JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917229547749376 |
|---|---|
| author | Capellera, Guillem Ferraz, Luis Rubio, Antonio Alahi, Alexandre Agudo, Antonio |
| author_facet | Capellera, Guillem Ferraz, Luis Rubio, Antonio Alahi, Alexandre Agudo, Antonio |
| contents | Generative models often treat continuous data and discrete events as separate processes, creating a gap in modeling complex systems where they interact synchronously. To bridge this gap, we introduce JointDiff, a novel diffusion framework designed to unify these two processes by simultaneously generating continuous spatio-temporal data and synchronous discrete events. We demonstrate its efficacy in the sports domain by simultaneously modeling multi-agent trajectories and key possession events. This joint modeling is validated with non-controllable generation and two novel controllable generation scenarios: weak-possessor-guidance, which offers flexible semantic control over game dynamics through a simple list of intended ball possessors, and text-guidance, which enables fine-grained, language-driven generation. To enable the conditioning with these guidance signals, we introduce CrossGuid, an effective conditioning operation for multi-agent domains. We also share a new unified sports benchmark enhanced with textual descriptions for soccer and football datasets. JointDiff achieves state-of-the-art performance, demonstrating that joint modeling is crucial for building realistic and controllable generative models for interactive systems. https://guillem-cf.github.io/JointDiff/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22522 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation Capellera, Guillem Ferraz, Luis Rubio, Antonio Alahi, Alexandre Agudo, Antonio Machine Learning Computer Vision and Pattern Recognition Generative models often treat continuous data and discrete events as separate processes, creating a gap in modeling complex systems where they interact synchronously. To bridge this gap, we introduce JointDiff, a novel diffusion framework designed to unify these two processes by simultaneously generating continuous spatio-temporal data and synchronous discrete events. We demonstrate its efficacy in the sports domain by simultaneously modeling multi-agent trajectories and key possession events. This joint modeling is validated with non-controllable generation and two novel controllable generation scenarios: weak-possessor-guidance, which offers flexible semantic control over game dynamics through a simple list of intended ball possessors, and text-guidance, which enables fine-grained, language-driven generation. To enable the conditioning with these guidance signals, we introduce CrossGuid, an effective conditioning operation for multi-agent domains. We also share a new unified sports benchmark enhanced with textual descriptions for soccer and football datasets. JointDiff achieves state-of-the-art performance, demonstrating that joint modeling is crucial for building realistic and controllable generative models for interactive systems. https://guillem-cf.github.io/JointDiff/ |
| title | JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.22522 |