# Multi-Modal Multi-Task (M3T) Federated Foundation Models for Embodied AI: Potentials and Challenges for Edge Integration

arXiv: https://arxiv.org/abs/2505.11191 · HTML: https://mlsanity.com/paper/2505.11191/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 11 of 11)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [A Survey of Embodied AI: From Simulators to Research Tasks](https://mlsanity.com/paper/2103.04918/) (2021)
- [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024)
- [RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation](https://mlsanity.com/paper/2306.11706/) (2023)
- [Universal Actions for Enhanced Embodied Foundation Models](https://mlsanity.com/paper/2501.10105/) (2025)
- [Opportunities of Federated Learning in Connected, Cooperative and Automated Industrial Systems](https://mlsanity.com/paper/2101.03367/) (2021)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [ECBench: Can Multi-modal Foundation Models Understand the Egocentric World? A Holistic Embodied Cognition Benchmark](https://mlsanity.com/paper/2501.05031/) (2025)

## Built on by (most cited first, 6 of 6)

- [Sanitizing Manufacturing Dataset Labels Using Vision-Language Models](https://mlsanity.com/paper/2506.23465/) (2025)
- [pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models](https://mlsanity.com/paper/2507.05394/) (2025)
- [Multi-Modal Multi-Task Federated Foundation Models for Next-Generation Extended Reality Systems: Towards Privacy-Preserving Distributed Intelligence in AR/VR/MR](https://mlsanity.com/paper/2506.05683/) (2025)
- [Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges](https://mlsanity.com/paper/2509.07946/) (2025)
- [Vision-Language Models for Infrared Industrial Sensing in Additive Manufacturing Scene Description](https://mlsanity.com/paper/2512.11098/) (2025)
- [BLEND: Balancing Personalization vs. Generalization in Federated Vision-Language Models](https://mlsanity.com/paper/2610.12907/) (2026)

## Abstract (arXiv)

As embodied AI systems become increasingly multi-modal, personalized, and interactive, they must learn effectively from diverse sensory inputs, adapt continually to user preferences, and operate safely under resource and privacy constraints. These challenges expose a pressing need for machine learning models capable of swift, context-aware adaptation while balancing model generalization and personalization. Here, two methods emerge as suitable candidates, each offering parts of these capabilities: multi-modal multi-task foundation models (M3T-FMs) provide a pathway toward generalization across tasks and modalities, whereas federated learning (FL) offers the infrastructure for distributed, privacy-preserving model updates and user-level model personalization. However, when used in isolation, each of these approaches falls short of meeting the complex and diverse capability requirements of real-world embodied AI environments. In this vision paper, we introduce multi-modal multi-task federated foundation models (M3T-FFMs) for embodied AI, a new paradigm that unifies the strengths of M3T-FMs with the privacy-preserving distributed training nature of FL, enabling intelligent systems at the wireless edge. We collect critical deployment dimensions of M3T-FFMs in embodied AI ecosystems under a unified framework, which we name "EMBODY": Embodiment heterogeneity, Modality richness and imbalance, Bandwidth and compute constraints, On-device continual learning, Distributed control and autonomy, and Yielding safety, privacy, and personalization. For each, we identify concrete challenges and envision actionable research directions. We also present an evaluation framework for deploying M3T-FFMs in embodied AI systems, along with the associated trade-offs. Finally, we present a prototype implementation of M3T-FFMs and evaluate their energy and latency performance.