Research map / Multi-agent systems and games / Human-AI and goal-conditioned

FlowMoP: Stochastic Multi-Person Motion Prediction

NeurIPS 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes FlowMoP, a conditional flow matching framework for stochastic multi-person 3D motion prediction that generates diverse plausible future motions instead of deterministic outputs.

Problem

Multi-person 3D motion prediction is inherently stochastic, but the dominant paradigm is deterministic, producing a fixed number of outputs per agent.

Approach

Uses conditional flow matching to jointly model multiple agents' future motions as a distribution over plausible continuations conditioned on observed history, rather than a fixed set of deterministic predictions.

Closest papers by meaning

• MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation (CVPR 2025 · similarity 0.89)
• Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning (CVPR 2024 · similarity 0.88)
• Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports (ICLR 2025 · similarity 0.87)
• Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction (NeurIPS 2024 · similarity 0.86)
• Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling (CVPR 2025 · similarity 0.86)
• MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction (NeurIPS 2026 · similarity 0.85)