Cross-Hand Latent Representation for Vision-Language-Action Models - 2026-03-10 - Research Publication - The authors introduce XL-VLA, a vision-language-action framework integrated with a unified latent action space shared across diverse dex- terous hands. Shown above, an action prediction can be instantiated on the Ability… - source: arxiv.org
TacCompress: A Benchmark for Multi-Point Tactile Data Compression in Dexterous Hand - 2025-05-22 - Research Publication - Keywords Multi-point tactile dataset, tactile data compression ∗Corresponding author. 3 Dataset Collection This section describes the data collection setup and acquisition process for the Dex-MPTD dataset, as illustrated… - source: arxiv.org