Tag: vision-language-action
Browse our exclusive articles!
CF-VLA: Fast Coarse-to-Fine Action Generation for VLA Policies
Discover CF-VLA, an efficient coarse-to-fine method boosting real-time vision-language-action policies with faster, high-quality action generation.
Optimizing Vision-Language-Action Models for On-Robot XPUs
Discover how Vision-Language-Action models can be accelerated on XPUs for cost-effective, real-time robot deployment with improved energy efficiency.
Vision-Language-Action in Robotics: Key Datasets & Benchmarks
Explore the latest survey on Vision-Language-Action in robotics, covering datasets, benchmarks, and data engines driving embodied learning advancements.
HELM: Advanced Memory for Long-Horizon Vision-Language Tasks
Discover HELM, a framework boosting long-horizon vision-language-action tasks with enhanced memory, verification, and recovery for improved manipulation su...
vla-eval: Efficient Evaluation for Vision-Language-Action Models
vla-eval streamlines Vision-Language-Action model evaluation with automated benchmarks, faster processing, and a comprehensive leaderboard.