# Text2Interact: High-Fidelity and Diverse Text-to-Two-Person Interaction Generation

arXiv: https://arxiv.org/abs/2510.06504 · HTML: https://mlsanity.com/paper/2510.06504/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 49 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [MotionCLIP: Exposing Human Motion Generation to CLIP Space](https://mlsanity.com/paper/2203.08063/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model](https://mlsanity.com/paper/2304.01116/) (2023)
- [Language2Pose: Natural Language Grounded Pose Forecasting](https://mlsanity.com/paper/1907.01108/) (2019)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [Guided Motion Diffusion for Controllable Human Motion Synthesis](https://mlsanity.com/paper/2305.12577/) (2023)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras](https://mlsanity.com/paper/2112.01524/) (2021)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [Text2Action: Generative Adversarial Synthesis from Language to Action](https://mlsanity.com/paper/1710.05298/) (2017)
- [TLControl: Trajectory and Language Control for Human Motion Synthesis](https://mlsanity.com/paper/2311.17135/) (2023)
- [EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation](https://mlsanity.com/paper/2312.02256/) (2023)
- [CoMo: Controllable Motion Generation through Language Guided Pose Code Editing](https://mlsanity.com/paper/2403.13900/) (2024)
- [C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters](https://mlsanity.com/paper/2309.11351/) (2023)
- [ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model](https://mlsanity.com/paper/2412.14559/) (2024)
- [InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling](https://mlsanity.com/paper/2410.10010/) (2024)
- [Digital Life Project: Autonomous 3D Characters with Social Intelligence](https://mlsanity.com/paper/2312.04547/) (2023)

## Built on by (most cited first, 11 of 11)

- [EgoReAct: Egocentric Video-Driven 3D Human Reaction Generation](https://mlsanity.com/paper/2512.22808/) (2025)
- [InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs](https://mlsanity.com/paper/2512.07410/) (2025)
- [UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors](https://mlsanity.com/paper/2603.15975/) (2026)
- [Next-Scale Autoregressive Models for Text-to-Motion Generation](https://mlsanity.com/paper/2604.03799/) (2026)
- [HumanCLAW: Can Vision-Language Models Act Through a Body?](https://mlsanity.com/paper/2607.27180/) (2026)
- [Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation](https://mlsanity.com/paper/2604.20336/) (2026)
- [MoSAT: Human Motion Generation from Spatial Audio and Textual Description](https://mlsanity.com/paper/2609.23797/) (2026)
- [Unified Number-Free Text-to-Motion Generation Via Flow Matching](https://mlsanity.com/paper/2603.27040/) (2026)
- [InterCMDM: Block-Causal Diffusion for Autoregressive Human Interaction Generation](https://mlsanity.com/paper/2607.01743/) (2026)
- [ARMS: Anchor-Relational Motion Streaming for Seamless Solo-Social Motion Transitions](https://mlsanity.com/paper/2607.05733/) (2026)
- [COSMI: COmpositional Synthesis of Multi-object Interactions](https://mlsanity.com/paper/2610.03252/) (2026)

## Abstract (arXiv)

Modeling human-human interactions from text remains challenging because it requires not only realistic individual dynamics but also precise, text-consistent spatiotemporal coupling between agents. Currently, progress is hindered by 1) limited two-person training data, inadequate to capture the diverse intricacies of two-person interactions; and 2) insufficiently fine-grained text-to-interaction modeling, where language conditioning collapses rich, structured prompts into a single sentence embedding. To address these limitations, we propose our Text2Interact framework, designed to generate realistic, text-aligned human-human interactions through a scalable high-fidelity interaction data synthesizer and an effective spatiotemporal coordination pipeline. First, we present InterCompose, a scalable synthesis-by-composition pipeline that aligns LLM-generated interaction descriptions with strong single-person motion priors. Given a prompt and a motion for an agent, InterCompose retrieves candidate single-person motions, trains a conditional reaction generator for another agent, and uses a neural motion evaluator to filter weak or misaligned samples-expanding interaction coverage without extra capture. Second, we propose InterActor, a text-to-interaction model with word-level conditioning that preserves token-level cues (initiation, response, contact ordering) and an adaptive interaction loss that emphasizes contextually relevant inter-person joint pairs, improving coupling and physical plausibility for fine-grained interaction modeling. Extensive experiments show consistent gains in motion diversity, fidelity, and generalization, including out-of-distribution scenarios and user studies. We will release code and models to facilitate reproducibility.