Alternatives and similar repositories for MetaVQA

Users that are interested in MetaVQA are comparing it to the libraries listed below

• PJLab-ADG / LeapVAD
  ☆25Updated last year
• Robot-K / Hint-AD
  CoRL2024 | Hint-AD: Holistically Aligned Interpretability for End-to-End Autonomous Driving
  ☆72Updated last year
• OpenDriveLab / ReSim
  [NeurIPS 2025 Spotlight] ReSim: Reliable World Simulation for Autonomous Driving
  ☆138Updated 3 weeks ago
• Robertwyq / Drivingdojo
  [NeurIPS 2024] DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
  ☆83Updated last year
• 6550Zhao / Policy-World-Model
  Official implementation of "From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction"
  ☆56Updated 2 months ago
• XiandaGuo / Drive-MLLM
  [NeurIPS 2025] SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
  ☆78Updated 4 months ago
• OpenDriveLab / Nexus
  [ICCV 2025] Nexus: Decoupled Diffusion Sparks Adaptive Scene Generation
  ☆110Updated 3 weeks ago
• ayesha-ishaq / DriveLMM-o1
  Benchmark and model for step-by-step reasoning in autonomous driving.
  ☆68Updated 10 months ago
• xmed-lab / NuInstruct
  ☆70Updated last year
• sreeramsa / DriveSim
  Simulator designed to generate diverse driving scenarios.
  ☆43Updated 11 months ago
• YanhaoWu / UMGen
  Code for CVPR2025 paper: Generating Multimodal Driving Scenes via Next-Scene Prediction
  ☆100Updated 2 months ago
• YuanJianhao508 / RAG-Driver
  A Multi-Modal Large Language Model with Retrieval-augmented In-context Learning capacity designed for generalisable and explainable end-t…
  ☆120Updated last year
• xiaomi-research / genesis
  [NeurIPS 2025]Genesis: Multimodal Driving Scene Generation with Spatio-Temporal and Cross-Modal Consistency
  ☆75Updated 4 months ago
• wzzheng / Doe
  Doe-1: Closed-Loop Autonomous Driving with Large World Model
  ☆116Updated last year
• IRL-VLA / IRL-VLA
  Official repo for IRL-VLA
  ☆75Updated 5 months ago
• jxbbb / TOD3Cap
  [ECCV 2024] TOD3Cap: Towards 3D Dense Captioning in Outdoor Scenes
  ☆128Updated 10 months ago
• DLUT-LYZ / CODA-LM
  Official PyTorch implementation of CODA-LM(https://arxiv.org/abs/2404.10595)
  ☆99Updated last year
• metadriverse / SimGen
  Simulator-conditioned Driving Scene Generation
  ☆132Updated 9 months ago
• wzzheng / GPD
  GPD-1: Generative Pre-training for Driving
  ☆82Updated last year
• vita-epfl / RAP
  RAP: 3D Rasterization Augmented End-to-End Planning
  ☆119Updated last month
• OpenDriveLab / ETA
  [ICCV 2025] ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models
  ☆38Updated 6 months ago
• fudan-zvg / RealEngine
  ☆43Updated 7 months ago
• LLVM-AD / MAPLM
  [CVPR 2024] MAPLM: A Large-Scale Vision-Language Dataset for Map and Traffic Scene Understanding
  ☆164Updated 2 years ago
• wyddmw / WiseAD
  This is the official implementation of WiseAD.
  ☆26Updated 9 months ago
• happinesslz / DrivePI
  DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning
  ☆76Updated last month
• chaytonmin / Awesome-Papers-World-Models-Autonomous-Driving
  Awesome Papers about World Models in Autonomous Driving
  ☆87Updated last year
• pengxuanyang / WorldRFT
  [AAAI 2026] WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving
  ☆25Updated last month
• Shamdan17 / CarFormer
  The official repository for the ECCV2024 paper "CarFormer: Self-Driving with Learned Object-Centric Representations"
  ☆54Updated last year
• zhangzaibin / AD-H
  ☆15Updated last year
• fudan-zvg / Reason2Drive
  [ECCV 2024] Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving
  ☆98Updated 2 years ago