# EP-Diffuser: An Efficient Diffusion Model for Traffic Scene Generation and Prediction via Polynomial Representations

arXiv: https://arxiv.org/abs/2504.05422 · HTML: https://mlsanity.com/paper/2504.05422/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 31 of its 50 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks](https://mlsanity.com/paper/1803.10892/) (2018)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [CoverNet: Multimodal Behavior Prediction using Trajectory Sets](https://mlsanity.com/paper/1911.10298/) (2019)
- [MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion](https://mlsanity.com/paper/2306.03083/) (2023)
- [Understanding and Mitigating Copying in Diffusion Models](https://mlsanity.com/paper/2305.20086/) (2023)
- [MotionLM: Multi-Agent Motion Forecasting as Language Modeling](https://mlsanity.com/paper/2309.16534/) (2023)
- [Leapfrog Diffusion Model for Stochastic Trajectory Prediction](https://mlsanity.com/paper/2303.10895/) (2023)
- [The Waymo Open Sim Agents Challenge](https://mlsanity.com/paper/2305.12032/) (2023)
- [Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders](https://mlsanity.com/paper/2308.09882/) (2023)
- [DSDNet: Deep Structured self-Driving Network](https://mlsanity.com/paper/2008.06041/) (2020)
- [UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction](https://mlsanity.com/paper/2403.15098/) (2024)
- [DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling](https://mlsanity.com/paper/1911.12736/) (2019)
- [JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving](https://mlsanity.com/paper/2212.08710/) (2022)
- [QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Prediction](https://mlsanity.com/paper/2306.10508/) (2023)
- [Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections](https://mlsanity.com/paper/1901.05105/) (2019)
- [Interactive multi-modal motion planning with Branch Model Predictive Control](https://mlsanity.com/paper/2109.05128/) (2021)
- [Self-Driving like a Human driver instead of a Robocar: Personalized comfortable driving experience for autonomous vehicles](https://mlsanity.com/paper/2001.03908/) (2020)
- [DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction](https://mlsanity.com/paper/2310.14570/) (2023)
- [Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation](https://mlsanity.com/paper/2408.00766/) (2024)
- [Behaviorally Diverse Traffic Simulation via Reinforcement Learning](https://mlsanity.com/paper/2011.05741/) (2020)
- [RACP: Risk-Aware Contingency Planning with Multi-Modal Predictions](https://mlsanity.com/paper/2402.17387/) (2024)
- [Improving Out-of-Distribution Generalization of Trajectory Prediction for Autonomous Driving via Polynomial Representations](https://mlsanity.com/paper/2407.13431/) (2024)
- [GAMMA: A General Agent Motion Model for Autonomous Driving](https://mlsanity.com/paper/1906.01566/) (2019)
- [An Empirical Bayes Analysis of Object Trajectory Representation Models](https://mlsanity.com/paper/2211.01696/) (2022)
- [Annealed Winner-Takes-All for Motion Forecasting](https://mlsanity.com/paper/2409.11172/) (2024)

## Built on by (most cited first, 1 of 1)

- [ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving](https://mlsanity.com/paper/2606.14058/) (2026)

## Abstract (arXiv)

As the prediction horizon increases, predicting the future evolution of traffic scenes becomes increasingly difficult due to the multi-modal nature of agent motion. Most state-of-the-art (SotA) prediction models primarily focus on forecasting the most likely future. However, for the safe operation of autonomous vehicles, it is equally important to cover the distribution for plausible motion alternatives. To address this, we introduce EP-Diffuser, a novel parameter-efficient diffusion-based generative model designed to capture the distribution of possible traffic scene evolutions. Conditioned on road layout and agent history, our model acts as a predictor and generates diverse, plausible scene continuations. We benchmark EP-Diffuser against two SotA models in terms of accuracy and plausibility of predictions on the Argoverse 2 dataset. Despite its significantly smaller model size, our approach achieves both highly accurate and plausible traffic scene predictions. We further evaluate model generalization ability in an out-of-distribution (OoD) test setting using Waymo Open dataset and show superior robustness of our approach. The code and model checkpoints are available at: https://github.com/continental/EP-Diffuser.