erl-hub/behaviour1k-Qwen3-DINOv3 download history

erl-hub/behaviour1k-Qwen3-DINOv3 is a robotics dataset on the Hugging Face Hub. In the last 30 days it was downloaded 36 times (5 in the last 7 days), and 207 times in total. It ranks #237,825 among datasets by monthly downloads.

PLS-VLA skill features Per-frame conditioned features e_t = Phi(f_t, L_sub^(j), L), mean-pooled skill latents S_j, aligned proprioception q_t, actions a_t, and subtask progress p_t. DINOv3 visual features V(f_t) are also included. Training inputs/targets for the Primitive Skill Compos

Open erl-hub/behaviour1k-Qwen3-DINOv3 on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.