liu, Mengyu Wang, Hanwen Liang, Eric Li, Yikai Wang#, Xiaojie Jin, Yao Zhao, Yunchao Wei#. PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion. International Conference on Machine Learning (ICML, Spotlight), CCF-A, 2026
Chushan Zhang, Ruihan Lu, Jinguang Tong, Yikai Wang#, Hongdong Li#. 3D-IDE: 3D Implicit Depth Emergent. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2026
Di Kong, Yikai Wang, Wenjie Guo, Yifan Bu, Boya Zhang, Yuexin Duan, Xiawei Yue, Wenbiao Du, Yiman Zhong, Yuwen Chen, Cheng Ma. GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2026
Keyang Lu, Sifan Zhou, Hongbin Xu, Gang Xu, Zhifei Yang, Yikai Wang, Zhen Xiao, Jieyi Long, Ming Li. Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-critic Expansion. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2026
Hong Li, Chongjie Ye, Houyuan Chen, Weiqing Xiao, et al, Yikai Wang, Baochang Zhang, Xiaoguang Han, Jiaolong Yang, Hao Zhao. NeAR: Coupled Neural Asset–renderer Stack. IEEE Conference on Computer Vision and Pattern Recognition (CVPR, Highlight), CCF-A, 2026
Yiwen Chen, Zhihao Li, Yihao Luo, Yikai Wang, Hu Zhang, Lei Li, Qin Li, Chi Zhang, Guosheng Lin. Ultra3D: Efficient and High-fidelity 3D Generation with Part Attention. European Conference on Computer Vision (ECCV), THU-A, 2026
Fangfu Liu, Wenqiang Sun, Hanyang Wang, Yikai Wang#, Haowen Sun, Junliang Ye, Jun Zhang, Yueqi Duan#. ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model. IEEE Transactions on Image Processing (TIP), IF=15.3, CCF-A, 2026
Ling Wang, Hao-Xiang Guo, Xinzhou Wang, Fuchun Sun#, et al, Guangyuan Fu, Eric Li, Yang Liu, Yikai Wang#. SceneTransporter: Optimal Transport-guided Compositional Latent Diffusion for Single-image Structured 3D Scene Generation. International Conference on Learning Representations (ICLR), CCF-A, 2026
Yuming Li*, Yikai Wang*, Yuying zhu, Zhongyu Zhao, Ming Lu, Qi She, Shanghang Zhang. BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models. International Conference on Learning Representations (ICLR), CCF-A, 2026
Houyuan Chen, Hong Li, Chongjie Ye, et al, Yikai Wang, Baochang Zhang, Satoshi Ikehata, Boxin Shi, Anyi Rao, Hao Zhao. Light of Normals: Unified Feature Representation for Universal Photometric Stereo. International Conference on Learning Representations (ICLR), CCF-A, 2026
2025年
Yikai Wang, Guangce Liu, Xinzhou Wang, Zilong Chen, Jiafang Li, Xin Liang, Fuchun Sun, Jun Zhu. Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), CCF-A, IF=20.4, 2025
Zilong Chen, Yikai Wang#, Feng Wang, Zhengyi Wang, Fuchun Sun, Huaping Liu#. V3D: Video Diffusion Models are Effective 3D Generators. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), CCF-A, IF=20.4, 2025
Fangfu Liu, Junliang Ye, Yikai Wang, Hanyang Wang, Zhengyi Wang, Jun Zhu, Yueqi Duan. DreamReward-X: Boosting High-Quality 3D Generation with Human Preference Alignment. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), CCF-A, IF=20.4, 2025
Wenqiang Sun, Shuo Chen, Fangfu Liu, Zilong Chen, Yueqi Duan, Jun Zhu#, Jun Zhang#, Yikai Wang#. DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion. International Conference on Computer Vision (ICCV), CCF-A, 2025
Luxi Chen, Zihan Zhou, Min Zhao, Yikai Wang#, Ge Zhang, Wenhao Huang, Hao Sun, Ji-Rong Wen, Chongxuan Li#. FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis. Advances in Neural Information Processing Systems (NeurIPS), CCF-A, 2025
Yiwen Chen, Yikai Wang#, Yihao Luo, Zhengyi Wang, Zilong Chen, Jun Zhu, Chi Zhang#, Guosheng Lin#. MeshAnything V2: Artist-Created Mesh Generation with Adjacent Mesh Tokenization. International Conference on Computer Vision (ICCV), CCF-A, 2025
