Related papers: LCLA: Language-Conditioned Latent Alignment for Vi…

We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates…

Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally aligned reasoning and…

Latent Action Models (LAMs) enable Vision- Language-Action (VLA) systems to learn semantic action representations from large-scale unannotated data. Yet, we identify two bottlenecks of LAMs: 1) the commonly adopted end-to-end trained image…

This paper proposes to solve the problem of Vision-and-Language Navigation with legged robots, which not only provides a flexible way for humans to command but also allows the robot to navigate through more challenging and cluttered scenes.…

Visual navigation policy is widely regarded as a promising direction, as it mimics humans by using egocentric visual observations for navigation. However, optical information of visual observations is difficult to be explicitly modeled like…

Vision-language-action (VLA) models provide a powerful approach to training control policies for physical systems, such as robots, by combining end-to-end learning with transfer of semantic knowledge from web-scale vision-language model…

While Vision-Language-Action (VLA) models have revolutionized autonomous driving by unifying perception and planning, their reliance on explicit textual Chain-of-Thought (CoT) leads to semantic-perceptual decoupling and perceptual-symbolic…

Pretraining Vision-Language-Action (VLA) policies on internet-scale video is appealing, yet current latent-action objectives often learn the wrong thing: they remain anchored to pixel variation rather than action-relevant state transitions,…

The capability of performing long-horizon, language-guided robotic manipulation tasks critically relies on leveraging historical information and generating coherent action sequences. However, such capabilities are often overlooked by…

Vision-Language-Action (VLA) models benefit from chain-of-thought (CoT) reasoning, but existing approaches incur high inference overhead and rely on discrete reasoning representations that mismatch continuous perception and control. We…

Vision-language-action models (VLAs) have shown generalization capabilities in robotic manipulation tasks by inheriting from vision-language models (VLMs) and learning action generation. Most VLA models focus on interpreting vision and…

Latent Action Models (LAMs) enable the learning of world models from unlabeled video by inferring abstract actions between consecutive frames. However, LAMs face a fundamental trade-off between action abstraction and generation fidelity.…

Driver visual attention prediction is a critical task in autonomous driving and human-computer interaction (HCI) research. Most prior studies focus on estimating attention allocation at a single moment in time, typically using static RGB…

Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where…

We investigate the Vision-and-Language Navigation (VLN) problem in the context of autonomous driving in outdoor settings. We solve the problem by explicitly grounding the navigable regions corresponding to the textual command. At each…

Recent Vision-Language-Action (VLA) models built on pre-trained Vision-Language Models (VLMs) require extensive post-training, resulting in high computational overhead that limits scalability and deployment.We propose CogVLA, a…

We consider the problem of Vision-and-Language Navigation (VLN). The majority of current methods for VLN are trained end-to-end using either unstructured memory such as LSTM, or using cross-modal attention over the egocentric observations…

Vision-Language-Action (VLA) models have shown remarkable achievements, driven by the rich implicit knowledge of their vision-language components. However, achieving generalist robotic agents demands precise grounding into physical…

Recent vision-language-action (VLA) models have significantly advanced robotic manipulation by unifying perception, reasoning, and control. To achieve such integration, recent studies adopt a predictive paradigm that models future visual…

Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to control signals. This "black-box" mapping forces a single forward pass to simultaneously handle instruction interpretation,…