Related papers: KERV: Kinematic-Rectified Speculative Decoding for…

Vision-Language-Action (VLA) models show promise for robotic control, yet performance in complex household environments remains sub-optimal. Mobile manipulation requires reasoning about global scene layout, fine-grained geometry, and…

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…

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…

Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. However, exploiting offline data with limited visited states will…

Vision-Language-Action (VLA) models extend vision-language models to embodied control by mapping natural-language instructions and visual observations to robot actions. Despite their capabilities, VLA systems face significant challenges due…

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…

Vision-language-action (VLA) models finetuned from vision-language models (VLMs) hold the promise of leveraging rich pretrained representations to build generalist robots across diverse tasks and environments. However, direct fine-tuning on…

Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities. However, their high computational cost and low execution frequency hinder their suitability for real-time tasks such as robotic…

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We introduce DREAM, a novel…

Standard vision-language-action (VLA) models rely on fitting statistical data priors, limiting their robust understanding of underlying physical dynamics. Reinforcement learning enhances physical grounding through exploration yet typically…

Classical pixel-based Visual Servoing (VS) approaches offer high accuracy but suffer from a limited convergence area due to optimization nonlinearity. Modern deep learning-based VS methods overcome traditional vision issues but lack…

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for robotic manipulation. However, existing post-training methods face a dilemma between stability and exploration: Supervised Fine-Tuning (SFT) is constrained by…

Vision-and-Language Navigation (VLN) requires agents to interpret natural language instructions and act coherently in visually rich environments. However, most existing methods rely on reactive state-action mappings without explicitly…

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…

While Vision-Language-Action (VLA) models show strong promise for generalist robot control, it remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics, where training data is…

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…

Transformer-based models have driven significant advancements in Multimodal Large Language Models (MLLMs), yet their computational costs surge drastically when scaling resolution, training data, and model parameters. A key bottleneck stems…

Vision-Language-Action (VLA) models exhibit strong generalization in robotic manipulation, yet reinforcement learning (RL) fine-tuning often degrades robustness under spatial distribution shifts. For flow-matching VLA policies, this…

This paper proposes a novel approach to address the challenge that pretrained VLA models often fail to effectively improve performance and reduce adaptation costs during standard supervised finetuning (SFT). Some advanced finetuning methods…