Related papers: FASTer: Toward Efficient Autoregressive Vision Lan…

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 have emerged as a popular paradigm for learning robot manipulation policies that can follow language instructions and generalize to novel scenarios. Recent works have begun to explore the incorporation of…

Current Vision-Language-Action (VLA) models primarily focus on mapping 2D observations to actions, but exhibit notable limitations in spatiotemporal perception and reasoning: 1) spatial representations often rely on additional sensors,…

Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…

Recent advances in vision-language-action (VLA) models have motivated the extension of their capabilities to embodied settings, where reinforcement learning (RL) offers a principled way to optimize task success through interaction. However,…

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…

Developing robust and general-purpose manipulation policies represents a fundamental objective in robotics research. While Vision-Language-Action (VLA) models have demonstrated promising capabilities for end-to-end robot control, existing…

Vision-Language-Action models have demonstrated remarkable capabilities in predicting agent movements within virtual environments and real-world scenarios based on visual observations and textual instructions. Although recent research has…

Despite advances in Vision-Language-Action (VLA) models, robotic manipulation struggles with fine-grained tasks because current models lack mechanisms for active visual attention allocation. Human gaze naturally encodes intent, planning,…

In this paper, we introduce a novel kinematics-rich vision-language-action (VLA) task, in which language commands densely encode diverse kinematic attributes (such as direction, trajectory, orientation, and relative displacement) from…

Over the past few years, vision transformers (ViTs) have consistently demonstrated remarkable performance across various visual recognition tasks. However, attempts to enhance their robustness have yielded limited success, mainly focusing…

Trustworthy robot behavior requires not only high levels of task success but also that the robot can reliably quantify how likely it is to succeed. To this end, we present a first-of-its-kind study of confidence calibration in…

Vision-Language-Action (VLA) models convert high-level language instructions into concrete, executable actions, a task that is especially challenging in open-world environments. We present Visual Foresight Planning (ForeAct), a general and…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

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…

Recent advances in robot manipulation have leveraged pre-trained vision-language models (VLMs) and explored integrating 3D spatial signals into these models for effective action prediction, giving rise to the promising…

Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation. However,…

Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration…

Human vision is a highly active process driven by gaze, which directs attention to task-relevant regions through foveation, dramatically reducing visual processing. In contrast, robot learning systems typically rely on passive, uniform…

Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop,…