Zilong Chen, Yikai Wang#, Wenqiang Sun, Feng Wang, Yiwen Chen, Huaping Liu#. MeshGen: Generating PBR Textured Mesh with Render-Enhanced Auto-Encoder and Generative Data Augmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2025
Haohan Weng, Yikai Wang#, Tong Zhang, C. L. Philip Chen, Jun Zhu. PivotMesh: Generic 3D Mesh Generation via Pivot Vertices Guidance. International Conference on Learning Representations (ICLR), THU-A, 2025
Ling Wang, Runfa Chen, Fuchun Sun#, Xinzhou Wang, Sun Kai, Chengliang Zhong, Guangyuan Fu, Yikai Wang#. Equivariant Local Reference Frames for Unsupervised Non-rigid Point Cloud Shape Correspondence. IEEE Transactions on Image Processing (TIP), CCF-A, IF=15.3, 2025
Junting Chen, Checheng Yu, Xunzhe Zhou, Tianqi Xu, Yao Mu, Mengkang Hu, Wenqi Shao, Yikai Wang#, Guohao Li, Lin Shao#. EMOS: Embodiment-aware Heterogeneous Multi-robot Operating System with LLM Agents. International Conference on Learning Representations (ICLR), THU-A, 2025
Ruowen Zhao, Junliang Ye, Zhengyi Wang, Guangce Liu, Yiwen Chen, Yikai Wang, Jun Zhu. DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning. International Conference on Computer Vision (ICCV), CCF-A, 2025
Xuying Zhang, Yupeng Zhou, Kai Wang, Yikai Wang, Zhen Li, Shaohui Jiao, Daquan Zhou, Qibin Hou, Ming-Ming Cheng. AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-view Prediction. International Conference on Computer Vision (ICCV), CCF-A, 2025
Guojun Lei, Chi Wang, Rong Zhang, Yikai Wang, Hong Li, Weiwei Xu. AnimateAnything: Consistent and Controllable Animation for Video Generation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2025
Fusheng Hao, Fengxiang He, Yikai Wang, Fuxiang Wu, Jing Zhang, Jun Cheng, Dacheng Tao. Human-Imperceptible, Machine-Recognizable Images. International Joint Conference on Artificial Intelligence (IJCAI), CCF-A, 2025
2024年
Yikai Wang*, Xinzhou Wang*, Zilong Chen, Zhengyi Wang, Fuchun Sun, Jun Zhu. Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels. Advances in Neural Information Processing Systems (NeurIPS), CCF-A, 2024
He Liu*, Yikai Wang*, Huaping Liu, Fuchun Sun, Anbang Yao. Small Scale Data-Free Knowledge Distillation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2024
Xinzhou Wang, Yikai Wang#, Junliang Ye, Zhengyi Wang, Fuchun Sun#, Pengkun Liu, Ling Wang, et al. AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation. European Conference on Computer Vision (ECCV), THU-A, 2024
Zilong Chen, Feng Wang, Yikai Wang, Huaping Liu. Text-to-3D using Gaussian Splatting. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2024
Xiao Yang, Longlong Xu, Tianyu Pang, Yinpeng Dong,Yikai Wang, Hang Su, Jun Zhu.Face3DAdv: Exploiting Robust Adversarial 3D Patches on Physical Face Recognition. International Journal of Computer Vision (IJCV), CCF-A, 2024
Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, et al. GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2024
Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, Jun Zhu. CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Models. European Conference on Computer Vision (ECCV), THU-A, 2024
Junliang Ye, Fangfu Liu, Qixiu Li, Zhengyi Wang, Yikai Wang, Xinzhou Wang, Yueqi Duan, Jun Zhu. DreamReward: Aligning Human Preference in Text-to-3D Generation. European Conference on Computer Vision (ECCV), THU-A, 2024
Jianhui Li, Shilong Liu, Zidong Liu, Yikai Wang, Kaiwen Zheng, Jinghui Xu, Jianmin Li, Jun Zhu. InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image. International Conference on Learning Representations (ICLR), THU-A, 2024
