4 papers
VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding
Jingkun Yi, Shujie Zhang, Zirui Zhou +8
Pretrained vision-language models (VLMs) already exhibit strong visual, spatial and reasoning capabilities relevant to robotic manipulation. The key challenge in turning pretrained…
RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation
Shujie Zhang, Jingkun Yi, Weipeng Zhong +6
Recovering real-world scenes as interactive simulation environments can enable generalizable robot learning and reproducible policy evaluation. However, constructing scenes that ar…
3D Scene Change Modeling With Consistent Multi-View Aggregation
Zirui Zhou, Junfeng Ni, Shujie Zhang +2
Change detection plays a vital role in scene monitoring, exploration, and continual reconstruction. Existing 3D change detection methods often exhibit spatial inconsistency in the…
Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
Junfeng Ni, Yu Liu, Ruijie Lu +4
Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, par…