# Grounding Multimodal Large Language Models in Actions

arXiv: https://arxiv.org/abs/2406.07904 · HTML: https://mlsanity.com/paper/2406.07904/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 58 of its 69 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 58)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [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)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality](https://mlsanity.com/paper/2304.14178/) (2023)
- [Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic](https://mlsanity.com/paper/2306.15195/) (2023)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks](https://mlsanity.com/paper/2112.03227/) (2021)
- [Otter: A Multi-Modal Model with In-Context Instruction Tuning](https://mlsanity.com/paper/2305.03726/) (2023)

## Built on by (most cited first, 30 of 35)

- [UniVLA: Learning to Act Anywhere with Task-centric Latent Actions](https://mlsanity.com/paper/2505.06111/) (2025)
- [Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation](https://mlsanity.com/paper/2410.08001/) (2024)
- [Pure Vision Language Action (VLA) Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.19012/) (2025)
- [From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons](https://mlsanity.com/paper/2412.08442/) (2024)
- [A Survey of Embodied Learning for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2408.11537/) (2024)
- [BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning](https://mlsanity.com/paper/2506.06072/) (2025)
- [From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities](https://mlsanity.com/paper/2412.11694/) (2024)
- [Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning](https://mlsanity.com/paper/2504.00907/) (2025)
- [VipAct: Visual-Perception Enhancement via Specialized VLM Agent Collaboration and Tool-use](https://mlsanity.com/paper/2410.16400/) (2024)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [Guiding Audio Editing with Audio Language Model](https://mlsanity.com/paper/2509.21625/) (2025)
- [On the Modeling Capabilities of Large Language Models for Sequential Decision Making](https://mlsanity.com/paper/2410.05656/) (2024)
- [Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision](https://mlsanity.com/paper/2410.08209/) (2024)
- [QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning](https://mlsanity.com/paper/2412.15576/) (2024)
- [When Continue Learning Meets Multimodal Large Language Model: A Survey](https://mlsanity.com/paper/2503.01887/) (2025)
- [Expanding LLM Agent Boundaries with Strategy-Guided Exploration](https://mlsanity.com/paper/2603.02045/) (2026)
- [MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization](https://mlsanity.com/paper/2511.19878/) (2025)
- [RoboAgent: Chaining Basic Capabilities for Embodied Task Planning](https://mlsanity.com/paper/2604.07774/) (2026)
- [AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models](https://mlsanity.com/paper/2506.09082/) (2025)
- [PhysiAgent: An Embodied Agent Framework in Physical World](https://mlsanity.com/paper/2509.24524/) (2025)
- [Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents](https://mlsanity.com/paper/2502.01218/) (2025)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models](https://mlsanity.com/paper/2605.04678/) (2026)
- [Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents](https://mlsanity.com/paper/2605.12620/) (2026)
- [TSPE: Task-Specific Prompt Ensemble for Improved Zero-Shot Audio Classification](https://mlsanity.com/paper/2501.00398/) (2024)
- [Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets](https://mlsanity.com/paper/2601.09605/) (2026)
- [The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data](https://mlsanity.com/paper/2412.06877/) (2024)
- [Boosting Robotic Manipulation Generalization with Minimal Costly Data](https://mlsanity.com/paper/2503.19516/) (2025)
- [Embodied AI in Machine Learning -- is it Really Embodied?](https://mlsanity.com/paper/2505.10705/) (2025)
- [From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning](https://mlsanity.com/paper/2512.24532/) (2025)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have demonstrated a wide range of capabilities across many domains, including Embodied AI. In this work, we study how to best ground a MLLM into different embodiments and their associated action spaces, with the goal of leveraging the multimodal world knowledge of the MLLM. We first generalize a number of methods through a unified architecture and the lens of action space adaptors. For continuous actions, we show that a learned tokenization allows for sufficient modeling precision, yielding the best performance on downstream tasks. For discrete actions, we demonstrate that semantically aligning these actions with the native output token space of the MLLM leads to the strongest performance. We arrive at these lessons via a thorough study of seven action space adapters on five different environments, encompassing over 114 embodied tasks.