# FMimic: Foundation Models are Fine-grained Action Learners from Human Videos

arXiv: https://arxiv.org/abs/2507.20622 · HTML: https://mlsanity.com/paper/2507.20622/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Robot manipulation imitation learning, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 28 Jul 2025.

## Placed in

- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Built on by (most cited first, 3 of 3)

- [ConLA: Contrastive Latent Action Learning from Human Videos for Robotic Manipulation](https://mlsanity.com/paper/2602.00557/) (2026)
- [See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations](https://mlsanity.com/paper/2512.07582/) (2025)
- [Long-Horizon Visual Imitation Learning via Plan and Code Reflection](https://mlsanity.com/paper/2509.05368/) (2025)

## Abstract (arXiv)

Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in foundation models, particularly Vision Language Models (VLMs), have demonstrated remarkable capabilities in visual and linguistic reasoning for VIL tasks. Despite this progress, existing approaches primarily utilize these models for learning high-level plans from human demonstrations, relying on pre-defined motion primitives for executing physical interactions, which remains a major bottleneck for robotic systems. In this work, we present FMimic, a novel paradigm that harnesses foundation models to directly learn generalizable skills at even fine-grained action levels, using only a limited number of human videos. Extensive experiments demonstrate that our FMimic delivers strong performance with a single human video, and significantly outperforms all other methods with five videos. Furthermore, our method exhibits significant improvements of over 39% and 29% in RLBench multi-task experiments and real-world manipulation tasks, respectively, and exceeds baselines by more than 34% in high-precision tasks and 47% in long-horizon tasks.