← Back to all news
arXiv AI By Billy Yan, Isaac Tu, Kelly Lee, Blake Chang, Kenny Ma, Kanad Patel, Dhawal Kabra, Neer Patel, Kevin Wu, Lerrel Pinto, Irmak Guzey

Steertuning Policies from a Few Human Videos

Read the original on arXiv AI →

Steertuning is a system that lets robots learn new tasks in new environments from only five human demonstrations, completing the entire process in under five minutes. It first pre‑trains a 400‑million‑parameter diffusion policy on 100 hours of egocentric human data, then fine‑tunes the model for just 2 minutes using the demonstration most similar to the current environment. The approach achieves a 71 % success rate across 12 tasks in 12 distinct settings, from labs to kitchens, and the authors will release the dataset, model weights, code, and robot videos.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Computer Vision
Sep 28

InternW0-$\Delta$: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data

InternW0-Δ is a unified World Action Model that integrates pretrained visual dynamics, scene semantics, 4D geometry, and motion priors within a Mixture-of-Transformers framework to generate robot actions. It leverages a frozen VLM for semantic guidance, a 4D foundation model for geometric priors, and introduces Causal Imprint to learn future-relevant scene changes without future-video rollout. The model is pretrained on a newly curated 20K‑hour heterogeneous corpus of robot and human demonstrations, achieving superior performance on simulation benchmarks and real‑robot platforms.

By Xingyu Miao, Zizun Li, Baole Fang, Kaiwen Song, Tenghui Wang, Hanxue Zhang, Yating Wang, Xudong Li, Yuping He, Xueyuan Wei, Chao Gao, Xijie Yang, Yingxiang Xu, Kerui Ren, Wenqi Guo, Jianjun Zhou, Xinzhe Wang, Weiguang Zhao, Ni Yang, Zetao Cai, Yufei Xue, Hengjie Li, Zeyu He, Yuanzhen Zhou, Rong Fu, Jianyang Zhang, Siwei Cui, Fuxian Huang, Yunsong Zhou, Xing Gao, Yifei Yao, Qiaojun Yu, Kailin Li, Ming Zhou, Mu Huang, Xinyue Li, Wenze Cui, Bingqi Jiang, Xueyue Zhu, Junting Dong, Haoyu Guo, Tao Lu, Mulin Yu, Bowen Zhou, Bin Zhao, Tianfan Xue, Weinan Zhang, Chunhua Shen
llmsroboticsefficiencymultimodalbenchmarks
More like this →
arXiv AI
Sep 18

HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface

HIL-UMI is a policy-guided Universal Manipulation Interface that enables robot‑free, human‑in‑the‑loop post‑training of vision‑language‑action models. By querying the current policy during handheld demonstrations and using an Energy Score to detect out‑of‑distribution states, it selectively collects new data and refines a progress‑based advantage estimator. The updated estimator then drives advantage‑conditioned behavioral cloning, improving performance on long‑horizon and precise manipulation tasks while reducing per‑frame collection time compared to HG‑DAgger.

By Zimu Han, Yiming Zeng, Jiyao Zhang, Zihao Zhao, Yuanfei Wang, Yixiang Jin, Shiqi Li, Shuangben Chen, Wei Huang, Ruodai Li, Hui Shen, Hao Dong
roboticsfine-tuningmultimodal
More like this →
arXiv AI
Oct 7

Guided Action Flow: Value-Guided Sampling for Frozen Vision-Language-Action Policies

arXiv:2607.02092v4 Announce Type: replace-cross Abstract: Reinforcement learning can improve vision-language-action (VLA) policies beyond supervised fine-tuning, although this typically involves furt...

By Liuhaichen Yang, Zhuang Jiang, Chenchao Sheng, Ningwei Bai, Qichen Yin, Hanbo Ma, Junkai Liu, Junkai Sun, Dongcheng Lyu, Yi Dong, Zezhi Tang
reinforcement-learningroboticsfine-tuningmultimodal
More like this →