AI Paper Atlas

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

Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling

Hao Li, Shuai Yang, Yilun Chen, Xinyi Chen, Xiaoda Yang, Yang Tian, Hanqing Wang, Tai Wang, Dahua Lin, Feng Zhao, Jiangmiao Pang

AAAI 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 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
feed multiple frames directly into the VLM backbone with discrete action tokens (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 31.0 -> 32.4 (WidowX VM 10.4 -> 4.2; speed 5.18 -> 3.09 Hz)Mixed
replace discrete action tokens with continuous feature prediction and train decoder (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 32.4 -> 48.2; 3.09 -> 8.73 HzImproved
also train the vision-language backbone in multi-frame post-training (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 48.2 -> 67.2Improved
add multi-frame regularization (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 67.2 -> 70.9Improved
add cross-attention in decoder instead of self-attention (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 68.3 -> 70.9Improved
add feature modulator (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 63.5 -> 70.9Improved
use DiT decoder instead of MLP decoder (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 51.8 -> 70.9Improved
use diffusion objective (DiT) instead of flow matching (SiT) (ablation)CronusVLA 7B · SimplerEnv avgsuccess rate (%): 67.6 -> 70.9Improved
increase number of input frames beyond optimum (ablation)CronusVLA · SimplerEnv avgsuccess rate (%)Hurt
multi-frame modeling with CronusVLA vs single-frame modelsCronusVLA 7B · SimplerEnv-OR total avgR-Score: 72.1 -> 86.9 (vs CogACT)Improved

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