activity
20242026
collaborators

20 papers

cs.CV2026

ZimaBlue: Evolving Generalizable World Action Models through Scalable Video Pre-training

Xionghao Wu, Yijun Yang, Shiyang Zhou +17

Robotic manipulation faces a fundamental scaling challenge: robust generalization demands broad physical experience, yet action-labeled robot trajectories are expensive to collect…

cs.RO2026

Scaling Manual-Grounded Appliance Manipulation with Data Synthesis and Unified Planning

Yuxing Long, Lei Kang, Ziyan Yu +8

Operating household appliances requires long-horizon planning that is state-dependent and robust to disturbances, yet existing large models fall short, as no sufficiently diverse,…

cs.CV2026

PatchScene: Patch-based Voxel Diffusion for Large-Scale Scene Completion

Qingdong Xu, Jiajun Zhu, Shilin Zhu +4

We propose PatchScene, a novel diffusion-based framework for large-scale LiDAR scene completion. Unlike existing methods that rely on global latent representations or dense voxel g…

cs.CV2026

Embodied3DBench: Benchmarking Low-Level Embodied Spatial Intelligence of Vision Language Models

Jiyao Zhang, Mingxu Zhang, Yitong Peng +8

Are current Vision Language Models (VLMs) ready to comprehend and reason about complex embodied interactions in 3D environments? We introduce Embodied3DBench, a robot-centric bench…

cs.RO2026

HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning

Jiyao Zhang, Zimu Han, Junhan Wang +7

Robotic imitation learning faces a fundamental trade-off between modeling long-horizon dependencies and enabling fine-grained closed-loop control. Existing fixed-frequency action c…

cs.CV2026

FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario

Hang Dai, Hongwei Fan, Han Zhang +3

The increasing demand for augmented reality and robotics is driving the need for articulated object reconstruction with high scalability. However, existing settings for reconstruct…