Research map / Label-efficient and robust learning / Recognition and long-tail
WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarios
Runsheng Xu, Hubert Lin, Wonseok Jeon, Hao Feng, Yuliang Zou, Liting Sun, John Gorman, Kate Tolstaya, Sarah Tang, Brandyn White, Ben Sapp, Mingxing Tan and 2 more
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add finetuning on WOD-E2E long-tail training data (ablation) | NaiveEMMA (Gemini Flash) · WOD-E2E internal test split | RFS: 7.14 -> 7.22 | Improved |
| add multi-camera inputs (ablation) | NaiveEMMA (Gemini Flash) · WOD-E2E internal test split | RFS: 7.22 -> 7.30 | Improved |
| add test-time scaling (multi sampling) (ablation) | NaiveEMMA (Gemini Flash) · WOD-E2E internal test split | RFS: 7.30 -> 7.39 | Improved |
| add RL post-training with RFS as reward (Poutine) | Qwen2.5 3B MLLM planner · WOD-E2E leaderboard (test) | RFS: HMVLM (SFT) 7.736 -> Poutine (SFT+RL, RFS reward) 7.986 | Improved |
| use ADE as RL reward (AutoVLA) instead of RFS | Qwen2.5 3B MLLM planner · WOD-E2E leaderboard (test) | RFS: 7.556 (AutoVLA) vs baseline 7.528 | No clear effect |
| add supplementary datasets with large distribution gap to MLLM-based planners | Poutine, AutoVLA · WOD-E2E leaderboard (test) | RFS | Improved |
| add supplementary datasets with large distribution gap to diffusion planners | UniPlan, DiffusionLTF · WOD-E2E leaderboard (test) | RFS | No clear effect |
| lower ADE across leaderboard submissions | E2E driving methods · WOD-E2E leaderboard (test) | RFS: HMVLM RFS 7.736 with ADE 3.071; Swin-Trajectory RFS 7.543 with ADE 2.814 | Mixed |
Closest papers by meaning
- Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving (NeurIPS 2024 · similarity 0.87)
- WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving (ICML 2025 · similarity 0.85)
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation (CVPR 2025 · similarity 0.85)
- DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model (NeurIPS 2024 · similarity 0.84)
- DriveHierarchy: A Benchmark for Diagnosing VLM Driving Capabilities from Open-Loop Understanding to Closed-Loop Execution (NeurIPS 2026 · similarity 0.84)
- DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
