← Back to all news
arXiv Computer Vision

Spatially Aware World Action Model via Geometric Latent Diffusion

The paper introduces Spatially Aware World Action Model (SA‑WAM), a diffusion‑based framework that extends existing World Action Models by incorporating depth information alongside RGB to enable 3‑D‑aware action and future‑state prediction. SA‑WAM repurposes a pretrained video diffusion model, using a nonlinear encoding to map unbounded depth into the tokenizer’s bounded domain, thus preserving pretrained visual priors without 3‑D‑specific fine‑tuning. The model achieves state‑of‑the‑art performance on RoboCasa and LIBERO‑Plus benchmarks and demonstrates superior real‑world performance on a UR5 robotic arm in randomized environments, while also providing analysis linking world‑model prediction quality to rollout success.

Related stories

arXiv Computer Vision
Sep 16

World-Action Models for Robot Learning and Control: A Survey

The survey "World-Action Models for Robot Learning and Control" reviews recent advances in coupling future world prediction with executable action generation for robots in open environments. It clarifies the scope of World-Action Models (WAMs) relative to conventional world models, model-based RL, and Vision‑Language‑Action policies, and organizes existing methods through a unified taxonomy covering representations, transition modeling, action interfaces, architectures, training pipelines, data modalities, and scaling strategies. The paper also surveys applications in manipulation, navigation, and autonomous driving, summarizes datasets, benchmarks, and metrics, and discusses key challenges such as action alignment, spatial consistency, long‑horizon memory, and efficient inference.

By Zuxing Lu, Hongjia Zhai, Guanzhi Wang, Huajian Zeng, Jiaqi Yang, Jingyu Liu, Lei Cheng, Yuantai Zhang, Yuheng Qiu, Zezhou Cheng, Ivan Laptev, Danfei Xu, Benjamin Riviere, Giuseppe Loianno, Eric Xing, Xingxing Zuo
agentsdiffusionreinforcement-learningroboticsmultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
3d ago

Learning the 4D World through Point Trajectory Forecasting

arXiv:2610.28594v1 Announce Type: new Abstract: Reliable multi-view forecasting requires videos from different cameras to describe the same evolving 3D scene. To this end, we introduce Video-Point Mo...

By Byungwoo Jeon, Sunghwan Hong, Dohyeon Kim, Jonghoon Lee, Jungwoo Park, Inhee Lee, Doosan Baek, Jinil Kim, Taehyun Lim, Hanbyul Joo, Marc Pollefeys, Saining Xie, Jinwoo Shin
diffusionroboticsbenchmarks
More like this →
arXiv Machine Learning
Jun 16

Geometric Action Model for Robot Policy Learning

arXiv:2606. 17046v1 Announce Type: cross Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world.

By Jisang Han, Seonghu Jeon, Jaewoo Jung, Ren\'e Zurbr\"ugg, Honggyu An, Tifanny Portela, Marco Hutter, Marc Pollefeys, Seungryong Kim, Sunghwan Hong
roboticsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 8

Video Prediction Policy 2: Predict Better, Act Better

Video Prediction Policy 2 (VPP2) is a new world action model that improves zero‑shot generalization for both video prediction and action generation. It achieves this by pretraining a large, diverse manipulation video dataset with event‑level supervision, then distilling the model into a single‑step visual planner and adding a mixture‑of‑transformers action module. Experiments show VPP2 outperforms leading baselines on open‑ended video prediction, real‑world zero‑shot manipulation, and several challenging benchmarks.

By Yanjiang Guo, Haodong Yan, Zhide Zhong, Zhongru Zhang, Qingyuan Yang, Qingzhou Lu, Xiaoyu Chen, Yen-Jen Wang, Shuying Deng, Chenghan Yang, Puzhen Yuan, Chenxin Liu, Tun Ban, Xiang Zhu, Yichen Liu, Kun Feng, Haoang Li, Jianyu Chen
llmsroboticsbenchmarks
More like this →
arXiv Machine Learning
Oct 5

XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation

XGenAct is a world action model that encodes RGB observations, robot actions, metric depth, surface normals, and functional role segmentation as RGB videos using deterministic codecs. It trains a single video diffusion transformer with a unified objective, sampling different perception and action tasks to learn temporal prediction across multiple spatial modalities without separate heads. Experiments on RLBench show that structured perception training boosts closed‑loop success, with XGenAct achieving 52% success on five external tasks compared to 26% for the best baselines, and it outperforms pipelines that first generate RGB and then apply a frozen perception expert for depth and segmentation prediction.

By Tingting Du, Ziyao Wang, Guoheng Sun, Ang Li
llmsdiffusioncomputer-visionrobotics
More like this →
arXiv AI
Aug 27

DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation

DELE-w0.5 is a robotic manipulation framework that predicts future latent states instead of generating full video sequences, thereby inferring robot actions directly from these compact representations. By focusing on physical state changes rather than visual transitions, it reduces model complexity and inference latency. In 480 real‑robot trials across four long‑horizon tasks, DELE‑w0.5 achieved 62.5 % overall task success and 81.3 % macro ordered‑stage progress, outperforming the strongest baseline by 47.5 and 30.7 percentage points.

By Fenghao Lei, Zhixiong Huang, Long Yang, Jiabao Chen, Peilin Huang, Han Fu, Zhuo Li, Xiaoxue Ren
diffusionrobotics
More like this →