AI Paper Atlas

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

Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance

Wenxuan Song, Jiayi Chen, Shuai Chen, Jingbo Wang, Pengxiang Ding, Han Zhao, qin yikai, Xinhu Zheng, Yan Wang, Donglin Wang, Haoang Li

ECCV 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 10 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 block size as multiple of action dimensionality instead of random (ablation)Fast-dVLA (Dream-VLA) · LIBERO-Longsuccess rate: 73.3% -> 74.7%Improved
use block size as multiple of action dimensionality instead of random (ablation)Fast-dVLA (Dream-VLA) · LIBERO-Longspeedup: 3.95x -> 4.01xImproved
lower confidence threshold tau_conf to 0.5 (ablation)Fast-dVLA · LIBEROsuccess rate and speed: 2.8x acceleration, 2% dropMixed
distill asymmetrically from finetuned weight instead of training from scratch (ablation)Fast-dVLA (Dream-VLA) · LIBEROtraining steps: 2,000 steps, 1/10 of scratchImproved
raise tau_add and tau_act from 0.4/0.4 to 0.6/0.8 (ablation)Fast-dVLA (UD-VLA) · CALVIN ABCD->Davg length / speed: 4.42 -> 4.57 length, 253.1 -> 160.7 tokens/sMixed
use dual-state thresholds tau_add 0.5, tau_act 0.7 instead of equal 0.5/0.5 (ablation)Fast-dVLA (UD-VLA) · CALVIN ABCD->Davg length: 4.44 -> 4.54Improved
use more conservative radical decoding log4 instead of log2 (ablation)Fast-dVLA (UD-VLA) · CALVIN ABCD->Dspeed: 186.67 -> 144.71 tokens/sHurt
use log4 instead of log2 radical decoding (ablation)Fast-dVLA (UD-VLA) · CALVIN ABCD->Davg length: 4.54 -> 4.58No clear effect
apply Fast-dLLM KV reuse to Dream-VLADream-VLA · LIBEROsuccess rate: 0.856 -> 0.828Hurt
apply Fast-dVLA to Dream-VLADream-VLA · LIBEROspeed: 98.8 -> 313.1 tokens/sImproved
apply Fast-dVLA to DD-VLADiscrete Diffusion VLA · LIBEROspeed: 152.1 -> 402.7 tokens/sImproved
apply Fast-dVLA to UD-VLAUD-VLA · CALVIN ABCD->Davg length: 4.64 -> 4.54Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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