Vision-Language-Action (VLA) models have emerged as a promising paradigm for robot learning, but their representations are still largely inherited from static image-text pretraining, leaving physical dynamics to be learned from comparatively limited action data. Generative video models, by contrast, encode rich spatiotemporal structure and implicit physics, making them a compelling foundation for robotic manipulation. But their potentials are not fully explored in the literature. To bridge the gap, we introduce DiT4DiT, an end-to-end Video-Action Model that couples a video Diffusion Transformer with an action Diffusion Transformer in a unified cascaded framework. Instead of relying on reconstructed future frames, DiT4DiT extracts intermediate denoising features from the video generation process and uses them as temporally grounded conditions for action prediction. We further propose a dual flow-matching objective with decoupled timesteps and noise scales for video prediction, hidden-state extraction, and action inference, enabling coherent joint training of both modules. Across simulation and real-world benchmarks, DiT4DiT achieves state-of-the-art results, reaching average success rates of 98.6% on LIBERO and 50.8% on RoboCasa GR1 while using substantially less training data. On the Unitree G1 robot, it also delivers superior real-world performance and strong zero-shot generalization. Importantly, DiT4DiT improves sample efficiency by over 10x and speeds up convergence by up to 7x, demonstrating that video generation can serve as an effective scaling proxy for robot policy learning. We release code and models at https://dit4dit.github.io/.
ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI
University of California San Diego(加州大学圣地亚哥分校);Carnegie Mellon University(卡内基梅隆大学);Hillbot(Hillbot公司);TU Dresden(德累斯顿技术大学);Tsinghua University(清华大学);King’s College London(伦敦国王学院)
AffordDexGrasp: Open-set Language-guided Dexterous Grasp with Generalizable-Instructive Affordance
School of Computer Science and Engineering, Sun Yat-sen University, China(中山大学计算机科学与工程学院);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China(教育部人工智能与高级计算重点实验室)
TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
School of Computing, National University of Singapore(新加坡国立大学计算机学院);School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(华中科技大学人工智能与自动化学院)
Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction
Institute of Artificial intelligence (TeleAI), China Telecom(人工智能研究院(TeleAI),中国电信);Northwestern Polytechnical University(西北工业大学);Hong Kong University of Science and Technology(香港科技大学)
Generalizable Skill Learning for Construction Robots with Crowdsourced Natural Language Instructions, Composable Skills Standardization, and Large Language Model
Virginia Tech(弗吉尼亚理工大学);University of Michigan(密歇根大学)
Reinforcement learning in linear embedding space unlocks generalizable control across soft robot configurations
National University of Defense Technology(国防科技大学);Hefei University of Technology(合肥工业大学);Nanjing University (Suzhou Campus)(南京大学(苏州校区));Technical University of Munich(慕尼黑工业大学);Beihang University(北京航空航天大学);Newcastle University(纽卡斯尔大学)
LLM-Based Generalizable Hierarchical Task Planning and Execution for Heterogeneous Robot Teams with Event-Driven Replanning
Department of Mechanical Engineering, IIT Gandhinagar(印度加尔各直辖区理工学院机械工程系);Sahyadri College of Engineering and Management(萨哈亚德里工程与管理学院);Vishwakarma Institute of Information Technology(维什瓦克arma信息技术学院)
Human Demonstrations are Generalizable Knowledge for Robots
School of Automation, Beijing Institute of Technology, Beijing, 100081, China(自动化学院,北京理工大学,北京,100081,中国);Beijing Zhongguancun Academy, Beijing, 100094, China(中关村学院,北京,100094,中国)
Skill-Aware Diffusion for Generalizable Robotic Manipulation
School of Control Science and Engineering, Shandong University(控制科学与工程学院,山东大学);Department of Computer Science, The University of Manchester(计算机科学系,曼彻斯特大学)
GeniWorld: A Generalizable Interactive World Model for Robotic Manipulation via Visual Actions
Shenzhen International Graduate School, Tsinghua University(清华大学深圳国际研究生院);Tencent Robotics X(腾讯Robotics X实验室);The Hong Kong University of Science and Technology(香港科技大学);Shenzhen Technology University(深圳技术大学)
Learning Latent Volumetric Dynamics for Multimodal Goal-Conditioned Robot Manipulation of Hair
Robotics Institute, Carnegie Mellon University(卡内基梅隆大学机器人学院);Epic Games, Inc.(Epic Games公司);Meta Codec Avatars Lab(Meta编码人像实验室);Bosch Center for Artificial Intelligence(博世人工智能中心)
Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts
School of Software Technology, Zhejiang University(浙江大学软件学院);School of Computer Sciene and Technology, Hangzhou Dianzi University(杭州电子科技大学计算机学院);China Mobile (Zhejiang) Research & Innovation Institute(中国移动(浙江)研究院);State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室);The Hong Kong Polytechnic University(香港理工大学);Zhiyuan Research Institute(智源研究院);School of Computer Sciene and Technology, Xidian University(西安电子科技大学计算机学院)