arXiv:2606. 28385v1 Announce Type: cross Abstract: Recent advances in robot world models enable synthetic video generation for embodied prediction and planning.
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.
arXiv:2611.05163v2 Announce Type: replace-cross Abstract: Robot foundation models have shown remarkable performance in robot control, yet adapting them to a new task still relies heavily on teleopera...
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.
The paper introduces RoboTryOn, a method that transforms human egocentric videos into synthetic demonstrations for robots by virtually swapping the human with a target robot while preserving task, objects, and background. It uses autoregressive keyframe translation guided by human hand skeletons and an inverse dynamics model to generate action labels for policy learning. Experiments on various humanoid robots show that policies trained on these synthetic videos achieve up to 60% success on new tasks, matching teleoperated demonstration performance at roughly one‑third the cost.
arXiv:2609.38172v1 Announce Type: cross Abstract: Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. How...
RoboGene is an agentic framework designed to generate diverse and informative manipulation tasks for single-arm, dual-arm, and mobile robots. It employs diversity-driven sampling, agentic self-reflection for task quality assessment, and human-verified feedback memory to validate and refine tasks. The framework produced 18,000 real-world trajectories and introduced new metrics for task feasibility and diversity, outperforming models like GPT‑4o and Gemini 2.5 Pro in training VLA models that achieve higher success rates and stronger generalization.
arXiv:2606. 00054v1 Announce Type: cross Abstract: Recent progress in generalizable embodied control has been driven by large-scale pretraining of Vision-Language-Action (VLA) models.
Being‑M0.7 is a latent world‑action model that learns from a large mixed‑modality human dataset (over 10,000 hours of video‑only, motion‑only, and paired video‑motion data) to predict future latent visual states and motion. The model is pre‑trained on human data, adapted to robot viewpoints during mid‑training, and then combined with an action expert via gated cross‑attention during post‑training to produce executable whole‑body commands. In experiments, Being‑M0.7 outperforms baselines on the SIMPLE benchmark and matches the best baseline on real‑world Unitree G1 loco‑manipulation tasks.
arXiv:2610.31845v1 Announce Type: cross Abstract: Scaling policy learning requires broad experience and reliable supervision. Robot demonstrations provide high-quality trajectory supervision but are...
arXiv:2609.19142v1 Announce Type: new Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse...
arXiv:2610.06598v2 Announce Type: replace-cross Abstract: Action-conditioned robot world models must respond precisely to robot trajectories while preserving realistic visual dynamics, yet learning b...