Zekun Qi

News

2026-02 One paper accepted to CVPR 2026.
2026-01 Three papers accepted to ICLR 2026.
2025-09 Two papers accepted to NeurIPS 2025, and one of them as Spotlight presentation.
2025-07 One paper accepted to ACMMM 2025 as Oral presentation.
2025-06 Two papers accepted to ICCV 2025, and one of them as Highlight presentation.
2025-01 One paper accepted to ICLR 2025.
2024-07 One paper accepted to ECCV 2024 and one paper accepted to ACMMM 2024.
2024-01 One paper accepted to ICLR 2024 as Spotlight presentation.
2023-09 One paper accepted to NeurIPS 2023.
2023-04 One paper accepted to ICML 2023.
2023-01 One paper accepted to ICLR 2023.

Publications

* indicates equal contribution

Selected Works By Date

Humanoid-GPT

Humanoid Generative Pre-Training for Zero-Shot Motion Tracking

Zekun Qi*, Xuchuan Chen*, Jilong Wang*, Chenghuai Lin*, Yunrui Lian, Zhikai Zhang, Yu Guan, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

We introduce Humanoid-GPT, a GPT-style Transformer trained on a billion-scale motion corpus for whole-body control, achieving zero-shot generalization to unseen motions and control tasks.

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

International Conference on Learning Representations (ICLR), 2026

Based on cognitive psychology, we introduce a comprehensive and complex spatial reasoning benchmark, including 50 detailed categories and 1.5K manual labeled QA pairs.

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

Zekun Qi*, Wenyao Zhang*, Yufei Ding*, Runpei Dong, Xinqiang Yu, Jingwen Li, Lingyun Xu, Baoyu Li, Xialin He, Guofan Fan, Jiazhao Zhang, Jiawei He, Jiayuan Gu, Xin Jin, Kaisheng Ma, Zhizheng Zhang, He Wang, Li Yi

Conference on Neural Information Processing Systems (NeurIPS), 2025 Spotlight

We introduce the concept of semantic orientation, representing the object orientation condition on open vocabulary language.

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Wenyao Zhang*, Hongsi Liu*, Zekun Qi*, Yunnan Wang*, Xinqiang Yu, Jiazhao Zhang, Runpei Dong, Jiawei He, He Wang, Zhizheng Zhang, Li Yi, Wenjun Zeng, Xin Jin

Conference on Neural Information Processing Systems (NeurIPS), 2025

We recast the vision–language–action model as a perception–prediction–action model and make the model explicitly predict a compact set of dynamic, spatial and high-level semantic information.

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

European Conference on Computer Vision (ECCV), 2024

We present ShapeLLM, the first 3D Multimodal Large Language Model designed for embodied interaction, exploring a universal 3D object understanding with 3D point clouds and languages.

DreamLLM: Synergistic Multimodal Comprehension and Creation

Runpei Dong*, Chunrui Han*, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, Li Yi

International Conference on Learning Representations (ICLR), 2024 Spotlight

We present DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models empowered with frequently overlooked synergy between multimodal comprehension and creation.

ReCon

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

International Conference on Machine Learning (ICML), 2023

We propose contrast guided by reconstruct to mitigate the pattern differences between two self-supervised paradigms.

ACT

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

International Conference on Learning Representations (ICLR), 2023

We propose to use autoencoders as cross-modal teachers to transfer dark knowledge into 3D representation learning.

2026

Humanoid-GPT

Humanoid Generative Pre-Training for Zero-Shot Motion Tracking

Zekun Qi*, Xuchuan Chen*, Jilong Wang*, Chenghuai Lin*, Yunrui Lian, Zhikai Zhang, Yu Guan, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

We introduce Humanoid-GPT, a GPT-style Transformer trained on a billion-scale motion corpus for whole-body control, achieving zero-shot generalization to unseen motions and control tasks.

VLA-JEPA

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Jingwen Sun*, Wenyao Zhang*, Zekun Qi, Shaojie Ren, Zezhi Liu, Hanxin Zhu, Guangzhong Sun, Xin Jin, Zhibo Chen

ArXiv Preprint, 2026

We introduce VLA-JEPA, a JEPA-style pretraining framework that learns action-relevant transition semantics by predicting future latent states, achieving consistent gains in sample efficiency and generalization.

ReWorld

ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models

ArXiv Preprint, 2026

We introduce ReWorld, a framework that employs reinforcement learning to align video-based embodied world models with physical realism, task completion capability, embodiment plausibility and visual quality.

GS-Reasoner

Reasoning in Space via Grounding in the World

International Conference on Learning Representations (ICLR), 2026

We believe that grounding can be seen as a chain-of-thought for spatial reasoning. Based on this, we achieve a new SOTA performance on VSI-Bench.

