← Back to all news
Hugging Face Trending Papers

Human Demonstrations as Post-Training Data for Any Robot Body: Retargeting the Object, Not the Hand

Related stories

arXiv Machine Learning
Oct 9

VioLA: Learning Generalist Humanoid Control Policies from Human Data

VioLA is a generalist humanoid control policy that predicts body and hand motion latents instead of joint commands, enabling a pretrained controller to execute these latents on a robot. By aligning human and robot motion in shared latent spaces, the policy can be trained on a large dataset of 140.6 million frames, 93.2% of which are human demonstrations. As a result, VioLA can follow locomotion and manipulation instructions on a real robot zero‑shot, achieving 100% locomotion success and 88.6% manipulation success without task‑specific fine‑tuning.

By Mert Albaba, Jens Bei{\ss}wenger, Anna Manasyan, Daniel Marta, Michael J. Black, Wieland Brendel, Andreas Krause, Georg Martius, Martin Riedmiller
roboticsfine-tuning
More like this →
arXiv AI
Sep 18

Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation

Sim-and-Human Co-training (SimHum) is a method that combines simulation and human demonstration data to train bimanual manipulation policies. It first extracts kinematic priors from simulation and visual priors from human observations, then fine‑tunes on a small real‑robot dataset. With only 80 real‑robot episodes per task, SimHum achieves 62.5% success on out‑of‑distribution scenes across four tabletop tasks, outperforming real‑only training by 53.7% and improving the best single‑source baseline by 35.0% in a matched‑time study.

By Kaipeng Fang, Weiqing Liang, Yuyang Li, Ji Zhang, Pengpeng Zeng, Heng Tao Shen, Jingkuan Song, Lianli Gao
robotics
More like this →
arXiv Machine Learning
Oct 19

Embodiment-Classifier Guidance: Transferring Frozen VLAs Across Robot Dynamics without Demonstrations

The paper introduces Embodiment‑Classifier Guidance, a method that adapts a frozen flow‑based policy π_0 to new robot embodiments without additional demonstrations or parameter updates. By training a lightweight classifier to distinguish successful action chunks between source and target bodies, the policy’s denoising steps are nudged toward the target distribution using the classifier’s gradient. Experiments on the LIBERO simulation benchmark show that this guidance improves average success rates from 72% to 80% across 12 controller–body pairs, reduces failures by 31%, and demonstrates data‑efficient adaptation with only a few target‑body rollouts.

By Devin Han, Hershraj Niranjani
roboticsbenchmarks
More like this →