Related papers: Do World Action Models Generalize Better than VLAs…

The Visual-Language-Action (VLA) models can follow text instructions according to visual observations of the surrounding environment. This ability to map multimodal inputs to actions is derived from the training of the VLA model on…

Vision-Language-Action (VLA) models provide a promising paradigm for robot learning by integrating visual perception with language-guided policy learning. However, most existing approaches rely on 2D visual inputs to perform actions in 3D…

Pre-trained Vision-Language-Action (VLA) models have achieved remarkable success in improving robustness and generalization for end-to-end robotic manipulation. However, these models struggle with long-horizon tasks due to their lack of…

Trained on internet-scale video data, generative world models are increasingly recognized as powerful world simulators that can generate consistent and plausible dynamics over structure, motion, and physics. This raises a natural question:…

Vision-Language-Action (VLA) models often suffer from performance degradation under distribution shifts, as they struggle to learn generalized behavior representations across varying environments. While existing approaches attempt to…

Embodied intelligence systems, which enhance agent capabilities through continuous environment interactions, have garnered significant attention from both academia and industry. Vision-Language-Action models, inspired by advancements in…

A fundamental requirement for real-world robotic deployment is the ability to understand and respond to natural language instructions. Existing language-conditioned manipulation tasks typically assume that instructions are perfectly aligned…

The integration of Vision-Language-Action (VLA) models with World Models has gained increasing attention. One representative approach treats learned World Models as generative simulators, enabling policy optimization entirely within…

Vision-Language-Action (VLA) models trained on large robot datasets promise general-purpose, robust control across diverse domains and embodiments. However, existing approaches often fail out-of-the-box when deployed in novel environments,…

Recent studies have successfully integrated large vision-language models (VLMs) into low-level robotic control by supervised fine-tuning (SFT) with expert robotic datasets, resulting in what we term vision-language-action (VLA) models.…

World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions. However, the reliability of these imagined futures remains under-examined: is a generated future merely visually…

Vision-language-action (VLA) models achieve strong in-distribution performance but degrade sharply under novel camera viewpoints and visual perturbations. We show that this brittleness primarily arises from misalignment in Spatial Modeling,…

Mobile manipulation is the fundamental challenge for robotics to assist humans with diverse tasks and environments in everyday life. However, conventional mobile manipulation approaches often struggle to generalize across different tasks…

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…

Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited…

Vision-language-action models (VLAs) have become increasingly popular in robot manipulation for their end-to-end design and remarkable performance. However, existing VLAs rely heavily on vision-language models (VLMs) that only support…

Vision-Language-Action (VLA) models are driving a revolution in robotics, enabling machines to understand instructions and interact with the physical world. This field is exploding with new models and datasets, making it both exciting and…

Vision-Language-Action (VLA) models frequently encounter challenges in generalizing to real-world environments due to inherent discrepancies between observation and action spaces. Although training data are collected from diverse camera…

Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platforms, as well as their associated power budgets, remain poorly…

We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies. We address the challenge of mapping natural…