A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

Kaidong Zhang; Jian Zhang; Rongtao Xu; Yu Sun; Shuoshuo Xue; Youpeng Wen; Xiaoyu Guo; Minghao Guo

cs.ROApr 7, 2026

A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model

Authors: Kaidong Zhang, Jian Zhang, Rongtao Xu, Yu Sun, Shuoshuo Xue, Youpeng Wen, Xiaoyu Guo, Minghao Guo, +15 more

Organizations: SYSU · Spatialtemporal AI · MBZUAI

Abstract

Vision-Language-Action (VLA) models have emerged as a powerful paradigm for open-world robot manipulation, but their practical deployment is often constrained by cost: billion-scale VLM backbones and iterative diffusion/flow-based action heads incur high latency and compute, making real-time control expensive on commodity hardware. We present A1, a fully open-source and transparent VLA framework designed for low-cost, high-throughput inference without sacrificing manipulation success; Our approach leverages pretrained VLMs that provide implicit affordance priors for action generation. We release the full training stack (training code, data/data-processing pipeline, intermediate checkpoints, and evaluation scripts) to enable end-to-end reproducibility. Beyond optimizing the VLM alone, A1 targets the full inference pipeline by introducing a budget-aware adaptive inference scheme that jointly accelerates the backbone and the action head. Specifically, we monitor action consistency across intermediate VLM layers to trigger early termination, and propose Inter-Layer Truncated Flow Matching that warm-starts denoising across layers, enabling accurate actions with substantially fewer effective denoising iterations. Across simulation benchmarks (LIBERO, VLABench) and real robots (Franka, AgiBot), A1 achieves state-of-the-art success rates while significantly reducing inference cost (e.g., up to 72% lower per-episode latency for flow-matching inference and up to 76.6% backbone computation reduction with minor performance degradation). On RoboChallenge, A1 achieves an average success rate of 29.00%, outperforming baselines including pi0(28.33%), X-VLA (21.33%), and RDT-1B (15.00%).

Figures & tables

Figure 1: Overview of $A_{1}$ . $A_{1}$ comprises a Vision Language Model (VLM) backbone and an action head, where the VLM provides semantically rich and affordance-aware representations for downstream action prediction. We instantiate the latter in two forms: a flow-matching head and an MLP head. To reduce end-to-end inference latency, we introduce a budget-aware acceleration scheme that is compatible with both action-head designs and jointly reduces backbone computation and action-head iterations. Extensive experiments in simulators, on real hardware, and on RoboChallenge demonstrate that $A_{1}$ achieves strong manipulation performance with substantially improved efficiency.

Figure 2: Training and adaptive inference of

A_{1}

. During training, for each layer

i

of VLM, the shared action head generates actions

A_{t}^{(i)}

. For flow matching, the model is executed with the same number of layers

i

to generate predictions. All actions are supervised simultaneously. At inference time, we adaptively activate an appropriate size of VLM based on an exit criterion

c

. The threshold

\eta_{i}

is generated by training set and

c

. When the VLM reaches the

i

-th layer, we computes the discrepancy between the current actions and those from the previous layer, and determines whether to terminate via

\eta_{i}

. We propose Inter-Layer Truncated Flow Matching to accelerate early-exit inference.

Model	LIBERO					VLABench
	Spatial	Object	Goal	Long	Avg.	Toy	Fruit	Painting	Mahjong	Avg.
Octo ( 34 )	78.9	85.7	84.6	51.1	75.1	0	0	6	0	1.5
OpenVLA ( 18 )	84.7	88.4	79.2	53.7	76.5	4	6	40	8	14.5
OpenVLA-OFT ( 17 )	97.6	98.4	97.9	$\mathbf{94.5}$	$\mathbf{97.1}$	-	-	-	-	-
CoT-VLA ( 59 )	87.5	91.6	87.6	69.0	81.1	-	-	-	-	-
MolmoAct ( 20 )	87.0	95.4	87.6	77.2	86.6	-	-	-	-	-

Table 1: Experimental Results of Simulation Benchmarks (%).

Figure 3: Demonstrations show the execution process of $A_{1}$ (second row) and baselines $\pi_{0.5}$ (first row).

