GigaBrain Challenge 2026: Workshop on World Models Empowering Vision Language Action Model


Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation
Mutian Xu,
Tianbao Zhang,
Tianqi Liu,
Zhaoxi Chen,
Xiaoguang Han,
Ziwei Liu
[pdf] [arXiv]
[bibtex]
@InProceedings{Xu_2026_CVPR, author = {Xu, Mutian and Zhang, Tianbao and Liu, Tianqi and Chen, Zhaoxi and Han, Xiaoguang and Liu, Ziwei}, title = {Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied Simulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4495-4500} }

FineGrasp: Towards Robust Grasping for Delicate Objects
Yun Du,
Mengao Zhao,
Tianwei Lin,
Yiwei Jin,
Chaodong Huang,
Zhizhong Su
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Du_2026_CVPR, author = {Du, Yun and Zhao, Mengao and Lin, Tianwei and Jin, Yiwei and Huang, Chaodong and Su, Zhizhong}, title = {FineGrasp: Towards Robust Grasping for Delicate Objects}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4428-4435} }

RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
Feng Jiang,
Yang Chen,
Kyle Xu,
Yuchen Liu,
Haifeng Wang,
Zhenhao Shen,
Jasper Lu,
Shengze Huang,
Yuanfei Wang,
Chen Xie,
Ruihai Wu
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Jiang_2026_CVPR, author = {Jiang, Feng and Chen, Yang and Xu, Kyle and Liu, Yuchen and Wang, Haifeng and Shen, Zhenhao and Lu, Jasper and Huang, Shengze and Wang, Yuanfei and Xie, Chen and Wu, Ruihai}, title = {RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4455-4460} }

ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
Chuyao Fu,
Shengzhe Gan,
Zhuoli Ouyang,
Yuhan Rui,
Xiaowei Chi,
Sirui Han,
Jiankun Wang,
Hong Zhang
[pdf] [arXiv]
[bibtex]
@InProceedings{Fu_2026_CVPR, author = {Fu, Chuyao and Gan, Shengzhe and Ouyang, Zhuoli and Rui, Yuhan and Chi, Xiaowei and Han, Sirui and Wang, Jiankun and Zhang, Hong}, title = {ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4436-4445} }

Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate
Chen Yang,
Yucheng Hu,
Yunchao Ma,
Yunhuan Yang,
Jing Tan,
Haoqiang Fan
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Yang_2026_CVPR, author = {Yang, Chen and Hu, Yucheng and Ma, Yunchao and Yang, Yunhuan and Tan, Jing and Fan, Haoqiang}, title = {Realtime-VLA V2: Learning to Run VLAs Fast, Smooth, and Accurate}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4501-4509} }

ARM: Advantage Reward Modeling for Long-Horizon Manipulation
Yiming Mao,
Zixi Yu,
Weixin Mao,
Yinhao Li,
Qirui Hu,
Zihan Lan,
Minzhao Zhu,
Hua Chen
[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Mao_2026_CVPR, author = {Mao, Yiming and Yu, Zixi and Mao, Weixin and Li, Yinhao and Hu, Qirui and Lan, Zihan and Zhu, Minzhao and Chen, Hua}, title = {ARM: Advantage Reward Modeling for Long-Horizon Manipulation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4468-4477} }

Table30 V2: Evaluating Generalized Models by Real Robots at Scale
Yunchao Ma,
Ze Chen,
Erjin Zhou,
Ziming Liu,
Haowei Zhang,
Kai Liu,
Haoqiang Fan
[pdf]
[bibtex]
@InProceedings{Ma_2026_CVPR, author = {Ma, Yunchao and Chen, Ze and Zhou, Erjin and Liu, Ziming and Zhang, Haowei and Liu, Kai and Fan, Haoqiang}, title = {Table30 V2: Evaluating Generalized Models by Real Robots at Scale}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4461-4467} }

WA-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
Zezhong Qian,
Xiaowei Chi,
Yu Qi,
Haozhan Li,
Zhi Yang Chen,
Shanghang Zhang
[pdf] [supp]
[bibtex]
@InProceedings{Qian_2026_CVPR, author = {Qian, Zezhong and Chi, Xiaowei and Qi, Yu and Li, Haozhan and Chen, Zhi Yang and Zhang, Shanghang}, title = {WA-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4478-4485} }

A Latent-Centric Perspective on World Models for Autonomous Driving: Taxonomy, Evaluation, and Challenges
Rongxiang Zeng,
Yongqi Dong,
Zhida Shao
[pdf]
[bibtex]
@InProceedings{Zeng_2026_CVPR, author = {Zeng, Rongxiang and Dong, Yongqi and Shao, Zhida}, title = {A Latent-Centric Perspective on World Models for Autonomous Driving: Taxonomy, Evaluation, and Challenges}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4510-4519} }

CrossZero: Zero-Shot of Unseen Embodiment Manipulation via Object-Centric Hierarchical Diffusion Models
Yiheng Ge,
Yongqi Yan,
Mishuo Han,
Changxian LI,
Zizhong Ding,
Jiaxiang Li,
Fan Yang,
Tianshuo Yang,
Tong Shen,
Changle Ouyang,
Weijie Shen,
Weiliang Deng,
Shuhao Liu,
Tian Qi,
Yao Mu
[pdf]
[bibtex]
@InProceedings{Ge_2026_CVPR, author = {Ge, Yiheng and Yan, Yongqi and Han, Mishuo and LI, Changxian and Ding, Zizhong and Li, Jiaxiang and Yang, Fan and Yang, Tianshuo and Shen, Tong and Ouyang, Changle and Shen, Weijie and Deng, Weiliang and Liu, Shuhao and Qi, Tian and Mu, Yao}, title = {CrossZero: Zero-Shot of Unseen Embodiment Manipulation via Object-Centric Hierarchical Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4446-4454} }

LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation
Tianbao Zhang,
Zeyu Liu,
Shuyu Wu,
Fanxing Li,
Zhaoxin Fan,
wenjun wu,
Danping Zou
[pdf] [supp]
[bibtex]
@InProceedings{Zhang_2026_CVPR, author = {Zhang, Tianbao and Liu, Zeyu and Wu, Shuyu and Li, Fanxing and Fan, Zhaoxin and wu, wenjun and Zou, Danping}, title = {LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4520-4529} }

EchoArena: Learning World Models for Reliable VLA Policy Evaluation
Yu-Kai Wang,
Kevin Zhang,
Xiaowei Chi,
Tianxing Chen,
Siqiao Huang,
Chuyao Fu,
Tiecheng Guo,
Peidong Jia,
Yan Qin,
Kuangzhi Ge,
Siyuan Qian,
Weishi Mi,
Zezhong Qian,
Jiajun Li,
Qingpo Wuwu,
Xiaozhu Ju,
Jian Tang,
Shanghang Zhang
[pdf] [supp]
[bibtex]
@InProceedings{Wang_2026_CVPR, author = {Wang, Yu-Kai and Zhang, Kevin and Chi, Xiaowei and Chen, Tianxing and Huang, Siqiao and Fu, Chuyao and Guo, Tiecheng and Jia, Peidong and Qin, Yan and Ge, Kuangzhi and Qian, Siyuan and Mi, Weishi and Qian, Zezhong and Li, Jiajun and Wuwu, Qingpo and Ju, Xiaozhu and Tang, Jian and Zhang, Shanghang}, title = {EchoArena: Learning World Models for Reliable VLA Policy Evaluation}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2026}, pages = {4486-4494} }