Related papers: GigaWorld-Policy: An Efficient Action-Centered Wor…

Leveraging future observation modeling to facilitate action generation presents a promising avenue for enhancing the capabilities of Vision-Language-Action (VLA) models. However, existing approaches struggle to strike a balance between…

Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling,…

World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are difficult to ground in…

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

Training Vision-Language-Action (VLA) models for generalist robots typically requires large-scale real-world robot data, which is expensive and time-consuming to collect. The inefficiency of physical data collection severely limits the…

We propose Heterogeneous Masked Autoregression (HMA) for modeling action-video dynamics to generate high-quality data and evaluation in scaling robot learning. Building interactive video world models and policies for robotics is difficult…

Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy…

Learning robot policies using imitation learning requires collecting large amounts of costly action-labeled expert demonstrations, which fundamentally limits the scale of training data. A promising approach to address this bottleneck is to…

Web agents based on large language models have demonstrated promising capability in automating web tasks. However, current web agents struggle to reason out sensible actions due to the limitations of predicting environment changes, and…

Robust perception and dynamics modeling are fundamental to real-world robotic policy learning. Recent methods employ video diffusion models (VDMs) to enhance robotic policies, improving their understanding and modeling of the physical…

Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or…

Vision-Language-Action (VLA) models have shown strong potential for general-purpose robotic manipulation, but their reliance on expert demonstrations limits their ability to learn from failures and perform self-corrections. Reinforcement…

We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world representations. Existing world-model-based planners suffer…

Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to extensive rollouts, resets, supervision, and safety risks. Action-conditioned video world…

Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has…

World models are emerging as a foundational paradigm for scalable, data-efficient embodied AI. In this work, we present GigaWorld-0, a unified world model framework designed explicitly as a data engine for Vision-Language-Action (VLA)…

Robot learning from interacting with the physical world is fundamentally bottlenecked by the cost of physical interaction. The two alternatives, supervised finetuning (SFT) from expert demonstrations and reinforcement learning (RL) in a…

Robotic manipulation requires anticipating how the environment evolves in response to actions, yet most existing systems lack this predictive capability, often resulting in errors and inefficiency. While Vision-Language Models (VLMs)…

World models aim to improve robotic decision making by predicting the consequences of actions. However, in practice, their predictions often become unreliable once the robot encounters states outside the training distribution, limiting…

A unified video and action model holds significant promise for robotics, where videos provide rich scene information for action prediction, and actions provide dynamics information for video prediction. However, effectively combining video…