Researcher — paper.dinq.me

2026 顶会论文

作者位次 #17/19ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Yang Zhou · Yifan Wang · Jianjun Zhou · Wenzheng Chang · Haoyu Guo · Zizun Li · Kaijing Ma · Xinyue Li · Yating Wang · Haoyi Zhu · Mingyu Liu · Dingning Liu · Jiange Yang · Zhoujie Fu · Junyi Chen · Chunhua Shen · Jiangmiao Pang · Kaipeng Zhang · Tong He

多模态数据与预训练OpenReview

作者位次 #10/10ICLR 2026Poster· Applications / Robotics

Vision-Language-Action Instruction Tuning: From Understanding to Manipulation

Shuai Yang · Hao Li · Bin Wang · Yilun Chen · Yang Tian · Tai Wang · Hanqing Wang · Feng Zhao · Yiyi Liao · Jiangmiao Pang

对齐与偏好多模态OpenReview

作者位次 #12/12ICLR 2026Poster· Applications / Robotics

RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation

Hao Li · ziqin wang · Zi-han Ding · Shuai Yang · Yilun Chen · Yang Tian · Xiaolin Hu · Tai Wang · Dahua Lin · Feng Zhao · Si Liu · Jiangmiao Pang

可解释性OpenReview

作者位次 #14/18ICLR 2026Poster· Applications / Robotics

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

Ganlin Yang · Tianyi Zhang · Haoran Hao · Weiyun Wang · Yibin Liu · Dehui Wang · Guanzhou Chen · Zijian Cai · Junting Chen · Weijie Su · Wengang Zhou · Yu Qiao · Jifeng Dai · Jiangmiao Pang · Gen Luo · Wenhai Wang · Yao Mu · Zhi Hou

推理多模态OpenReview

作者位次 #13/13ICLR 2026Poster· Computer Vision / Vision Models & Multimodal

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

Sihan Yang · Runsen Xu · Yiman Xie · Sizhe Yang · Mo Li · Jingli Lin · Chenming Zhu · Xiaochen Chen · Haodong Duan · Xiangyu Yue · Dahua Lin · Tai Wang · Jiangmiao Pang

多模态评测与基准OpenReview

作者位次 #8/10ICLR 2026Poster· Computer Vision / 3D Rendering & Reconstruction

$\pi^3$: Permutation-Equivariant Visual Geometry Learning

Yifan Wang · Jianjun Zhou · Haoyi Zhu · Wenzheng Chang · Yang Zhou · Zizun Li · Junyi Chen · Jiangmiao Pang · Chunhua Shen · Tong He

多模态OpenReview

作者位次 #10/10ICLR 2026Poster· Applications / Robotics

ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward Guidance

Guanghao Li · Kerui Ren · Linning Xu · Zhewen Zheng · Changjian Jiang · Xin Gao · Bo DAI · Jian Pu · Mulin Yu · Jiangmiao Pang

OpenReview

作者位次 #16/21ICLR 2026Poster

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Haozhan Li · Yuxin Zuo · Jiale Yu · Yuhao Zhang · Yang Zhaohui · Kaiyan Zhang · Xuekai Zhu · Yuchen Zhang · Tianxing Chen · Ganqu Cui · Dehui Wang · Dingxiang Luo · Yuchen Fan · Youbang Sun · Jia Zeng · Jiangmiao Pang · Shanghang Zhang · Yu Wang · Yao Mu · Bowen Zhou · Ning Ding

强化学习与后训练OpenReview

作者位次 #10/11ICLR 2026Poster· Applications / Robotics

Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-Language Navigation

Meng Wei · Chenyang Wan · Peng · Xiqian Yu · Yuqiang Yang · Delin Feng · Wenzhe Cai · Chenming Zhu · Tai Wang · Jiangmiao Pang · Xihui Liu

多模态理论与学习动力学OpenReview

作者位次 #12/12ICLR 2026Poster

Spatially Guided Training for Vision-Language-Action Model

Jinhui Ye · Fangjing Wang · Ning Gao · Junqiu Yu · Yangkun Zhu · Bin Wang · Jinyu Zhang · Weiyang Jin · Yanwei Fu · Feng Zheng · Yilun Chen · Jiangmiao Pang

多模态OpenReview

作者位次 #16/16CVPR 2026Poster· Computer Vision & Pattern Recognition

InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy

Yang Tian · Yuyin Yang · Yiman Xie · Zetao Cai · Xu Shi · Ning Gao · Hangxu Liu · Xuekun Jiang · Zherui Qiu · Feng Yuan · Yaping Li · Ping Wang · Junhao Cai · Jia Zeng · Hao Dong · Jiangmiao Pang

