mlsanityData to 14 Oct 2026

ECTraj: Enhanced Consistency Training for Multi-Agent Trajectory Prediction

arXiv 2605.08572 ↗First posted 9 May 2026cs.CVcited by 0

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Diffusion models for multi-agent trajectory prediction are limited by iterative denoising, which causes inference latency that hinders their use in time-critical settings like autonomous driving. Fast-sampling variants using DDIM and informed initial noise distributions partially alleviate this issue, but they either fail to achieve true single-step generation or are constrained by the chosen noise distribution. Consistency Models (CMs) offer high-quality one-step generation by mapping noise directly to data, but are difficult to train from scratch. We propose ECTraj, an enhanced CM pipeline with improved training and conditional generation for trajectory prediction. Our framework extends the student-teacher consistency training scheme: the student produces standard outputs, while the teacher explicitly fuses its predictions with parts of the ground truth to give stronger supervision. We also exploit CMs' direct denoising for top-K multi-shot generation during training. Combining conditional generation with this enhanced consistency objective yields faster inference and improved prediction accuracy, establishing competitive new benchmarks on the large-scale Argoverse 2 dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 29 of its 37 references that are in the map. First posted on arXiv 9 May 2026.

Builds on

29 of 37 references.

Closest ancestors · 5

Same direction, newest first

  1. 2026Crowd-FM: Learned Optimal Selection of Conditional Flow Matching-generated Trajectories for Crowd Navigation6 Feb
  2. 2025SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictions11 Mar
  3. 2024TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction14 Oct
  4. 2024Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation1 Aug
  5. 2023Leapfrog Diffusion Model for Stochastic Trajectory Prediction20 Mar

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  6. 2023Consistency Modelscited by 1,822
  7. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  8. 2025Mean Flows for One-step Generative Modelingcited by 561
  9. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  10. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 459
  11. 2023Improved Techniques for Training Consistency Modelscited by 439
  12. 2024One Step Diffusion via Shortcut Modelscited by 391
12 more
  1. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  2. 2022Stochastic Trajectory Prediction via Motion Indeterminacy Diffusioncited by 185
  3. 2024Consistency Models Made Easycited by 144
  4. 2023Non-autoregressive Conditional Diffusion Models for Time Series Predictioncited by 78
  5. 2022FJMP: Factorized Joint Multi-Agent Motion Prediction over Learned Directed Acyclic Interaction Graphscited by 41
  6. 2023QCNeXt: A Next-Generation Framework For Joint Multi-Agent Trajectory Predictioncited by 31
  7. 2023Dynamic Scenario Representation Learning for Motion Forecasting with Heterogeneous Graph Convolutional Recurrent Networkscited by 28
  8. 2025Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directionscited by 14
  9. 2024Motion Forecasting in Continuous Drivingcited by 11
  10. 2025DONUT: A Decoder-Only Model for Trajectory Predictioncited by 7
  11. 2024FutureNet-LOF: Joint Trajectory Prediction and Lane Occupancy Field Prediction with Future Context Encodingcited by 6
  12. 2026AGMA: Adaptive Gaussian Mixture Anchors for Prior-Guided Multimodal Human Trajectory Forecastingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Heteroscedastic Diffusion for Multi-Agent Trajectory Modeling
  2. 2024Controllable Diverse Sampling for Diffusion Based Motion Behavior Forecasting
  3. 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling
  4. 2025Predictive Planner for Autonomous Driving with Consistency Models
  5. 2024Intention-aware Denoising Diffusion Model for Trajectory Prediction
  6. 2026Uncertainty-Aware Diffusion Model for Multimodal Highway Trajectory Prediction via DDIM Sampling
  7. 2024ADM: Accelerated Diffusion Model via Estimated Priors for Robust Motion Prediction under Uncertainties
  8. 2026MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction