AI Paper Atlas

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

Teaching Vision-Language-Action Models What to See and Where to Look

Yuguang Yang, Canyu Chen, Zhewen Tan, Yizhi Wang, Zichao Feng, Chunyang Liu, Kehua Sheng, Bo Zhang, Yan Wang, Juan Zhang, Linlin Yang, Baochang Zhang and 1 more

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 1 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
add DVD pretraining in place of VQA pretraining (ablation)Qwen2.5-VL-3B planner with CoT · NAVSIM navtestPDMS: 86.4 -> 87.1Improved
add 2D-TGP guidance (ablation)DVD + CoT planner · NAVSIM navtestPDMS: 87.1 -> 88.2Improved
add GRPO after TGP-guided CoT SFT (ablation)DriveTeach-VLA · NAVSIM navtestPDMS: 88.2 -> 90.4Improved
add 2D-TGP when GRPO is used (ablation)DVD + CoT + GRPO planner · NAVSIM navtestPDMS: 89.1 -> 90.4Improved
use block-wise (2x4) distillation instead of patch-by-patch (ablation)DVD TGP-Prompter · NAVSIM navtestPDMS: 86.5 -> 87.6Improved
use 4x7 blocks instead of 2x4 (ablation)DVD TGP-Prompter · NAVSIM navtestPDMS: 87.6 -> 87.1Hurt
add DVD pretraining to the TGP-Prompter (ablation)TGP-Prompter · NAVSIM navtestPDMS: 86.2 -> 87.6Improved
vary lambda_TGP from 0.05 to 0.10 (ablation)DVD pretraining · NAVSIM navtestPDMS: 86.3 -> 87.6Improved
raise lambda_TGP from 0.10 to 0.15 (ablation)DVD pretraining · NAVSIM navtestPDMS: 87.6 -> 87.4Hurt
drop 40% of bboxes in DVD distillation (ablation)DVD TGP-Prompter · NAVSIM navtestPDMS: 87.6 -> 85.3Hurt
jitter 20% of bbox corners in DVD (ablation)DVD TGP-Prompter · NAVSIM navtestPDMS: 87.6 -> 87.1Mixed
replace dual models with a single multi-turn QA model (ablation)Prompter-Planner · NAVSIM navtestPDMS: 88.2 -> 87.0Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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