AI Paper Atlas

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

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving

Shuyao Shang, Bing Zhan, Yunfei Yan, Yuqi Wang, Yingyan Li, Yasong An, Xiaoman Wang, Jierui Liu, Lu Hou, Lue Fan, Zhaoxiang Zhang, Tieniu Tan

ICML 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 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 Dynamics CoT instead of textual scene description CoT (ablation)DynVLA (EMU3) · NAVSIMPDMS: 85.3 -> 87.2Improved
add Dynamics CoT SFT (ablation)EMU3 baseline · NAVSIMPDMS: 85.6 -> 87.2Improved
add RFT on top of Dynamics CoT SFT (ablation)DynVLA (EMU3) · NAVSIMPDMS: 87.2 -> 91.7Improved
apply RFT to baseline without CoT (ablation)EMU3 baseline · NAVSIMPDMS: 85.6 -> 88.7Improved
use Dynamics CoT with Qwen2.5-VL base instead of no CoT (ablation)Qwen2.5-VL · NAVSIMPDMS: 85.3 -> 86.6 (SFT), 91.0 (SFT+RFT)Improved
decouple ego-centric and environment-centric dynamics with ego action regularization (ablation)Dynamics Tokenizer · NAVSIMPDMS: 86.2 -> 87.2Improved
decoupling dynamics to avoid codebook collapse (ablation)Dynamics Tokenizer · VQ code usage during tokenizer trainingactivated VQ codesImproved
add BEV branch (cross-view consistency) alongside image branch (ablation)Dynamics Tokenizer · NAVSIMPDMS: 86.7 -> 87.2Improved
add image branch alongside BEV branch (ablation)Dynamics Tokenizer · NAVSIMPDMS: 86.2 -> 87.2Improved
extend prediction horizon from K=2 to K=3 (ablation)Dynamics CoT · NAVSIMPDMS: 87.2 -> 86.7Hurt
extend prediction horizon from K=1 to K=2 (ablation)Dynamics CoT · NAVSIMPDMS: 86.5 -> 87.2Improved
increase dynamics tokens from 8 to 16 (ablation)Dynamics Tokenizer · NAVSIMPDMS: 87.2 -> 86.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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