MT‑WAM enhances the Fast‑WAM framework by adding complementary supervision for future 2‑D point trajectories and visual features while keeping the original training objectives. A lightweight dual‑stream branch and structured attention mask isolate motion‑specific processing, and motion‑stream tokens provide additional dynamics cues to the action expert. During inference, MT‑WAM skips future‑video prediction, using cached video and motion information to achieve higher success rates on LIBERO, LIBERO‑Plus, RoboTwin 2.0 Clean2Rand, and several real‑world tasks.
By Yiguang Yang, Jiankun Peng, Xiaoming Wang, Yiran Zhang, Zhibo Fang
DeltaWAM introduces a new approach to world-action models (WAMs) for bimanual manipulation by jointly predicting visual deltas and actions instead of dense future frames, thereby reducing redundant modeling of unchanged content and mitigating nuisance appearance variations. The method employs three architectures with varying representation and computation sharing, and incorporates Streaming Delta Memory (SDM) to update cached anchor context using compact observed deltas, which cuts heavy video-expert processing. Experiments on RoboTwin show that DeltaWAM with SDM raises average success rates from 81.3% to 85.4% in clean settings and from 75.8% to 83.9% under visual randomization, while also reducing training FLOPs by up to 23.77% and inference latency by 36.57%.
whyItMatters":"DeltaWAM improves both performance and computational efficiency for bimanual manipulation tasks by focusing on visual deltas and efficient memory updates, as demonstrated by higher success rates and lower FLOPs on RoboTwin."
By Han Yan, Zishang Xiang, Haokai Jiang, Zeyu Zhang, Qilin Wang, Weiyu Guo, Yandong Guo, Boxin Shi, Hao Tang
ZimaBlue is a scalable framework that learns generalizable World Action Models (WAMs) from large-scale egocentric videos. It follows a three-stage curriculum: causal video pre‑training, video‑action mid‑training with a unified action representation, and final specialization to a target robot. The system employs an asynchronous Slow‑Fast architecture to enable real‑time 30 Hz action prediction, achieving a jump in real‑robot zero‑shot success from 36.1% to 77.8% when leveraging over 120,000 hours of embodied video.
By Xionghao Wu, Yijun Yang, Shiyang Zhou, Haoze Sun, Jianhui Liu, Songsong Yu, Jiyao Zhang, Wenbo Li, Bo Wang, Guoqing Ma, Lin Song, Renjie Liao, Shenghe Zheng, Wei Tang, Xiaojuan Qi, Yanwei Li, Yuan Zhang, Zhuotao Tian, Haoyang Huang, Nan Duan
CtrlWAM introduces a controllable world action model that jointly predicts actions (intent) and visual futures (foresight). By executing perturbed actions in a simulator and pairing them with noised visual outcomes, it aligns action predictions with their visual consequences, using warped video–action noise schedules to maintain visual layout responsiveness. The model extends beyond ego‑only control to multiple agent streams, improving action forecasts, video–action agreement, and command following in driving and robotics experiments.
By Chensheng Peng, Wenhao Ding, Ran Tian, Zewei Zhou, Jef Packer, Maximilian Igl, Peter Karkus, Yan Wang, Masayoshi Tomizuka, Boris Ivanovic, Marco Pavone, Yuxiao Chen
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.
By Javier Alejandro Lopetegui Gonzalez, Paul Pacaud, Cordelia Schmid
arXiv:2609.22332v1 Announce Type: cross
Abstract: Generalizable robot manipulation requires predicting how a scene will evolve, identifying where interactions are feasible, and determining how to act...
By Jiadi You, Qize Yu, Yue Chen, Minghong Cai, Zhide Zhong, Yuran Wang, Bowen Ping, Jiaqi Liang, Zhenhao Shen, Haodong Yan, Yinchuan Li, Ruihai Wu, Xiaojuan Qi, Yingcong Chen
RotVLA introduces a Vision‑Language‑Action framework that replaces discrete latent action encoding with a continuous rotational latent action representation on the group SO(n). This design provides continuity, compositionality, and structured geometry that better capture real‑world action dynamics, and a triplet frame learning scheme enforces meaningful temporal dynamics while preventing degeneration. Trained with 1.7 B parameters on large cross‑embodiment datasets, RotVLA achieves state‑of‑the‑art performance on LIBERO and RoboTwin2.0 benchmarks and shows strong real‑world manipulation results.
By Qiwei Li, Xicheng Gong, Xinghang Li, Peiyan Li, Quanyun Zhou, Hangjun Ye, Jiahuan Zhou, Yadong Mu
arXiv:2606. 09811v1 Announce Type: cross Abstract: World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical priors into policy learning.
By Jisong Cai, Long Ling, Shiwei Chu, Zhongshan Liu, Jiayue Kang, Zhixuan Liang, Wenjie Xu, Yinan Mao, Weinan Zhang, Xiaokang Yang, Ru Ying, Ran Zheng, Yao Mu
InternW0-Δ is a unified World Action Model that integrates pretrained visual dynamics, scene semantics, 4D geometry, and motion priors within a Mixture-of-Transformers framework to generate robot actions. It leverages a frozen VLM for semantic guidance, a 4D foundation model for geometric priors, and introduces Causal Imprint to learn future-relevant scene changes without future-video rollout. The model is pretrained on a newly curated 20K‑hour heterogeneous corpus of robot and human demonstrations, achieving superior performance on simulation benchmarks and real‑robot platforms.
By Xingyu Miao, Zizun Li, Baole Fang, Kaiwen Song, Tenghui Wang, Hanxue Zhang, Yating Wang, Xudong Li, Yuping He, Xueyuan Wei, Chao Gao, Xijie Yang, Yingxiang Xu, Kerui Ren, Wenqi Guo, Jianjun Zhou, Xinzhe Wang, Weiguang Zhao, Ni Yang, Zetao Cai, Yufei Xue, Hengjie Li, Zeyu He, Yuanzhen Zhou, Rong Fu, Jianyang Zhang, Siwei Cui, Fuxian Huang, Yunsong Zhou, Xing Gao, Yifei Yao, Qiaojun Yu, Kailin Li, Ming Zhou, Mu Huang, Xinyue Li, Wenze Cui, Bingqi Jiang, Xueyue Zhu, Junting Dong, Haoyu Guo, Tao Lu, Mulin Yu, Bowen Zhou, Bin Zhao, Tianfan Xue, Weinan Zhang, Chunhua Shen
arXiv:2607. 08436v1 Announce Type: cross Abstract: Egocentric human data offers scalable supervision for robot manipulation.
By Baoyu Li, Xinchen Yin, Mengying Lin, Yixin Zhang, Danfei Xu
The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
By Shiqian Li, Chenguo Lin, Zhiguang Liu, Yu Tang, Jiarong Ou, Rui Chen, Yixin Zhu
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