# Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy

arXiv: https://arxiv.org/abs/2503.18349 · HTML: https://mlsanity.com/paper/2503.18349/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 69 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## Builds on (most cited first, 30 of 52)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [Object Motion Guided Human Motion Synthesis](https://mlsanity.com/paper/2309.16237/) (2023)
- [Stochastic Scene-Aware Motion Prediction](https://mlsanity.com/paper/2108.08284/) (2021)
- [HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes](https://mlsanity.com/paper/2210.09729/) (2022)
- [CG-HOI: Contact-Guided 3D Human-Object Interaction Generation](https://mlsanity.com/paper/2311.16097/) (2023)
- [Scaling Up Dynamic Human-Scene Interaction Modeling](https://mlsanity.com/paper/2403.08629/) (2024)
- [Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes](https://mlsanity.com/paper/2012.05522/) (2020)
- [COUCH: Towards Controllable Human-Chair Interactions](https://mlsanity.com/paper/2205.00541/) (2022)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [Synthesizing Diverse Human Motions in 3D Indoor Scenes](https://mlsanity.com/paper/2305.12411/) (2023)
- [Controllable Human-Object Interaction Synthesis](https://mlsanity.com/paper/2312.03913/) (2023)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [Synthesizing Physical Character-Scene Interactions](https://mlsanity.com/paper/2302.00883/) (2023)
- [Unified Human-Scene Interaction via Prompted Chain-of-Contacts](https://mlsanity.com/paper/2309.07918/) (2023)
- [HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models](https://mlsanity.com/paper/2312.06553/) (2023)
- [Towards Diverse and Natural Scene-aware 3D Human Motion Synthesis](https://mlsanity.com/paper/2205.13001/) (2022)
- [From Motor Control to Team Play in Simulated Humanoid Football](https://mlsanity.com/paper/2105.12196/) (2021)
- [DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control](https://mlsanity.com/paper/2410.05260/) (2024)
- [Compositional Human-Scene Interaction Synthesis with Semantic Control](https://mlsanity.com/paper/2207.12824/) (2022)
- [Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance](https://mlsanity.com/paper/2403.18036/) (2024)

## Built on by (most cited first, 12 of 12)

- [Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis](https://mlsanity.com/paper/2508.02106/) (2025)
- [OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model](https://mlsanity.com/paper/2505.18947/) (2025)
- [InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2602.06035/) (2026)
- [UniHM: Unified Dexterous Hand Manipulation with Vision Language Model](https://mlsanity.com/paper/2603.00732/) (2026)
- [WorldAgents: Can Foundation Image Models be Agents for 3D World Models?](https://mlsanity.com/paper/2603.19708/) (2026)
- [DiscoForcing: A Unified Framework for Real-Time Audio-Driven Character Control with Diffusion Forcing](https://mlsanity.com/paper/2605.28491/) (2026)
- [Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models](https://mlsanity.com/paper/2605.19663/) (2026)
- [Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics](https://mlsanity.com/paper/2606.22806/) (2026)
- [PhotoHOI: Synthesizing 3D Hand-Object Interactions from a Single RGB Photograph](https://mlsanity.com/paper/2608.01905/) (2026)
- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)
- [InterEvolve: Test-Time Evolution of Reward Programs for Humanoid Loco-Manipulation](https://mlsanity.com/paper/2610.02196/) (2026)
- [Scalable Multi-Human Cooperative Manipulation via Commander-Executor Coordination](https://mlsanity.com/paper/2610.14911/) (2026)

## Abstract (arXiv)

Human-object interaction (HOI) synthesis is crucial for applications in animation, simulation, and robotics. However, existing approaches either rely on expensive motion capture data or require manual reward engineering, limiting their scalability and generalizability. In this work, we introduce the first unified physics-based HOI framework that leverages Vision-Language Models (VLMs) to enable long-horizon interactions with diverse object types, including static, dynamic, and articulated objects. We introduce VLM-Guided Relative Movement Dynamics (RMD), a fine-grained spatio-temporal bipartite representation that automatically constructs goal states and reward functions for reinforcement learning. By encoding structured relationships between human and object parts, RMD enables VLMs to generate semantically grounded, interaction-aware motion guidance without manual reward tuning. To support our methodology, we present Interplay, a novel dataset with thousands of long-horizon static and dynamic interaction plans. Extensive experiments demonstrate that our framework outperforms existing methods in synthesizing natural, human-like motions across both simple single-task and complex multi-task scenarios. For more details, please refer to our project webpage: https://vlm-rmd.github.io/.