Model

UR5

Franka

AgiBot

OpenArm

Dobot-Arm

Mean

stack

arrange

put cup

arrange

fruits

move

pick

clean

tidy

select

cook

pour

blocks

fruits

on coaster

fruits

(small)

objects

glue

table

yellow

vegetable

water

\pi_{0}

( 2 )

\mathbf{100}

\mathbf{70}

\mathbf{80}

\mathbf{40}

40.8

\pi_{0.5}

( 14 )

\mathbf{100}

\mathbf{80}

\mathbf{20}

47.5

A_{1}

\mathbf{100}

\mathbf{40}

\mathbf{50}

\mathbf{80}

\mathbf{80}

\mathbf{20}

\mathbf{80}

\mathbf{20}

\mathbf{56.7}

Table 2: Experimental Results of Real-World Evaluation (%) across Multiple Robot Platforms.

	CLIP	LLM ( $L$ =28)	FM ( $\delta$ =10)	$A_{1}$ -FM ( $\delta$ =10)	$A_{1}$ -FM e ( $\delta$ =10)	$A_{1}$ -FM e ( $\delta$ =2)
Time (s)	0.167	0.612	0.366	1.151	4.443	0.728
GFLOPS	2013.36	9061.01	4.93	11130.30	11503.30	11160.20

Table 3: Computation cost and latency of different parts of the model.

A_{1}

-FM e denotes adaptive early-exit reaching the final layer, where we set

K

=14 to evaluate the exit criterion (Eq. (6)) every two layers.

Figure 4: Example of adaptive inference visualization for the $A_{1}$ model with the exit criterion $c=0.6$ . A successful execution episode from the LIBERO-Long task (instruction: turn on the stove and put the moka pot on it ). Green numbers indicate the layer indices where the $A_{1}$ model exits (the model has 28 layers in total). At each frame, the model outputs actions for the next 8 time steps (action chunk = 8).

Model	Arrange	Hang	Set	Shred	Sort	Stack	Move	Press	Arrange	Arrange
	Fruits	Cup	Plates	Paper	Books	Blocks	Objects	Buttons	Flowers	Cups
DM0 ( 46 )	100	80	100	30	20	100	100	90	70	30
Spirit-v1.5 ( 35 )	80	80	80	20	0	80	80	90	50	0
GigaBrain ( 33 )	60	40	90	0	0	100	90	40	40	80
$\pi_{0.5}$ ( 14 )	40	50	80	0	0	100	50	0	50	0
wall-oss ( 51 )	80	60	50	0	0	100	60	100	20	0

Table 4: Comparison with state-of-the-art open-source VLA models on Table30 benchmark in RoboChallenge. List in success rate. Bold for highest. § Denotes fully open-source models with complete training stack, weights, and data pipelines.

Config	Spatial	Object	Goal	Long	Avg.	TFLOPs	Inf. time
no exit †	98.3	99.3	97.0	88.3	95.8	243.0	17.5
no exit ‡	97.4	100.0	97.4	91.0	96.5	243.0	17.5
c=1.0	97.4	99.8	97.6	91.4	96.6	205.0 (15.6%↓)	20.6 ↑
c=0.7	98.4	99.8	97.4	89.6	96.3	148.1 (39.1%↓)	16.5 ↓
c=0.4	95.6	98.4	95.0	87.0	94.0	100.8 (58.5%↓)	6.8 ↓
c=0.1	96.2	98.2	94.4	80.4	92.3	57.0 (76.6%↓)	5.6 ↓

Table 5: Adaptive early-exit inference with

A_{1}

-MLP. Average accuracy, per-episode computation cost (TFLOPs) and model inference time (second) under different exit criteria

c

on the LIBERO benchmark. † Full-layer training. ‡ Multi-exit training.

$c$ , $\delta$	Spatial	Object	Goal	Long	Avg.	TFLOPs	Inf. time
no exit † , 10	97.2	99.2	94.6	79.2	92.6	231.3	37.9
no exit ‡ , 10	97.4	99.2	96.2	91.2	96.0	229.8	37.8
no exit ‡ , 2	97.4	98.6	96.8	89.6	95.6	226.9	32.2
1.0, 10	97.2	99.6	97.0	91.8	96.4	150.6 ↓	40.9 (7.9%↑)
1.0, 2	94.6	99.0	98.0	90.0	95.4	167.9 ↓	27.5 (27.4%↓)
1.0, 2 ∗	95.4	99.0	97.8	93.2	96.4	156.8 ↓	10.5 (72.3%↓)

Table 6: Adaptive early-exit inference with

A_{1}

-FM. Accuracy, per-episode computation cost (TFLOPs) and model inference time (second) under different exit criteria

c

and denoising steps

\delta

on the LIBERO benchmark. ∗ Layer

i+1

denoising initialized with layer

i

output (Eq. ( 10 )). † Full-layer training. ‡ Multi-exit training.

