Pith Number

pith:7UNFV772

pith:2026:7UNFV772FNRC5AX63ECEBJJNLW

not attested not anchored not stored refs resolved

RotVLA: Rotational Latent Action for Vision-Language-Action Model

Hangjun Ye, Jiahuan Zhou, Peiyan Li, Qiwei Li, Quanyun Zhou, Xicheng Gong, Xinghang Li, Yadong Mu

RotVLA replaces discrete action codes with continuous rotations in SO(n) for vision-language-action models.

arxiv:2605.13403 v1 · 2026-05-13 · cs.RO · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{7UNFV772FNRC5AX63ECEBJJNLW}

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

With only 1.7B parameters and 1700+ hours of pretraining data, RotVLA achieves 98.2% on LIBERO and 89.6% / 88.5% on RoboTwin2.0 under clean and randomized settings, respectively. It also demonstrates strong real-world performance on manipulation tasks, consistently outperforming existing VLA models.

C2weakest assumption

That representing latent actions as elements of SO(n) together with a triplet-frame objective inherently supplies continuity, compositionality, and physically meaningful structure while preventing trivial frame-reconstruction solutions.

C3one line summary

RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.

References

86 extracted · 86 resolved · 28 Pith anchors

[1] A Survey on Vision-Language-Action Models for Embodied AI 2024 · arXiv:2405.14093

[2] Roumelio- tis, and Manoj Karkee 2025

[3] Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916 2023

[4] Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks 2024

[5] Qwen2.5-VL Technical Report 2025 · arXiv:2502.13923

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T02:44:47.562788Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

fd1a5afffa2b622e82fed90440a52d5da9bbc0d853c481f1fed1519437d83071

Aliases

arxiv: 2605.13403 · arxiv_version: 2605.13403v1 · doi: 10.48550/arxiv.2605.13403 · pith_short_12: 7UNFV772FNRC · pith_short_16: 7UNFV772FNRC5AX6 · pith_short_8: 7UNFV772

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/7UNFV772FNRC5AX63ECEBJJNLW \
  | 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: fd1a5afffa2b622e82fed90440a52d5da9bbc0d853c481f1fed1519437d83071

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b0058c9cb08bfe16717aa0f2996ad0907bf79985020d3514a734f2490e937e93",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-13T11:58:02Z",
    "title_canon_sha256": "156756c0e83713819ca534a0933f03d1d22d311eef5d9fb16e469ff32a419c15"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13403",
    "kind": "arxiv",
    "version": 1
  }
}