# Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation

arXiv: https://arxiv.org/abs/2502.20370 · HTML: https://mlsanity.com/paper/2502.20370/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 52 references that are in the map.
- First posted on arXiv 27 Feb 2025.

## Builds on (most cited first, 30 of 36)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019)
- [MotionGPT: Human Motion as a Foreign Language](https://mlsanity.com/paper/2306.14795/) (2023)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [World-Grounded Human Motion Recovery via Gravity-View Coordinates](https://mlsanity.com/paper/2409.06662/) (2024)
- [Inter-X: Towards Versatile Human-Human Interaction Analysis](https://mlsanity.com/paper/2312.16051/) (2023)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions](https://mlsanity.com/paper/2311.17057/) (2023)
- [Taming Diffusion Probabilistic Models for Character Control](https://mlsanity.com/paper/2404.15121/) (2024)
- [Interactive Character Control with Auto-Regressive Motion Diffusion Models](https://mlsanity.com/paper/2306.00416/) (2023)
- [C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters](https://mlsanity.com/paper/2309.11351/) (2023)
- [ReGenNet: Towards Human Action-Reaction Synthesis](https://mlsanity.com/paper/2403.11882/) (2024)
- [Generating Human Motion in 3D Scenes from Text Descriptions](https://mlsanity.com/paper/2405.07784/) (2024)
- [Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment](https://mlsanity.com/paper/2403.18811/) (2024)
- [Hierarchical Generation of Human-Object Interactions with Diffusion Probabilistic Models](https://mlsanity.com/paper/2310.02242/) (2023)
- [Digital Life Project: Autonomous 3D Characters with Social Intelligence](https://mlsanity.com/paper/2312.04547/) (2023)
- [Interaction Transformer for Human Reaction Generation](https://mlsanity.com/paper/2207.01685/) (2022)
- [Neural Categorical Priors for Physics-Based Character Control](https://mlsanity.com/paper/2308.07200/) (2023)
- [Music-Driven Group Choreography](https://mlsanity.com/paper/2303.12337/) (2023)
- [Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning](https://mlsanity.com/paper/2404.05218/) (2024)

## Built on by (most cited first, 28 of 28)

- [MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space](https://mlsanity.com/paper/2503.15451/) (2025)
- [Absolute Coordinates Make Motion Generation Easy](https://mlsanity.com/paper/2505.19377/) (2025)
- [CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects](https://mlsanity.com/paper/2505.21437/) (2025)
- [ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation](https://mlsanity.com/paper/2607.08741/) (2026)
- [Unified Multi-Modal Interactive & Reactive 3D Motion Generation via Rectified Flow](https://mlsanity.com/paper/2509.24099/) (2025)
- [Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models](https://mlsanity.com/paper/2512.19692/) (2025)
- [InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs](https://mlsanity.com/paper/2512.07410/) (2025)
- [ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning](https://mlsanity.com/paper/2603.13500/) (2026)
- [UMO: Unified In-Context Learning Unlocks Motion Foundation Model Priors](https://mlsanity.com/paper/2603.15975/) (2026)
- [MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation](https://mlsanity.com/paper/2508.16911/) (2025)
- [Diffusion Forcing for Multi-Agent Interaction Sequence Modeling](https://mlsanity.com/paper/2512.17900/) (2025)
- [PolySLGen: Online Multimodal Speaking-Listening Reaction Generation in Polyadic Interaction](https://mlsanity.com/paper/2604.08125/) (2026)
- [MoReact: Generating Reactive Motion from Textual Descriptions](https://mlsanity.com/paper/2509.23911/) (2025)
- [ARMFlow: AutoRegressive MeanFlow for Online 3D Human Reaction Generation](https://mlsanity.com/paper/2512.16234/) (2025)
- [DyaPlex: Full-Duplex Speech-Motion Model for Dyadic Interaction](https://mlsanity.com/paper/2606.03874/) (2026)
- [Social Structure Matters in 3D Human-Human Interaction Generation](https://mlsanity.com/paper/2606.24255/) (2026)
- [Motion In-Betweening for Densely Interacting Characters](https://mlsanity.com/paper/2510.00314/) (2025)
- [ReactionMamba: Generating Short & Long Human Reaction Sequences](https://mlsanity.com/paper/2512.00208/) (2025)
- [Dancing Points: Synthesizing Ballroom Dancing with Three-Point Inputs](https://mlsanity.com/paper/2601.02096/) (2026)
- [Contact Matrix: Enhancing Dance Motion Synthesis with Precise Interaction Modeling](https://mlsanity.com/paper/2605.04662/) (2026)
- [MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations](https://mlsanity.com/paper/2606.27779/) (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)
- [Inter-X++: A Comprehensive Benchmark for Multimodal Human-Human Interaction Analysis](https://mlsanity.com/paper/2608.20312/) (2026)
- [Multi-Modal Controlled Coherent Motion Generation](https://mlsanity.com/paper/2609.11439/) (2026)
- [Generative Interactions: Weaving Multiparty Human Motion with Bilevel Latent Dynamics](https://mlsanity.com/paper/2609.37708/) (2026)
- [Streaming Multi-Track Timeline Control for 3D Human Motion Generation](https://mlsanity.com/paper/2610.03873/) (2026)
- [Sonic-AMG: Streaming Human Motion Generation from Spatial Audio](https://mlsanity.com/paper/2610.13300/) (2026)

## Abstract (arXiv)

This paper addresses the task of generating two-character online interactions. Previously, two main settings existed for two-character interaction generation: (1) generating one's motions based on the counterpart's complete motion sequence, and (2) jointly generating two-character motions based on specific conditions. We argue that these settings fail to model the process of real-life two-character interactions, where humans will react to their counterparts in real time and act as independent individuals. In contrast, we propose an online reaction policy, called Ready-to-React, to generate the next character pose based on past observed motions. Each character has its own reaction policy as its "brain", enabling them to interact like real humans in a streaming manner. Our policy is implemented by incorporating a diffusion head into an auto-regressive model, which can dynamically respond to the counterpart's motions while effectively mitigating the error accumulation throughout the generation process. We conduct comprehensive experiments using the challenging boxing task. Experimental results demonstrate that our method outperforms existing baselines and can generate extended motion sequences. Additionally, we show that our approach can be controlled by sparse signals, making it well-suited for VR and other online interactive environments.