Related papers: DynVLA: Learning World Dynamics for Action Reasoni…
Achieving generalizable manipulation in unconstrained environments requires the robot to proactively resolve information uncertainty, i.e., the capability of active perception. However, existing methods are often confined in limited types…
The intrinsic dynamics of an object governs its physical behavior in the real world, playing a critical role in enabling physically plausible interactive simulation with 3D assets. Existing methods have attempted to infer the intrinsic…
Vision-Language-Action (VLA) models have demonstrated significant advantages in robotic manipulation. However, their reliance on vision and language often leads to suboptimal performance in tasks involving visual occlusion, fine-grained…
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-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requiring precise spatial reasoning due to limited spatial…
Visual-language reasoning, driving knowledge, and value alignment are essential for advanced autonomous driving systems. However, existing approaches largely rely on data-driven learning, making it difficult to capture the complex logic…
Data-driven learning has advanced autonomous driving, yet task-specific models struggle with out-of-distribution scenarios due to their narrow optimization objectives and reliance on costly annotated data. We present DriveX, a…
Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicate this success in visual tasks. Some works attempt to extend this approach to autonomous…
Driving in a complex urban environment is a difficult task that requires a complex decision policy. In order to make informed decisions, one needs to gain an understanding of the long-range context and the importance of other vehicles. In…
We propose LCLA (Language-Conditioned Latent Alignment), a framework for vision-language navigation that learns modular perception-action interfaces by aligning sensory observations to a latent representation of an expert policy. The expert…
Vision-Language-Action (VLA) models aim for general robot learning by aligning action as a modality within powerful Vision-Language Models (VLMs). Existing VLAs rely on end-to-end supervision to implicitly enable the action decoding process…
Vision-Language-Action (VLA) models are dominant in embodied intelligence but are constrained by inference overheads. While model quantization alleviates these bottlenecks for edge deployment, static quantization approaches remain…
Mobile robots are increasingly required to navigate and interact within unknown and unstructured environments to meet human demands. Demand-driven navigation (DDN) enables robots to identify and locate objects based on implicit human…
Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned…
End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language…
Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception, suboptimal multimodal fusion, and instability in reinforcement learning. To bridge…
In this study, we address the problem of language-guided robotic manipulation, where a robot is required to manipulate a wide range of objects based on visual observations and natural language instructions. This task is essential for…
Vision-language pre-training (VLP) has recently proven highly effective for various uni- and multi-modal downstream applications. However, most existing end-to-end VLP methods use high-resolution image-text box data to perform well on…
We learn an interactive vision-based driving policy from pre-recorded driving logs via a model-based approach. A forward model of the world supervises a driving policy that predicts the outcome of any potential driving trajectory. To…
With the rapid advancement of large language models (LLMs) and vision-language models (VLMs), significant progress has been made in developing open-vocabulary robotic manipulation systems. However, many existing approaches overlook the…