AI Paper Atlas

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

Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving

Bo Jiang, Shaoyu Chen, Bencheng Liao, Xingyu Zhang, Wei Hong Yin, Qian Zhang, Chang Huang, Wenyu Liu, Xinggang Wang

IJCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 196 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 meta-action planning QA to training (ablation)Senna · DriveX valplanning accuracy (%): 52.67 -> 71.21Improved
add scene description QA to training (ablation)Senna · DriveX valplanning accuracy (%): 53.65 -> 71.21Improved
add traffic light QA to training (ablation)Senna · DriveX valplanning accuracy (%): 57.39 -> 71.21Improved
add planning explanation QA to training (ablation)Senna · DriveX valplanning accuracy (%): 67.91 -> 71.21Improved
add VRU identification QA to training (ablation)Senna · DriveX valplanning accuracy (%): 68.44 -> 71.21Improved
add motion intention prediction QA to training (ablation)Senna · DriveX valplanning accuracy (%): 68.70 -> 71.21Improved
use surround-view multi-image input instead of front view only (ablation)Senna · DriveX valplanning accuracy (%): 64.91 -> 71.21Improved
compress each image to 128 tokens instead of the original 576 (ablation)Senna · DriveX valplanning accuracy (%): 0.00 -> 71.21Improved
reduce image tokens from 128 to 64 or 32 per image (ablation)Senna · DriveX valplanning accuracy (%): 71.21 -> 70.42 -> 69.36No clear effect
scale training data from 100k to 800k clips (ablation)Senna · DriveX valplanning accuracy (%): 57.45 -> 71.21Improved
use mix pre-training with driving fine-tuning and planning fine-tuning (ablation)Senna · DriveX valplanning accuracy (%): 60.01 -> 71.21Improved
predict meta-actions with LVLM instead of low-frequency trajectories as connectorSenna vs DriveVLM · DriveX valL2 error at 3s (m): 3.00 -> 2.62Improved

Later papers that compared with this method

1 later accepted paper reports Senna-2-3B as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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