Vision-Language-Action (VLA) models
PulseAugur coverage of Vision-Language-Action (VLA) models — every cluster mentioning Vision-Language-Action (VLA) models across labs, papers, and developer communities, ranked by signal.
5 天有情绪数据
-
New RAW-Dream paradigm enables zero-shot VLA model adaptation
研究人员引入了RAW-Dream，一种无需任务特定数据即可适应视觉-语言-动作（VLA）模型的新范式。该方法利用预训练的、与任务无关的世界模型来预测未来轨迹，并利用现成的视觉-语言模型（VLM）来生成奖励。通过将世界模型学习与下游任务分离，RAW-Dream实现了VLA的零样本适应，实验表明在模拟和现实世界场景中均取得了性能提升。
-
Driving AI models show reasoning fragility under sensor perturbations
A new research paper titled "Lost in Fog" investigates the reasoning fragility of Vision-Language-Action (VLA) models in autonomous driving. The study subjected the Alpamayo R1 model to various sensor perturbations, inc…
-
HandITL method improves robotic hand manipulation via seamless intervention
Researchers have developed a new method called Hand-in-the-Loop (HandITL) to improve the performance of Vision-Language-Action (VLA) models in complex robotic manipulation tasks. This technique addresses the issue of "g…
-
RAW-Dream enables zero-shot VLA adaptation via task-agnostic world models
Researchers have introduced RAW-Dream, a novel approach to adapt Vision-Language-Action (VLA) models for new tasks using reinforcement learning within task-agnostic world models. This method disentangles world model lea…
-
DreamAvoid framework prevents VLA model failures in robotics
Researchers have developed DreamAvoid, a novel framework designed to prevent failures in Vision-Language-Action (VLA) models during critical manipulation tasks. The system uses a "dreaming" process at test time to antic…
-
Robotic VLAs learn from past successes with new adaptation method
Researchers have developed a new framework called Retrieve-then-Steer to improve the reliability of Vision-Language-Action (VLA) models in robotic manipulation tasks. This method allows a partially competent, frozen VLA…