数据与预训练多模态OpenReview 项目页

作者位次 #10/15CVPR 2026Poster· Computer Vision & Pattern Recognition

MM-ACT: Learn from Multimodal Parallel Generation to Act

Haotian Liang · Xinyi Chen · Bin Wang · Mingkang Chen · Yitian Liu · Yuhao Zhang · Zanxin Chen · Tianshuo Yang · Yilun Chen · Jiangmiao Pang · Dong Liu · Xiaokang Yang · Yao Mu · Wenqi Shao · Ping Luo

多模态OpenReview 项目页

作者位次 #9/9CVPR 2026Spotlight· Computer Vision & Pattern Recognition

Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3-D Constrained Terrains

Qingwei Ben · Botian Xu · Kailin Li · Feiyu Jia · Wentao Zhang · Jingping Wang · Jingbo Wang · Dahua Lin · Jiangmiao Pang

多模态社会与人本OpenReview 项目页

作者位次 #10/10CVPR 2026Poster· Computer Vision & Pattern Recognition

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

Wenbo Hu · Jingli Lin · Yilin Long · Yunlong Ran · Lihan Jiang · Yifan Wang · Chenming Zhu · Runsen Xu · Tai Wang · Jiangmiao Pang

多模态推理OpenReview 项目页

作者位次 #14/14CVPR 2026Poster· Computer Vision & Pattern Recognition

ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation

Yang Li · Zhaxizhuoma Zhaxizhuoma · Hongru Jiang · Junjie Xia · Hongquan Zhang · Jinda Du · Yunsong Zhou · Jia Zeng · Ce Hao · Jieji Ren · Qiaojun Yu · Cewu Lu · Yu Qiao · Jiangmiao Pang

多模态OpenReview 项目页

作者位次 #7/8SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

TrajVG: 3D Trajectory-Coupled Visual Geometry Learning

Xingyu Miao · Weiguang Zhao · Tao Lu · Linning Xu · Mulin Yu · Yang Long · Jiangmiao Pang · Junting Dong

多模态OpenReview

作者位次 #14/14SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking

Weiguang Zhao · Haoran Xu · Xingyu Miao · Qin Zhao · Rui Zhang · Kaizhu Huang · Ning Gao · Peizhou Cao · Mingze Sun · Mulin Yu · Tao Lu · Linning Xu · Junting Dong · Jiangmiao Pang

数据与预训练OpenReview

作者位次 #6/9SIGGRAPH 2026Oral· Computer Graphics (Conference Track)

EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

Xijie Yang · Mulin Yu · Changjian Jiang · Kerui Ren · Tao Lu · Jiangmiao Pang · Dahua Lin · Bo DAI · Linning Xu

OpenReview

作者位次 #7/7ICRA 2026Oral· Robotics & Automation

Behavior Foundation Model for Humanoid Robots

Weishuai Zeng · Shunlin Lu · Kangning Yin · Xiaojie Niu · Minyue Dai · Jingbo Wang · Jiangmiao Pang

社会与人本OpenReview

作者位次 #9/9ICRA 2026Oral· Robotics & Automation

NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance

Wenzhe Cai · Jiaqi Peng · Yuqiang Yang · Yujian Zhang · Meng Wei · Hanqing Wang · Yilun Chen · Tai Wang · Jiangmiao Pang

OpenReview

作者位次 #8/8ICRA 2026Oral· Robotics & Automation

One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation

Juncheng Mu · Sizhe Yang · Hojin Bae · Feiyu Jia · Qingwei Ben · Boyi Li · Huazhe Xu · Jiangmiao Pang

OpenReview

作者位次 #7/7ICRA 2026Oral· Robotics & Automation

UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data

Sizhe Yang · Yiman Xie · Zhixuan Liang · Yang Tian · Jia Zeng · Dahua Lin · Jiangmiao Pang

数据与预训练OpenReview

作者位次 #6/7ICRA 2026Oral· Robotics & Automation

H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer

Yunfeng Lin · Minghuan Liu · Yufei Xue · Ming Zhou · s Ark Lab) · Jiangmiao Pang · Ruiming Tang (Huawei Noah&#x27

数据与预训练社会与人本OpenReview

作者位次 #8/9ICRA 2026Oral· Robotics & Automation

VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception

Junli Ren · Tao Huang · Huayi Wang · Zirui Wang · Qingwei Ben · Junfeng Long · Yanchao Yang · Jiangmiao Pang · Ping Luo

