Pith Number

pith:ZARD27V7

pith:2026:ZARD27V76RNBZ5IFD7F5FHBUYV

not attested not anchored not stored refs pending

MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction

Dohyeok Lee, Jin Woo Koo, Jung Min Lee, Jungwoo Lee, Li Zhao, Sangwoo Hong, Seokhun Ju, Taehyun Cho

Cross-viewpoint reconstruction trains latent actions to capture underlying robot actions rather than camera-specific details.

arxiv:2602.03668 v3 · 2026-02-03 · 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{ZARD27V76RNBZ5IFD7F5FHBUYV}

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

MVP-LAM produces more action-centric latent actions, achieving higher mutual information with ground-truth actions and improved action prediction, including under out-of-distribution evaluation. Finally, pretraining VLAs with MVP-LAM latent actions improves downstream manipulation performance on various benchmarks.

C2weakest assumption

That forcing a latent action from one viewpoint to explain the future in another viewpoint will make the latent action contain information about the underlying ground-truth actions rather than viewpoint-specific cues.

C3one line summary

MVP-LAM learns action-centric latent actions from multi-view videos via cross-viewpoint reconstruction, yielding higher mutual information with ground-truth actions and improved downstream VLA manipulation performance.

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Why Latent Actions Fail, and How to Prevent It

Receipt and verification

First computed	2026-05-28T01:04:36.264068Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b

Aliases

arxiv: 2602.03668 · arxiv_version: 2602.03668v3 · doi: 10.48550/arxiv.2602.03668 · pith_short_12: ZARD27V76RNB · pith_short_16: ZARD27V76RNBZ5IF · pith_short_8: ZARD27V7

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/ZARD27V76RNBZ5IFD7F5FHBUYV \
  | 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: c8223d7ebff45a1cf5051fcbd29c34c55f934fd57294adb660f11ef5352b8c3b

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "45e4aaeaa709cd485cc2eb7893f6e4469d4d6f62a8ed77de72c0efa5046b2dd0",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-02-03T15:51:25Z",
    "title_canon_sha256": "dadabbac91cc2e0b0c79aceb634cafd2e709dfa00da201181bf898701319c8a7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.03668",
    "kind": "arxiv",
    "version": 3
  }
}