Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

VLAct: Representation-Centric Pre-Training Boosts VLA Models Beyond Data Scaling

AI By Crimson AI Hugging Face Papers 31 August 2026 · 00:00 1 views
Share: X Telegram

A new Hugging Face paper introduces VLAct, a continued pre-training approach for vision-language-action models that preserves VLM priors and shared action semantics, achieving strong results on simulations and unseen embodiments with modest compute.

VLAct: Representation-Centric Pre-Training Boosts VLA Models Beyond Data Scaling

Key points

Scaling robot data is essential for building generalist Vision-Language-Action (VLA) models, but collecting robot trajectories is costly and sparse compared to web-scale image-text data. This makes representation quality a key bottleneck: under a fixed data budget, continued pre-training must turn limited trajectories into transferable visual-action knowledge rather than merely fitting actions.

To address this, researchers propose VLAct, a VLA-oriented VLM backbone trained on broad, heterogeneous, multi-embodiment robot data before task-specific fine-tuning. VLAct preserves the broad VLM prior and encourages shared action semantics across embodiments through three mechanisms: VLM-prior preservation, multi-head continuous action co-supervision, and a partially unified cross-embodiment action layout, while allowing task-specific action heads during fine-tuning.

Across simulation, real-world, and unseen-embodiment transfer, VLAct consistently improves downstream performance under fixed fine-tuning protocols. On LIBERO-Plus and RoboTwin 2.0, VLAct surpasses industrial VLA systems including ABot-M0 and LingBot-VLA, achieving success rates of 82.6% and 92.5%. On RoboDojo, VLAct ranks sixth among all policies by success rate and outperforms all explicitly designated world-action model (WAM) entries on both metrics.

Most notably, on RoboCasa-GR1, an unseen humanoid embodiment, VLAct using only 20% of downstream trajectories outperforms the full-data GR00T-N1.6 baseline. These results are obtained using fully open-source data and only a 16-GPU training setup, showing that representation-centric continued pre-training can deliver highly competitive performance under a modest compute budget and is an important independent axis of VLA progress beyond data scaling.

VLAct is strong, open, and research-friendly: it releases the data, models, and complete training/fine-tuning pipeline, with full continued pre-training requiring only 16 GPUs.

BenchmarkVLAct Success RateComparison
LIBERO-Plus82.6%Surpasses ABot-M0 and LingBot-VLA
RoboTwin 2.092.5%Surpasses ABot-M0 and LingBot-VLA
RoboDojo#6 by success rateOutperforms all World Action Models
RoboCasa-GR1 (unseen humanoid)Outperforms full-data GR00T-N1.6 with 20% dataBaseline: GR00T-N1.6
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1