DextER
junha-l
Language-conditioned dexterous grasp generation evaluated on instruction and grasp-taxonomy benchmarks.
What you can explore
Explore released training, evaluation and checkpoints for DexGYS and Dexonomy.
Before you use it
The authors corrected contact/pose alignment in a July 2026 data release. Use the corrected version and benchmark-specific evaluation; check model and source-data permissions.
Original contributors
Junha Lee, Eunha Park and Minsu Cho
License / access: Reuse terms not established in the reviewed material; confirm with the original authors
Keep exploring
DexGYS / Grasp as You Say
Dexterous grasp labels paired with language guidance for learning instruction-conditioned grasp generation.
Dexonomy
Contact templates and a grasp taxonomy for synthesizing human-like dexterous grasp configurations.
CEDex
Cross-embodiment dexterous grasping with a human-like contact representation.
Editorial reference · checked 2026-09-22