Related papers: DepthCache: Depth-Guided Training-Free Visual Toke…

Vision-language-action (VLA) models show potential for general robotic tasks, but remain challenging in spatiotemporally coherent manipulation, which requires fine-grained representations. Typically, existing methods embed 3D positions into…

Leveraging diverse robotic data for pretraining remains a critical challenge. Existing methods typically model the dataset's action distribution using simple observations as inputs. However, these inputs are often incomplete, resulting in a…

The rapid evolution of Embodied AI has enabled Vision-Language-Action (VLA) models to excel in multimodal perception and task execution. However, applying Reinforcement Learning (RL) to these massive models in large-scale distributed…

Vision-Language-Action (VLA) models have rapidly advanced embodied intelligence, enabling robots to execute complex, instruction-driven tasks. However, as model capacity and visual context length grow, the inference cost of VLA systems…

Scaling Vision-Language-Action (VLA) models requires massive datasets that are both semantically coherent and physically feasible. However, existing scene generation methods often lack context-awareness, making it difficult to synthesize…

Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been…

Despite remarkable progress in Vision--Language--Action (VLA) models, a central bottleneck remains underexamined: the data infrastructure that underlies embodied learning. In this survey, we argue that future advances in VLA will depend…

Vision-Language-Action (VLA) models have achieved significant breakthroughs by leveraging Large Vision Language Models (VLMs) to jointly interpret instructions and visual inputs. However, the substantial increase in visual tokens,…

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading…

Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and…

As a fundamental backbone for video generation, diffusion models are challenged by low inference speed due to the sequential nature of denoising. Previous methods speed up the models by caching and reusing model outputs at uniformly…

Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLAC, a general process reward model built upon InternVL and…

Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks. However, their substantial parameter sizes and high inference latency pose significant…

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic…

Robotic manipulation in 3D requires effective computation of N degree-of-freedom joint-space trajectories that enable precise and robust control. To achieve this, robots must integrate semantic understanding with visual perception to…

Vision-Language-Action (VLA) models exhibit unprecedented capabilities for embodied intelligence. However, their extensive computational and memory costs hinder their practical deployment. Existing VLA compression and acceleration…

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by…

Vision-Language-Action (VLA) models have demonstrated strong performance in robotic manipulation, yet their closed-loop deployment is hindered by the high latency and compute cost of repeatedly running large vision-language backbones at…

Since current Vision-Language-Action (VLA) systems suffer from limited spatial perception and the absence of memory throughout manipulation, we investigate visual anchors as a means to enhance spatial and temporal reasoning within VLA…