mlsanityData to 14 Oct 2026

DriveCode: Domain Specific Numerical Encoding for LLM-Based Autonomous Driving

arXiv 2603.00919 ↗First posted 1 Mar 2026cs.CV cs.ROcited by 0

On the map: End-to-end autonomous driving → Large language models for driving

Abstract (arXiv)

Large language models (LLMs) have shown great promise for autonomous driving. However, discretizing numbers into tokens limits precise numerical reasoning, fails to reflect the positional significance of digits in the training objective, and makes it difficult to achieve both decoding efficiency and numerical precision. These limitations affect both the processing of sensor measurements and the generation of precise control commands, creating a fundamental barrier for deploying LLM-based autonomous driving systems. In this paper, we introduce DriveCode, a novel numerical encoding method that represents numbers as dedicated embeddings rather than discrete text tokens. DriveCode employs a number projector to map numbers into the language model's hidden space, enabling seamless integration with visual and textual features in a unified multimodal sequence. Evaluated on OmniDrive, DriveGPT4, and DriveGPT4-V2 datasets, DriveCode demonstrates superior performance in trajectory prediction and control signal generation, confirming its effectiveness for LLM-based autonomous driving systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Large language models for driving, one of 9 directions in End-to-end autonomous driving. Builds on 40 of its 51 references that are in the map. First posted on arXiv 1 Mar 2026.

Builds on

40 of 51 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023LMDrive: Closed-Loop End-to-End Driving with Large Language Models12 Dec
  2. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model2 Oct

Other references · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2023Visual Instruction Tuningcited by 7,869
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  6. 2023Video-LLaVA: Learning United Visual Representation by Alignment Before Projectioncited by 1,402
  7. 2022Planning-oriented Autonomous Drivingcited by 1,087
  8. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 622
  9. 2024TinyLlama: An Open-Source Small Language Modelcited by 618
  10. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 467
  11. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 289
  12. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 260
26 more
  1. 2023VTimeLLM: Empower LLM to Grasp Video Momentscited by 255
  2. 2024Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Drivingcited by 252
  3. 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Tokencited by 166
  4. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 150
  5. 2023Teaching Arithmetic to Small Transformerscited by 123
  6. 2023Recent Advancements in End-to-End Autonomous Driving using Deep Learning: A Surveycited by 103
  7. 2023Hidden Biases of End-to-End Driving Modelscited by 96
  8. 2023ADAPT: Action-aware Driving Caption Transformercited by 78
  9. 2023Positional Description Matters for Transformers Arithmeticcited by 56
  10. 2025Omni-R1: Do You Really Need Audio to Fine-Tune Your Audio LLM?cited by 46
  11. 2024LC-LLM: Explainable Lane-Change Intention and Trajectory Predictions with Large Language Modelscited by 35
  12. 2024NumeroLogic: Number Encoding for Enhanced LLMs' Numerical Reasoningcited by 31
  13. 2025Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Reportcited by 31
  14. 2025LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuningcited by 28
  15. 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Modelscited by 23
  16. 2024Language Models Encode the Value of Numbers Linearlycited by 20
  17. 2024Surveying the MLLM Landscape: A Meta-Review of Current Surveyscited by 20
  18. 2023InsMapper: Exploring Inner-instance Information for Vectorized HD Mappingcited by 19
  19. 2024The Geometry of Numerical Reasoning: Language Models Compare Numeric Properties in Linear Subspacescited by 10
  20. 2024Interleaving Text and Number Embeddings to Solve Mathemathics Problemscited by 5
  21. 2025Exploring Finetuned Audio-LLM on Heart Murmur Featurescited by 5
  22. 2025Number Representations in LLMs: A Computational Parallel to Human Perceptioncited by 4
  23. 2025Pre-trained Language Models Learn Remarkably Accurate Representations of Numberscited by 4
  24. 2025Language Models Do Not Embed Numbers Continuouslycited by 4
  25. 2025InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformercited by 1
  26. 2025sam-llm: interpretable lane change trajectoryprediction via parametric finetuningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving
  2. 2024Generalizing End-To-End Autonomous Driving In Real-World Environments Using Zero-Shot LLMs
  3. 2023LLM4Drive: A Survey of Large Language Models for Autonomous Driving
  4. 2023DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
  5. 2024Large Language Models for Human-like Autonomous Driving: A Survey
  6. 2026Orion-Lite: Distilling LLM Reasoning into Efficient Vision-Only Driving Models
  7. 2024XLM for Autonomous Driving Systems: A Comprehensive Review
  8. 2023A Survey on Multimodal Large Language Models for Autonomous Driving