Pith Number

pith:W7YHVHSF

pith:2025:W7YHVHSFZTXULAWRRYTSXEG3E3

not attested not anchored not stored refs resolved

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models

Chuheng Zhang, Hangxing Wei, Jiang Bian, Jianyu Chen, Kaixin Wang, Li Zhao, Pushi Zhang, Rushuai Yang, Xiaoyu Chen, Xinquan Xiao, Yanjiang Guo, Yucen Wang

villa-X improves latent action modeling in VLA models to enable zero-shot generation of action plans for unseen robot embodiments and open-vocabulary instructions.

arxiv:2507.23682 v3 · 2025-07-31 · cs.RO · cs.AI · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{W7YHVHSFZTXULAWRRYTSXEG3E3}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

villa-X can generate latent action plans in a zero-shot fashion, even for unseen embodiments and open-vocabulary symbolic understanding. This capability enables villa-X to achieve superior performance across diverse simulation tasks in SIMPLER and on two real-world robotic setups involving both gripper and dexterous hand manipulation.

C2weakest assumption

The improvements to latent action learning and incorporation into VLA pre-training are assumed to be the direct cause of the reported zero-shot generalization and performance gains, without detailed controls or ablations visible in the abstract.

C3one line summary

villa-X enhances latent action modeling in VLA models to support zero-shot action planning for unseen robot embodiments and open-vocabulary instructions, yielding better manipulation results in simulation and real-world tests.

References

71 extracted · 71 resolved · 23 Pith anchors

[1] AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems 2025 · arXiv:2503.06669

[2] Hydra: Hybrid robot actions for imitation learning.arxiv, 2023 2023

[3] PaliGemma: A versatile 3B VLM for transfer 2024 · arXiv:2407.07726

[4] $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control 2024 · arXiv:2410.24164

[5] RT-1: Robotics Transformer for Real-World Control at Scale 2022 · doi:10.48550/arxiv.2212.06817

Formal links

3 machine-checked theorem links

Cited by

30 papers in Pith

Point Tracking Improves World Action Models

Reinforcing VLAs in Task-Agnostic World Models

SCAR: Self-Supervised Continuous Action Representation Learning

UAM: A Dual-Stream Perspective on Forgetting in VLA Training

Co-Evolving Latent Action World Models

Receipt and verification

First computed	2026-05-17T23:38:50.039571Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b7f07a9e45ccef4582d18e272b90db26d34a7c27b8791754b1ae4d432713bd4d

Aliases

arxiv: 2507.23682 · arxiv_version: 2507.23682v3 · doi: 10.48550/arxiv.2507.23682 · pith_short_12: W7YHVHSFZTXU · pith_short_16: W7YHVHSFZTXULAWR · pith_short_8: W7YHVHSF

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/W7YHVHSFZTXULAWRRYTSXEG3E3 \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: b7f07a9e45ccef4582d18e272b90db26d34a7c27b8791754b1ae4d432713bd4d

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1d14164641818f55f4c03ad223def933a0ac57d35ab0f4efdc7b58d05236c074",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2025-07-31T15:57:46Z",
    "title_canon_sha256": "1f157f28ee369f3044ddd2a529757b150f1a6ebc0647be7877bb5bc6af542a02"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2507.23682",
    "kind": "arxiv",
    "version": 3
  }
}