mlsanityData to 14 Oct 2026

DriveGPT: Scaling Autoregressive Behavior Models for Driving

arXiv 2412.14415 ↗First posted 19 Dec 2024cs.LG cs.AI cs.CVcited by 29

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners

Abstract (arXiv)

We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent states as tokens in an autoregressive fashion. We scale up our model parameters and training data by multiple orders of magnitude, enabling us to explore the scaling properties in terms of dataset size, model parameters, and compute. We evaluate DriveGPT across different scales in a planning task, through both quantitative metrics and qualitative examples, including closed-loop driving in complex real-world scenarios. In a separate prediction task, DriveGPT outperforms state-of-the-art baselines and exhibits improved performance by pretraining on a large-scale dataset, further validating the benefits of data scaling.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 27 of its 38 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

27 of 38 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Scaling Laws for Neural Language Modelscited by 6,586
  4. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  5. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  6. 2021Scaling Vision Transformerscited by 999
  7. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 537
  8. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 530
  9. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  10. 2023Scaling Data-Constrained Language Modelscited by 403
  11. 2020Learning Lane Graph Representations for Motion Forecastingcited by 382
  12. 2022Wayformer: Motion Forecasting via Simple & Efficient Attention Networkscited by 280
15 more
  1. 2022Motion Transformer with Global Intention Localization and Local Movement Refinementcited by 270
  2. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
  3. 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusioncited by 213
  4. 2023MotionLM: Multi-Agent Motion Forecasting as Language Modelingcited by 156
  5. 2023MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Queryingcited by 140
  6. 2022HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encodingcited by 110
  7. 2022M2I: From Factored Marginal Trajectory Prediction to Interactive Predictioncited by 81
  8. 2021Learning to Predict Vehicle Trajectories with Model-based Planningcited by 63
  9. 2024Solving Motion Planning Tasks with a Scalable Generative Modelcited by 40
  10. 2023Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encodingcited by 33
  11. 2023Large Trajectory Models are Scalable Motion Predictors and Plannerscited by 23
  12. 2024ControlMTR: Control-Guided Motion Transformer with Scene-Compliant Intention Points for Feasible Motion Predictioncited by 13
  13. 2021HYPER: Learned Hybrid Trajectory Prediction via Factored Inference and Adaptive Samplingcited by 12
  14. 2023MGTR: Multi-Granular Transformer for Motion Prediction with LiDARcited by 9
  15. 2024Scaling Motion Forecasting Models with Ensemble Distillationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 20.

29 papers.

Sort:

By area:

  1. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 36
  2. 2025Scaling Laws of Motion Forecasting and Planning -- Technical Reportcited by 19
  3. 2025ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Drivingcited by 15
  4. 2026Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Modelscited by 15
  5. 2026DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Drivingcited by 11
  6. 2025Generative AI for Autonomous Driving: Frontiers and Opportunitiescited by 7
  7. 2025ViLaD: A Large Vision Language Diffusion Framework for End-to-End Autonomous Drivingcited by 7
  8. 2026Accelerating Structured Chain-of-Thought in Autonomous Vehiclescited by 6
  9. 2026StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Drivingcited by 6
  10. 2025CoT4AD: A Vision-Language-Action Model with Explicit Chain-of-Thought Reasoning for Autonomous Drivingcited by 5
  11. 2025DAP: A Discrete-token Autoregressive Planner for Autonomous Drivingcited by 4
  12. 2026NaviDriveVLM: Decoupling High-Level Reasoning and Motion Planning for Autonomous Drivingcited by 4
17 more
  1. 2025MADrive: Memory-Augmented Driving Scene Modelingcited by 3
  2. 2026Efficient and Explainable End-to-End Autonomous Driving via Masked Vision-Language-Action Diffusioncited by 2
  3. 2025RDAR: Reward-Driven Agent Relevance Estimation for Autonomous Drivingcited by 1
  4. 2026ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Modelscited by 1
  5. 2026VL-DPO: Vision-Language-Guided Finetuning for Preference-Aligned Autonomous Drivingcited by 1
  6. 2026Motion Planning in Compressed Representation Spacescited by 1
  7. 2026Conditional Flow Matching for Continuous Anomaly Detection in Autonomous Driving on a Manifold-Aware Spectral Spacecited by 0
  8. 2026Toward Unified Multimodal Representation Learning for Autonomous Drivingcited by 0
  9. 2026A Neuro-Symbolic Framework Combining Inductive and Deductive Reasoning for Autonomous Driving Planningcited by 0
  10. 2026Information Coordination as a Bridge: A Neuro-Symbolic Architecture for Reliable Autonomous Driving Scene Understandingcited by 0
  11. 2026STELLAR: Scaling 3D Perception Large Models for Autonomous Drivingcited by 0
  12. 2026CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Drivingcited by 0
  13. 2026Event-Adaptive Motion Planning with Distilled Vision-Language Model in Safety-Critical Situationscited by 0
  14. 2026Towards Metric-Agnostic Trajectory Forecastingcited by 0
  15. 2026Agent-driven Long-tail Simulation for Autonomous Drivingcited by 0
  16. 2026GRAVA: Grounded Reasoning-to-Action Representation and Learning for Autonomous Drivingcited by 0
  17. 2026Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
  2. 2024DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers
  3. 2024Data Scaling Laws for Imitation Learning-Based End-to-End Autonomous Driving
  4. 2022Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving
  5. 2026BranchDrive: A Branch-Structured Dataset for Action-Conditioned Driving Prediction
  6. 2023Scaling Planning for Automated Driving using Simplistic Synthetic Data
  7. 2025Post-Training and Test-Time Scaling of Generative Agent Behavior Models for Interactive Autonomous Driving
  8. 2025DriveGen: Towards Infinite Diverse Traffic Scenarios with Large Models