pith. sign in
Pith Number

pith:XWR3HY4R

pith:2025:XWR3HY4R63WXARVJBBE3KP3PQ5
not attested not anchored not stored refs resolved

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

Benedek Forrai, Elvis Nava, Jonas Pai, Liam Achenbach, Oier Mees, Victoriano Montesinos

Pretrained video models plus a flow-matching decoder let robots learn manipulation with far less data than vision-language-action models.

arxiv:2512.15692 v2 · 2025-12-17 · cs.RO · cs.AI · cs.CV · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{XWR3HY4R63WXARVJBBE3KP3PQ5}

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

Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.

C2weakest assumption

That a pretrained internet video model already captures sufficient physical causality and temporal dynamics so that the remaining task reduces cleanly to low-level control via the flow-matching decoder.

C3one line summary

mimic-video combines internet video pretraining with a flow-matching decoder to achieve state-of-the-art robotic manipulation performance with 10x better sample efficiency than vision-language-action models.

References

64 extracted · 64 resolved · 35 Pith anchors

[1] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning 2025 · arXiv:2506.09985
[2] PaliGemma: A versatile 3B VLM for transfer 2024 · arXiv:2407.07726
[3] $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control 2024 · arXiv:2410.24164
[4] RoboCat : A self-improving foundation agent for robotic manipulation 2023
[5] Emerging Properties in Self-Supervised Vision Transformers 2021 · arXiv:2104.14294

Formal links

2 machine-checked theorem links

Cited by

24 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:52.754552Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

bda3b3e391f6ed7046a90849b53f6f8773a77ed8908f7f8ad73ae49c2ede6ab2

Aliases

arxiv: 2512.15692 · arxiv_version: 2512.15692v2 · doi: 10.48550/arxiv.2512.15692 · pith_short_12: XWR3HY4R63WX · pith_short_16: XWR3HY4R63WXARVJ · pith_short_8: XWR3HY4R
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/XWR3HY4R63WXARVJBBE3KP3PQ5 \
  | 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: bda3b3e391f6ed7046a90849b53f6f8773a77ed8908f7f8ad73ae49c2ede6ab2
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "e0d5f68d11feba92f0d5cc4636c6164c479c12c5155cd641402809cf223bf8da",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV",
      "cs.LG"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2025-12-17T18:47:31Z",
    "title_canon_sha256": "0412f0ff8a4ed450487be639acf053b40c333f1fd4bc4b5d02d74e264d01b310"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.15692",
    "kind": "arxiv",
    "version": 2
  }
}