12 papers
UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
Mengmeng Liu, Diankun Zhang, Jiuming Liu +7
World Action Models (WAMs) have shown strong potential for improving action generalization in autonomous driving by using future video prediction as dense supervision for scene dyn…
Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning
Hongyang He, Jiuming Liu, Victor Sanchez
Chain-of-thought (CoT) reasoning has emerged as an effective approach for activating latent reasoning capabilities in large language models. However, most existing CoT methods use…
Semi-Supervised Vision-Language-Action Model
Hongyang He, Jiuming Liu, Victor Sanchez
Vision-Language-Action (VLA) models enable robots to predict actions directly from visual observations and language instructions, but adapting them to new environments still depend…
Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
Jiuming Liu, Chaojun Ni, Mengmeng Liu +7
With rapid development of large language models and diffusion-based content generation, world modeling has attracted increasing research attention, benefiting various downstream do…
Mamba-VGGT: Persistent Long-Sequence Video Geometry Grounded Transformer via External Sliding Window Mamba Memory
Tianchen Deng, Zhenxiang Xiong, Nailin Wang +4
Visual Geometry Grounded Transformers (VGGT) have set new benchmarks in high-fidelity 3D scene reconstruction. However, as the sequence length increases, these models suffer from c…
SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
Xuyi Hu, Jin Lyu, Jiuming Liu +4
3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scenes, while existing methods pred…
DriveVA: Video Action Models are Zero-Shot Drivers
Mengmeng Liu, Diankun Zhang, Jiuming Liu +7
Generalization is a central challenge in autonomous driving, as real-world deployment requires robust performance under unseen scenarios, sensor domains, and environmental conditio…
VectorWorld: Efficient Streaming World Model via Diffusion Flow on Vector Graphs
Chaokang Jiang, Desen Zhou, Jiuming Liu +1
Closed-loop evaluation of autonomous-driving policies requires interactive simulation beyond log replay. However, existing generative world models often degrade in closed loop due…
RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer
Jiuming Liu, Guangming Wang, Zhe Liu +7
Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challe…
4DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generation
Mengmeng Liu, Jiuming Liu, Yunpeng Zhang +4
Remarkable advances in recent 2D image and 3D shape generation have induced a significant focus on dynamic 4D content generation. However, previous 4D generation methods commonly s…
DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion
Mengmeng Liu, Michael Ying Yang, Jiuming Liu +5
Visual-LiDAR odometry is a critical component for autonomous system localization, yet achieving high accuracy and strong robustness remains a challenge. Traditional approaches comm…
TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generation
Jiuming Liu, Zheng Huang, Mengmeng Liu +4
LiDAR scene generation is critical for mitigating real-world LiDAR data collection costs and enhancing the robustness of downstream perception tasks in autonomous driving. However,…