Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of behavior(al) foundation model (BFM) papers, articles, tutorials, slides, and projects
| Date | Stars |
|---|---|
| 2026-07-31 | 297 |
| 2026-08-05 | 301 |
| 2026-08-06 | 301 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome-BFM-Papers
[](https://github.com/yuanmingqi/awesome-bfm-papers) <a href="https://arxiv.org/pdf/2506.20487"><img src="https://img.shields.io/badge/Paper-arXiv-b31b1b" alt="Paper"></a>
A curated list of behavior(al) foundation model (BFM) papers, articles, tutorials, slides, and projects.
# Table of Contents
- [Awesome-BFM-Papers](#awesome-bfm-papers)
- [Table of Contents](#table-of-contents)
- [What is the Behavior Foundation Model?](#what-is-the-behavior-foundation-model)
- [Paper List](#paper-list)
- [Pre-training](#pre-training)
- [Forward-backward Representation Learning](#forward-backward-representation-learning)
- [Goal-conditioned Learning](#goal-conditioned-learning)
- [Intrinsic Reward-driven Learning](#intrinsic-reward-driven-learning)
- [Adaptation](#adaptation)
- [Fine-tuning Techniques](#fine-tuning-techniques)
- [Towards Hierarchical Control](#towards-hierarchical-control)
- [Datasets](#datasets)
- [Cite Us](#cite-us)
# What is the Behavior Foundation Model?
<div align=center>
<br>
<img src='./assets/preface.png' style="width: 90%">
<br>
</div>
A behavior foundation model learns **broad behavior priors** from **large-scale and diverse behavior data**, which can then be conveniently adapted to a wide range of downstream tasks.
# Paper List
An overview of the pre-training pipelines and adaptation strategies for BFMs discussed in this review. The goal-conditioned learning requires an **extrinsic reward** function and large-scale human data, while intrinsic reward-driven learning uses **intrinsic rewards** generated by self-supervised tasks. In contrast, the forward-backward representation learning learns a forward embedding network (FEN) and a backward embedding network (BEN) using **reward-free** transitions, which can then be combined with a specific reward function to infer a policy. For adaptation strategies, BFMs can be fine-tuned through common approaches, such as full fine-tuning (FFT) and low-rank adaptation (LoRA), as well as methods like latent space adaptation, which adjust the policy by modifying the latent task vector. Beyond fine-tuning, adaptation also involves strategies for hierarchical control, where high-level planners (\textit{e.g.}, generative models like LLMs or diffusion models) process abstract goals and generate subtasks for the BFM to execute as a low-level controller, enabling complex and long-horizon task completion.
<div align=center>
<br>
<img src='./assets/taxonomy.png' style="width: 90%">
<br>
</div>
## Pre-training
### Forward-Backward Representation Learning
| 📅Year | 🗃️Archive | 🔤Title | 📜Paper |🖥️Code |
|:-----: |:-----------: |:---------------------------------------------------------------------------------------: |:-----------------------------------------: |:--------: |
| 2025 | **arXiv** | BFM-Zero: Promptable Behavioral Foundation Model for Humanoid Control Using Unsupervised Reinforcement Learning | [Paper](https://arxiv.org/abs/2511.04131) | [Code](https://github.com/LeCAR-Lab/BFM-Zero) |
| 2025 | **ICLR** | Zero-shot Whole-body Humanoid Control via Behavioral Foundation Models | [Paper](https://arxiv.org/abs/2504.11054) | [Code](https://github.com/facebookresearch/metamotivo) |
| 2024 | **arXiv** | Finer Behavioral Foundation Models via Auto-regressive Features and Advantage Weighting | [Paper](https://arxiv.org/abs/2412.04368) | N/A |
| 2024 | **NeurIPS** | Fast Imitation via Behavior Foundation Models | [Paper](https://openreview.net/pdf?id=qnWtw3l0jb) | N/A |
| 2021 | **NeurIPS** | Excerpt of 16,842 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3c58a105052c80ac, desc:curated list