AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving

Yifang Xu, Jiahao Cui, Zhihao Zhu, Hanlin Shang, Shan Luan, Mingwang Xu, Feipeng Cai, Neng Zhang, Yaoyi Li, Jia Cai, Siyu Zhu

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Guidance and alignment for flow matching · 11 citations (OpenAlex)

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 changedWhereMeasuredEffect
use dedicated numerical tokenizer instead of Janus text tokenizer (ablation)WAM-Flow · NAVSIM-v1PDMS: 76.2 -> 81.1Improved
add metric-aligned triplet-margin embeddings (ablation)WAM-Flow · NAVSIM-v1PDMS: 81.1 -> 83.4Improved
add large-scale VQA pretraining (ablation)WAM-Flow · NAVSIM-v1PDMS: 83.4 -> 86.7Improved
add simulator-guided GRPO (after pretraining) (ablation)WAM-Flow · NAVSIM-v1PDMS: 86.7 -> 90.3Improved
add VQA pretraining on top of GRPO (ablation)WAM-Flow · NAVSIM-v1PDMS: 86.9 -> 90.3Improved
increase pretraining data from 0 to 0.65M VQA (ablation)WAM-Flow · NAVSIM-v1PDMS: +1.9 (numerical tokenizer), +5.2 (text tokenizer)Improved
increase pretraining data from 0.65M to 6.5M (ablation)WAM-Flow · NAVSIM-v1PDMS: +1.4 (numerical tokenizer), +2.6 (text tokenizer)Improved
pretrain for 3 epochs versus 0 (ablation)WAM-Flow · NAVSIM-v1PDMS: +3.3Improved
GRPO group size 3 instead of 2 (ablation)WAM-Flow · NAVSIM-v1PDMS: 89.2 -> 90.3Improved
GRPO group size 4 instead of 3 (ablation)WAM-Flow · NAVSIM-v1PDMS: 90.3 -> 89.6Hurt
reward weights favoring TTC (5:20:2) instead of 5:5:2 (ablation)WAM-Flow · NAVSIM-v1PDMS: 90.3 -> 89.7Hurt
reward weights favoring EP (20:5:2) instead of 5:5:2 (ablation)WAM-Flow · NAVSIM-v1PDMS: 90.3 -> 90.0Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy