AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Bird's-eye-view Informed Reasoning Driver

Yinuo Wang, Mining Tan, Yuanxin Zhong, Wang zhitao, Siyuan Cheng

ICLR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Embodied multimodal LLM agents

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
add Spatial Localization dataset (ablation)BIRDriver VLM (Qwen2.5VL-3B) · Test14-hard clipsx-error: 4.17m -> 3.76m (x), 1.28m -> 1.08m (y), 4.20° -> 3.80° (phi)Improved
add Driving Scene Stepwise dataset (ablation)BIRDriver VLM (Qwen2.5VL-3B) · Test14-hard clipsx-error: 4.27m -> 4.17m (x), 1.35m -> 1.28m (y), 4.23° -> 4.20° (phi)Improved
use full composite dataset vs KeyPoint only (ablation)BIRDriver VLM (Qwen2.5VL-3B) · Test14-hard clipskey point error: reduced by 11.9%, 20.0%, and 10.2%Improved
add weighted SFT loss (ablation)BIRDriver VLM (Qwen2.5VL-3B) · Test14-hard clipskey point error: 4.22m -> 3.76m (x), 1.19m -> 1.08m (y), 4.13° -> 3.80° (phi)Improved
use RDP key points instead of final trajectory point only (ablation)BIRDriver (InternVL2.5-4B) · InterPlanCLS-R: 34.72 -> 53.81Improved
scale VLM from InternVL2.5-2B to 4B (ablation)BIRDriver VLM · Key point errorx-error: 6.59m -> 3.71m (x), 2.79m -> 1.44m (y), 11.20° -> 4.89° (phi)Improved
scale VLM from Qwen2.5VL-3B to 7B (ablation)BIRDriver VLM · Key point errorx-error: 3.76m -> 3.60m (x), 1.08m -> 1.08m (y), 3.80° -> 3.83° (phi)No clear effect
add VLM key point guidance to PLUTOPLUTO · Test14-hardCLS-NR / CLS-R: 80.03 -> 80.56 (CLS-NR), 76.92 -> 80.33 (CLS-R)Improved
add VLM key point guidance to PLUTOPLUTO · InterPlanCLS-R: 48.92 -> 55.29Improved
add VLM key point guidance to PLUTOPLUTO · Test14-randomCLS-NR: 91.87 -> 91.46Hurt
add VLM key point guidance to PLUTOPLUTO · Test14-randomCLS-R: 90.03 -> 91.26Improved

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