Peike Li, Boyu Chen, Yao Yao, Yikai Wang, Allen Wang, Alex Wang Jen-1: Text-guided Universal Music Generation with Omnidirectional Diffusion Models. IEEE Conference on Artificial Intelligence (CAI), 2024
2023年
Yikai Wang, Fuchun Sun, Wenbing Huang, Fengxiang He, Dacheng Tao. Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), CCF-A, IF=20.4, 2023
Yikai Wang, Wenbing Huang, Fuchun Sun, Anbang Yao. Compacting Binary Neural Networks by Sparse Kernel Selection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2023
Yikai Wang, Yinpeng Dong, Fuchun Sun, Xiao Yang. Root Pose Decomposition Towards Generic Non-rigid 3D Reconstruction with Monocular Videos. International Conference on Computer Vision (ICCV), CCF-A, 2023
Zhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao, Chongxuan Li, Hang Su, Jun Zhu. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation. Advances in Neural Information Processing Systems (NeurIPS, Spotlight), Most Influential NeurIPS Papers, CCF-A, 2023
Xiao Yang, Chang Liu, Longlong Xu, Yikai Wang, Yinpeng Dong, et al. Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR, Highlight), CCF-A, 2023
Yinpeng Dong, Caixin Kang, Jinlai Zhang, Zijian Zhu, Yikai Wang, Xiao Yang, et al. Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2023
2022年
Yikai Wang, Xinghao Chen, Lele Cao, Wenbing Huang, Fuchun Sun, Yunhe Wang. Multimodal Token Fusion for Vision Transformers. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2022
Yikai Wang, Tengqi Ye, Lele Cao, Wenbing Huang, Fuchun Sun, Fengxiang He, Dacheng Tao. Bridged Transformer for Vision and Point Cloud 3D Object Detection. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), CCF-A, 2022
Yinfeng Yu, Wenbing Huang, Fuchun Sun, Changan Chen, Yikai Wang, Xiaolong Liu. Sound Adversarial Audio-Visual Navigation. International Conference on Learning Representations (ICLR), THU-A, 2022
He Liu, Huaping Liu, Yikai Wang, Fuchun Sun, Wenbing Huang. Fine-grained Multi-level Fusion for Anti-occlusion Monocular 3D Object Detection. IEEE Transactions on Image Processing (TIP), CCF-A, IF=15.3, 2022
2021年及以前
Yikai Wang, Yi Yang, Fuchun Sun, Anbang Yao. Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks. International Conference on Computer Vision (ICCV), CCF-A, 2021
Yikai Wang, Wenbing Huang, Bin Fang, Fuchun Sun, Chang Li. Elastic Tactile Simulation Towards Tactile-Visual Perception. ACM International Conference on Multimedia (MM, Oral), CCF-A, 2021
Yikai Wang, Wenbing Huang, Fuchun Sun, Tingyang Xu, Yu Rong, Junzhou Huang. Deep Multimodal Fusion by Channel Exchanging. Advances in Neural Information Processing Systems (NeurIPS), CCF-A, 2020
Yikai Wang, Fuchun Sun, Ming Lu, Anbang Yao. Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion. ACM International Conference on Multimedia (MM), CCF-A, 2020
Yikai Wang, Fuchun Sun, Duo Li, Anbang Yao. Resolution Switchable Networks for Runtime Efficient Image Recognition. European Conference on Computer Vision (ECCV), THU-A, 2020
Yikai Wang*, Liang Zhang*, Quanyu Dai, Fuchun Sun, et al. Regularized Adversarial Sampling and Deep Time-aware Attention for CTR Prediction. ACM International Conference on Information and Knowledge Management (CIKM), 2019
学术活动
会议审稿人：NeurIPS、ICML、CVPR、ICCV、ECCV、ICRA
期刊审稿人：IEEE TPAMI、IEEE TRO、IEEE TIP、IJCV
奖励与荣誉
2026年 入选中国自动化学会青年人才托举工程
2025年 入选北京市科协2025年度“高创计划”青年人才托举工程
2024年 入选中国人工智能学会博士学位论文激励计划
2022年 清华大学“水木学者”
2021年 博士生国家奖学金
2021年 华为“创新先锋奖”
2021年 IROS 国际机器人抓取比赛，获仿真组冠军、操作组季军
指导学生项目
2022年至2025年指导/共同指导20余名硕、博士研究生高质量完成科研实验，成功发表高水平期刊或会议（TPAMI、CVPR、ECCV、NeurIPS、ICLR等），部分成果获得国内外较多关注。
招生说明
每年招收硕士研究生和博士研究生。本团队能够提供充足的实验、计算资源，支持学生做出优秀的科研成果。欢迎同学们（包含高年级优秀本科生、在读硕士生、博士生）加入团队，一起实现科研理想。要求：1）对科研工作富有热情；2）求真务实，精益求精；3）有较强的编程基础。