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models

International Conference on Learning Representations (ICLR), 2026

Based on cognitive psychology, we introduce a comprehensive and complex spatial reasoning benchmark, including 50 detailed categories and 1.5K manual labeled QA pairs.

2025

Switch-JustDance

Switch-JustDance: Benchmarking Whole-Body Motion Tracking Policies Using a Commercial Console Game

Jeonghwan Kim*, Wontaek Kim*, Yidan Lu*, Jin Cheng*, Fatemeh Zargarbashi*, Zicheng Zeng*, Zekun Qi*, Zhiyang Dou, Nitish Sontakke, Donghoon Baek, Sehoon Ha, Tianyu Li

ArXiv Preprint, 2025

We present Switch-JustDance, a low-cost benchmarking pipeline that leverages Just Dance on Nintendo Switch to evaluate humanoid whole-body control, enabling direct human-robot comparison.

MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning

ArXiv Preprint, 2025

We present MM-Nav a multi-view VLA system with 360° perception. The model is trained on large-scale expert navigation data collected from multiple reinforcement learning agents.

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

Conference on Neural Information Processing Systems (NeurIPS), 2025 Spotlight

We introduce the concept of semantic orientation, representing the object orientation condition on open vocabulary language.

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Wenyao Zhang*, Hongsi Liu*, Zekun Qi*, Yunnan Wang*, Xinqiang Yu, Jiazhao Zhang, Runpei Dong, Jiawei He, He Wang, Zhizheng Zhang, Li Yi, Wenjun Zeng, Xin Jin

Conference on Neural Information Processing Systems (NeurIPS), 2025

We recast the vision–language–action model as a perception–prediction–action model and make the model explicitly predict a compact set of dynamic, spatial and high-level semantic information.

DexVLG: Dexterous Vision-Language-Grasp Model at Scale

International Conference on Computer Vision (ICCV), 2025 Highlight

We introduce DexVLG, a vision‑language‑grasp model trained on the 170M‑pose, 174k‑object dataset that can generate instruction‑aligned dexterous grasp poses.

Hybrid-Depth

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation

International Conference on Computer Vision (ICCV), 2025

We introduce Hybrid‑depth, a self‑supervised method that aligns hybrid semantics via language guided fusion, achieving SOTA accuracy on KITTI.

PPT

Positional Prompt Tuning for Efficient 3D Representation Learning

ACM International Conference on Multimedia (ACMMM), 2025 Oral

We rethink the role of positional encoding in 3D representation learning, and propose Positional Prompt Tuning for transfer learning.

DreamBench++

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

International Conference on Learning Representations (ICLR), 2025

We collect diverse images and prompts, and utilize GPT-4o for automated evaluation aligned with human preference.

2024

ShapeLLM: Universal 3D Object Understanding for Embodied Interaction

European Conference on Computer Vision (ECCV), 2024

We present ShapeLLM, the first 3D Multimodal Large Language Model designed for embodied interaction.

Point-GCC

Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast

ACM International Conference on Multimedia (ACMMM), 2024

We enhance the utilization of color information to improve 3D scene self-supervised learning.

DreamLLM: Synergistic Multimodal Comprehension and Creation

Runpei Dong*, Chunrui Han*, Yuang Peng, Zekun Qi, Zheng Ge, Jinrong Yang, Liang Zhao, Jianjian Sun, Hongyu Zhou, Haoran Wei, Xiangwen Kong, Xiangyu Zhang, Kaisheng Ma, Li Yi

International Conference on Learning Representations (ICLR), 2024 Spotlight

We present DreamLLM, a learning framework that first achieves versatile Multimodal Large Language Models.

2023

VPP

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

Conference on Neural Information Processing Systems (NeurIPS), 2023

We achieve rapid, multi-category 3D conditional generation by sharing the merits of different representations. VPP can generate 3D shapes in less than 0.2s.

ReCon

Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining

International Conference on Machine Learning (ICML), 2023

We propose contrast guided by reconstruct to mitigate the pattern differences between two self-supervised paradigms.

ACT

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

International Conference on Learning Representations (ICLR), 2023

We propose to use autoencoders as cross-modal teachers to transfer dark knowledge into 3D representation learning.

Honors and Awards

2024 National Scholarship & Xiaomi Special Scholarship, Xi'an Jiaotong University
2022 Outstanding Graduate, Xi'an Jiaotong University
2021 Annual Spiritual Civilization Award, Xi'an Jiaotong University
2020 National runner-up of the China Undergraduate Physics Tournament (CUPT) as the team leader