The paper investigates whether scaling data, diversity, and model capacity benefits embodied agents in virtual worlds. Using 120 training setups across four model sizes, six data budgets, and five data mixtures, the authors find that more data improves in‑corpus performance, diversity aids transfer to related worlds, and larger models boost data efficiency but may generalize less to distant worlds. They also identify distinct training phases and fit a scaling law, concluding that continued pre‑training alone is insufficient for fully generalist agents.
arXiv:2610.25959v2 Announce Type: replace Abstract: Building embodied agents that can perceive, reason, and act across diverse 3D worlds is a central research direction toward artificial general inte...
arXiv:2605.17912v2 Announce Type: replace-cross Abstract: World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason ab...
arXiv:2607. 03964v1 Announce Type: cross Abstract: World models are rapidly becoming a core infrastructure for embodied intelligence and interactive agents: they provide controllable simulators in which agents can perceive, act, forecast, and acquire scalable experience.
arXiv:2605. 28865v2 Announce Type: replace-cross Abstract: What does a world model learn from physical exploration, without any linguistic supervision?
arXiv:2609.24308v1 Announce Type: new Abstract: Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and responsiveness under exploration, int...
arXiv:2507. 06219v2 Announce Type: replace-cross Abstract: Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles of effective data scaling in robotic manipulation remain insufficiently understood.
GameVerse is a new minute‑scale gameplay video dataset designed to support long‑horizon interactive world modeling. It contains 69.7K clips totaling 1,655 hours and 349.6 million frames, including 1,358 hours of continuous two‑minute sequences—an order of magnitude longer than prior datasets. Each clip is processed through a unified pipeline that provides scene‑consistent segmentation, quality filtering, camera pose estimation, and event‑based caption annotation, with temporally stable camera trajectories and captions that distinguish static context from dynamic events.
arXiv:2607. 13560v1 Announce Type: cross Abstract: Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data.
arXiv:2606. 19990v1 Announce Type: new Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting exploration, behavioral diversity, and richer dynamic discovery.
Building capable embodied agents requires not only multimodal perception and understanding, but also agentic capabilities for reasoning about actions, adapting to evolving situations, and interacting with the physical world. In this report, we introduce Hy-Embodied-VLM-1.
arXiv:2610.04432v2 Announce Type: replace Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on...
arXiv:2607. 05352v1 Announce Type: cross Abstract: We introduce the first multiplayer world model for highly dynamic environments governed by complex physical interactions.