多模态社会与人本OpenReview

作者位次 #11/11ICRA 2026Oral· Robotics & Automation

Towards Adaptable Humanoid Control via Adaptive Motion Tracking

Tao Huang · Huayi Wang · Junli Ren · Kangning Yin · Zirui Wang · Xiao Chen · Feiyu Jia · Wentao Zhang · Junfeng Long · Jingbo Wang · Jiangmiao Pang

社会与人本OpenReview

作者位次 #4/5ICRA 2026Oral· Robotics & Automation

Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

Quanquan Peng · Yunfeng Lin · Yufei Xue · Jiangmiao Pang · Ruiming Tang (Huawei Noah&#x27

强化学习与后训练社会与人本OpenReview

作者位次 #6/6ICRA 2026Oral· Robotics & Automation

LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

Jiaqi Peng · Wenzhe Cai · Yuqiang Yang · Tai Wang · Yuan Shen · Jiangmiao Pang

多模态OpenReview

作者位次 #9/9ICRA 2026Oral· Robotics & Automation

RE 3 SIM: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation

Xiaoshen Han · Junqiu Yu · Minghuan Liu · Yilun Chen · Xiaoyang Lyu · Yang Tian · Bolun Wang · Ruiming Tang (Huawei Noah&#x27 · Jiangmiao Pang

社会与人本OpenReview

作者位次 #7/8ICRA 2026Oral· Robotics & Automation

Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP

Meng Wei · Chenyang Wan · Tai Wang · Wenzhe Cai · Yilun Chen · Hanqing Wang · Jiangmiao Pang · Xihui Liu

理论与学习动力学OpenReview

作者位次 #11/11ICRA 2026Oral· Robotics & Automation

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

Meng Wei · Chenyang Wan · Xiqian Yu · Tai Wang · Xiaohan Mao · Chenming Zhu · Wenzhe Cai · Hanqing Wang · Yilun Chen · Xihui Liu · Jiangmiao Pang

多模态OpenReview

作者位次 #7/10IROS 2026Poster· Learning Versatile and Robust Dexterous Manipulation

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-Of-Dexterous-Experts VLA

Tutian Tang · Xingyu Ji · Wanli XING · Ce Hao · Wenqiang Xu · Lin Shao · Jiangmiao Pang · Cewu Lu · Qiaojun Yu · Kaifeng Zhang

强化学习与后训练社会与人本Dexterous ManipulationDeep Learning in Grasping and ManipulationIn-Hand ManipulationOpenReview

作者位次 #11/11AAAI 2026Poster· Artificial Intelligence

Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

Hao Li · Shuai Yang · Yilun Chen · Xinyi Chen · Xiaoda Yang · Yang Tian · Hanqing Wang · Tai Wang · Dahua Lin · Feng Zhao · Jiangmiao Pang

多模态效率与系统OpenReview

Jiangmiao Pang

获取完整研究档案

联系方式

2026 顶会论文

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Vision-Language-Action Instruction Tuning: From Understanding to Manipulation

RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation

Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence

$\pi^3$: Permutation-Equivariant Visual Geometry Learning

ARTDECO: Toward High-Fidelity On-the-Fly Reconstruction with Hierarchical Gaussian Structure and Feed-Forward Guidance

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-Language Navigation

Spatially Guided Training for Vision-Language-Action Model

InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy

MM-ACT: Learn from Multimodal Parallel Generation to Act

Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3-D Constrained Terrains

G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning

ForceVLA2: Unleashing Hybrid Force-Position Control with Force Awareness for Contact-Rich Manipulation

TrajVG: 3D Trajectory-Coupled Visual Geometry Learning

SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking

EAG-PT: Emission-Aware Gaussians and Path Tracing for Diffuse Indoor Scene Reconstruction and Editing

Behavior Foundation Model for Humanoid Robots

NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance

One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation

UltraDexGrasp: Learning Universal Dexterous Grasping for Bimanual Robots with Synthetic Data

H-Zero: Cross-Humanoid Locomotion Pretraining Enables Few-shot Novel Embodiment Transfer

VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception

Towards Adaptable Humanoid Control via Adaptive Motion Tracking

Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometry

RE 3 SIM: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation

Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP

StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling

Towards Human-Like Manipulation through RL-Augmented Teleoperation and Mixture-Of-Dexterous-Experts VLA

Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

常见合作者