Method	Spatial	Object	Goal	Long	Avg.	TFLOPs	Inf. time (s)
OpenVLA	19.4	14.0	15.1	14.3	15.6	-	-
OpenVLA-OFT	84.0	66.5	63.0	66.4	69.6	-	-
$\pi_{0}$	60.7	61.4	44.9	48.4	53.6	-	-
$\pi_{0}$ -FAST	74.4	72.7	57.5	43.4	61.6	-	-
$A_{1}$ -FM	86.6	80.0	66.8	58.0	75.3	297.1	36.1

Table 7: Zero-shot results on LIBERO-Plus benchmark.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 5: The $A_{1}$ is deployed on our self-developed dual-arm platform OpenArm.

Configuration	Value
Optimizer	AdamW
Batch size	1024
Total training steps	200K
Learning Rates
ViT backbone	$0$ (frozen)
VLM components	$5\times 10^{-6}$

Appendix

Table 8: Hyperparameters for pretraining

A_{1}

Task / Benchmark	Batch Size	Training Steps	State Mask Prob
LIBERO	128	50K	$0.0$
VLABench	64	50K	$0.0$
RoboChallenge (Aloha)	64	100K	$0.3$
RoboChallenge (ARX5)	32	50K	$0.3$
RoboChallenge (UR5)	64	50K	$0.3$
RoboChallenge (Franka)	64	50K	$0.3$

Appendix

Table 9: Fine-tuning hyperparameters for A1 on downstream tasks. All tasks use AdamW optimizer, ViT frozen (LR=

0

), VLM LR=

5\times 10^{-6}

, Action Head LR=

5\times 10^{-5}

, and visual augmentation (Erasing, Sharpening). The state mask probability is set to

0.5

for all fine-tuning tasks unless otherwise specified.

Config	Metric	Pick glue
no exit †	accuracy	80
c=1.0	accuracy compute↓	70 ↓49.3
c=0.8	accuracy compute↓	70 ↓64.7
c=0.4	accuracy compute↓	80 ↓84.6

Appendix

Table 10: Real-world experiments of adaptive early-exit inference based on AgiBot. Average accuracy and computation reduction ratio (compute↓) under different exit criterion c for model

A_{1}

-FM with

\delta

=2. † Full-layer training.

Figure 6: AgiBot real-world example execution process of $A_{1}$ -FM for early-exit inference with the exit criterion $c=0.4$ . Green numbers indicate the layer indices where the $A_{1}$ model exits (the model has 28 layers in total). Task: Pick up the glue and put it into the pen holder.

Explore similar work

VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting
Jul 7, 2025Juyi Lin, Amir Taherin, Arash Akbari +11Robotic Control Efficient VLA Model Inference
Northeastern University, Boston, USA · EmbodyX,San Mateo,USA
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
Jul 29, 2026Hengyi Xie, Chenfei Yao, Xianjin Wu +4Efficient VLA Model Inference Efficient VLA Models
Huazhong University of Science and Technology
Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference
Jul 14, 2026Yuzhou Wu, Yuxin Zheng, Muchun Niu +6Efficient VLA Model Inference Efficient VLA Models
1Tianji KernalMind co ltd · 2Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · 3Shanghai Jiao Tong University, Shanghai, China +2

Jul 7, 2025J/K move · Enter open · S save

VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting

Juyi Lin, Amir Taherin, Arash Akbari, Arman Akbari+10

Northeastern University, Boston, USA · EmbodyX,San Mateo,USA

Robotic Control Efficient VLA Model Inference Efficient VLA Models Vision-Language-Action Models VLMs for Robotics

Open paper AskPDF arXiv

Recent large-scale Vision Language Action (VLA) models have shown superior performance in robotic manipulation tasks guided by natural language. However, current VLA models suffer from two drawbacks: (i) generation of massive tokens leading to high inference latency and increased training cost, and (ii) insufficient utilization of generated actions resulting in potential performance loss. To address these issues, we develop a training framework to finetune VLA models for generating significantly fewer action tokens with high parallelism, effectively reducing inference latency and training cost. Furthermore, we introduce an inference optimization technique with a novel voting-based ensemble strategy to combine current and previous action predictions, improving the utilization of generated actions and overall performance. Our results demonstrate that we achieve superior performance compared with state-of-the-art VLA models, achieving significantly higher success rates and 39

\times

faster inference than OpenVLA with 46 Hz throughput on edge platforms, demonstrating practical deployability. The code is available at https://github.com/LukeLIN-web/VOTE.

Abstract

Explore similar work

VOTE: Vision-Language-Action Optimization with Trajectory Ensemble Voting

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Reducing Temporal Redundancy for Efficient Vision-Language-Action Inference