AI Paper Atlas

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

Towards More Efficient Decoding for Autoregressive Vision-language-action Models

Wenxuan Song, Jiayi Chen, Pengxiang Ding, Yuxin Huang, Han Zhao, Yinchuan Li, Yingcong Chen, Donglin Wang, Haoang Li

ECCV 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
add adaptive early-exit decoding (ablation)CEED-VLA on OpenVLA · LIBERO-Longspeedup (x): 2.5 -> 4.1Improved
add adaptive early-exit decoding (ablation)CEED-VLA on OpenVLA · LIBERO-Longsuccess rate (%): 61.2 -> 62.3No clear effect
add consistency training (ablation)CEED-VLA on OpenVLA · LIBERO-Longspeedup (x): 1.6 -> 2.5Improved
add consistency training to Jacobi plus early-exit (ablation)CEED-VLA on OpenVLA · LIBERO-Longsuccess rate (%): 54.2 -> 62.3Improved
add Jacobi decoding over AR (ablation)CEED-VLA on OpenVLA · LIBERO-Longspeedup (x): 1.0 -> 1.6Improved
add adaptive early-exit to Jacobi decoding (ablation)CEED-VLA · decoding speed (average)tokens/s: 57.57 -> 79.24Improved
use consistency training model with intermediate output at j=12 and 8 (no consistency training) (ablation)LLaVA-VLA · CALVIN ABC->Daverage length: 1.99 and 1.44 vs above 3.34Hurt
increase AR loss weight to 10x (ablation)CEED-VLA LLaVA-VLA · CALVIN ABC->Dspeedup (x): 2.00x -> 1.79xMixed
raise confidence threshold sigma from 0.5 to 0.7 (ablation)CEED-VLA LLaVA-VLA · CALVIN ABC->Dspeedup (x): 2.0x -> 1.3xMixed
lower confidence threshold sigma from 0.5 to 0.4 (ablation)CEED-VLA · Real-worldsuccess rate (%): 77.5 -> 72.5Hurt
increase training trajectories beyond 120k (ablation)CEED-VLA LLaVA-VLA · CALVIN ABC->DspeedupNo clear effect
replace AR with CEED-VLA decodingpi0-FAST · LIBEROdecoding speed (tokens/s): 107.5 -> 420.6Improved

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