Pith Number

pith:PPQJJRR6

pith:2025:PPQJJRR6JS2EFMGIQSOLSRDKHW

not attested not anchored not stored refs resolved

HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

Chengkai Hou, Chenyang Gu, Hao Chen, Jiaming Liu, KC alex Zhou, Mengdi Zhao, Mengzhen Liu, Pengju An, Pheng-Ann Heng, Renrui Zhang, Shanghang Zhang, Sixiang Chen, Xiaoqi Li, Zhuoyang Liu, Ziyu Guo

HybridVLA unifies diffusion for continuous actions and autoregression for reasoning inside one vision-language-action model.

arxiv:2503.10631 v3 · 2025-03-13 · cs.CV · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{PPQJJRR6JS2EFMGIQSOLSRDKHW}

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

HybridVLA outperforms previous state-of-the-art VLA methods by 14% and 19% in mean success rate on simulation and real-world tasks, respectively, while demonstrating stable manipulation in unseen configurations.

C2weakest assumption

The collaborative training recipe successfully prevents interference between diffusion denoising and next-token prediction while allowing the two paradigms to reinforce each other across tasks.

C3one line summary

HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.

References

127 extracted · 127 resolved · 42 Pith anchors

[1] PaLM-E: An Embodied Multimodal Language Model 2023 · arXiv:2303.03378

[2] Do As I Can, Not As I Say: Grounding Language in Robotic Affordances 2022 · arXiv:2204.01691

[3] VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models 2023 · arXiv:2307.05973

[4] What Matters in Building Vision-Language-Action Models for Generalist Robots 2024 · arXiv:2412.14058

[5] Visual instruction tuning 2024

Cited by

38 papers in Pith

Point Tracking Improves World Action Models

A Survey on Vision-Language-Action Models for Embodied AI

$\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation

TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation

Receipt and verification

First computed	2026-05-17T23:38:50.020884Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7be094c63e4cb442b0c8849cb9446a3db7f263eb3cb1311bf4768c02971e3b80

Aliases

arxiv: 2503.10631 · arxiv_version: 2503.10631v3 · doi: 10.48550/arxiv.2503.10631 · pith_short_12: PPQJJRR6JS2E · pith_short_16: PPQJJRR6JS2EFMGI · pith_short_8: PPQJJRR6

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/PPQJJRR6JS2EFMGIQSOLSRDKHW \
  | 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: 7be094c63e4cb442b0c8849cb9446a3db7f263eb3cb1311bf4768c02971e3b80

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "facb64202c82213c7e5ffa87cf5850af1e79e6f349e74b2fb30c6e601c2a1d0c",
    "cross_cats_sorted": [
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-03-13T17:59:52Z",
    "title_canon_sha256": "3547a3a9f5d9e60b9a2fdd4375a5e12e48215603b741ba11840c7c6c0f109329"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2503.10631",
    "kind": "arxiv",
    "version": 3
  }
}