ZQ
Zekun qi
cs.CVcs.ROcs.AIcs.LGcs.CL
On Valency
published · living versionsW_qyzn94xf·v1 · currentpublished
UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction
with Xinqiang Yu, Jiawei He, Wenyao Zhang, Xuchuan Chen +4
1 version
Preprints & journals
22 papers in the corpus · 2022–2026UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction2609.12898v1 · Xinqiang Yu, Zekun qi, Jiawei He et al.2026 · 0 citationsarXivon Valency
RoboGesture: Real-Time Semantic-aligned Co-Speech Gestures Generation for Humanoid Interaction2608.28693v1 · Zifan Wang, Ziang Ren, Pengyang Shi et al.2026 · 0 citationsarXiv
HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark2608.13555v1 · Dairu Liu, Zekun Qi, Jiayu Zeng et al.2026 · 0 citationsarXiv
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?2606.19531v1 · Yuyang Zhang, Wenyao Zhang, Zekun Qi et al.2026 · 0 citationsarXiv
LIMMT: Less is More for Motion Tracking2606.06953v1 · Yu Guan, Zekun Qi, Chenghuai Lin et al.2026 · 0 citationsarXiv
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking2606.03985v1 · Zekun Qi, Xuchuan Chen, Dairu Liu et al.2026 · 0 citationsarXiv
Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining2604.16391v1 · Wenyao Zhang, Bozhou Zhang, Zekun Qi et al.2026 · 0 citationsarXiv
Learning Athletic Humanoid Tennis Skills from Imperfect Human Motion Data2603.12686v1 · Zhikai Zhang, Haofei Lu, Yunrui Lian et al.2026 · 0 citationsarXiv
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model2602.10098v2 · Jingwen Sun, Wenyao Zhang, Zekun Qi et al.2026 · 0 citationsarXiv
Switch-JustDance: Benchmarking Whole Body Motion Tracking Controllers Using a Commercial Console Game2511.17925v3 · Jeonghwan Kim, Wontaek Kim, Yidan Lu et al.2025 · 0 citationsarXiv
Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation2510.09320v1 · Wenyao Zhang, Hongsi Liu, Bohan Li et al.2025 · 3 citationsarXiv
MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning2510.03142v2 · Tianyu Xu, Jiawei Chen, Jiazhao Zhang et al.2025 · 0 citationsarXiv
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge2507.04447v3 · Wenyao Zhang, Hongsi Liu, Zekun Qi et al.2025 · 9 citationsarXiv
DexVLG: Dexterous Vision-Language-Grasp Model at Scale2507.02747v1 · Jiawei He, Danshi Li, Xinqiang Yu et al.2025 · 7 citationsarXiv
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation2502.13143v2 · Zekun Qi, Wenyao Zhang, Yufei Ding et al.2025 · 7 citationsarXiv
DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation2406.16855v2 · Yuang Peng, Yuxin Cui, Haomiao Tang et al.2024 · 0 citationsarXiv
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction2402.17766v3 · Zekun Qi, Runpei Dong, Shaochen Zhang et al.2024 · 43 citationsarXiv
DreamLLM: Synergistic Multimodal Comprehension and Creation2309.11499v2 · Runpei Dong, Chunrui Han, Yuang Peng et al.2023 · 21 citationsarXiv
VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation2307.16605v2 · Zekun Qi, Muzhou Yu, Runpei Dong et al.2023 · 2 citationsarXiv
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast2305.19623v2 · Guofan Fan, Zekun Qi, Wenkai Shi et al.2023 · 13 citationsarXiv
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining2302.02318v2 · Zekun Qi, Runpei Dong, Guofan Fan et al.2023 · 30 citationsarXiv
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?2212.08320v2 · Runpei Dong, Zekun Qi, Linfeng Zhang et al.2022 · 19 citationsarXiv
Career total: 25 works. 22 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.