Pith Number

pith:EQGXLM4P

pith:2026:EQGXLM4P37PQTSRZRDIC5NINLM

not attested not anchored not stored refs resolved

LACE: Latent Visual Representation for Cross-Embodiment Learning

Cristina Mata, Jorge Mendez-Mendez, Kanchana Ranasinghe, Michael S. Ryoo, Yichi Zhang, Yoo Sung Jang

LACE aligns latent visual features of humans and robots using sparse body-part correspondences from one demonstration to enable effective cross-embodiment policy transfer.

arxiv:2605.16743 v1 · 2026-05-16 · 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{EQGXLM4P37PQTSRZRDIC5NINLM}

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

In zero-shot transfer, policies using LACE-DINO outperform those using DINO by a large margin (65%), with consistent gains in low-data regimes and out-of-distribution environments.

C2weakest assumption

That sparse correspondences between shared body parts (automatically obtained via forward kinematics from a single robot demonstration) are sufficient to lift patch-level supervision to reliable semantic-level alignment in the latent space without degrading the quality of the pretrained SSL backbone features.

C3one line summary

LACE aligns human-robot visual features via semantic distribution matching on corresponding body parts plus Gram loss, yielding 65% better zero-shot policy transfer than baseline DINO.

References

73 extracted · 73 resolved · 16 Pith anchors

[1] Idd-x: A multi-view dataset for ego-relative important object localization and explanation in den se and unstructured traﬃc 2024 · doi:10.1109/icra57147.2024.10611477

[2] DROID: A large-scale in-the-wild robot manipulation dataset 2024 · doi:10.15607/rss.2024.xx.120

[3] Bridgedata v2: A dataset for robot learning at scale 2023

[4] Humanoid policy˜ human policy 2025

[5] Kanchana Ranasinghe, Xiang Li, Cristina Mata, Jong Sung Park, and Michael S. Ryoo. Pixel motion as universal representation for robot control.ArXiv, 2025 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:02:39.391209Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

240d75b38fdfdf09ca3988d02eb50d5b1c6407c3a65ecce911b9f0d4e2236608

Aliases

arxiv: 2605.16743 · arxiv_version: 2605.16743v1 · doi: 10.48550/arxiv.2605.16743 · pith_short_12: EQGXLM4P37PQ · pith_short_16: EQGXLM4P37PQTSRZ · pith_short_8: EQGXLM4P

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/EQGXLM4P37PQTSRZRDIC5NINLM \
  | 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: 240d75b38fdfdf09ca3988d02eb50d5b1c6407c3a65ecce911b9f0d4e2236608

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6ad1de50f5a2b91a5121e731c3adce8062d7a56b618b7bfc4983194009ce6c9f",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-05-16T01:50:18Z",
    "title_canon_sha256": "cb2798123b1b3ec910a5d7f27713e8ce5f9c3d75d6b4e5a84cc8015dbf39f385"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16743",
    "kind": "arxiv",
    "version": 1
  }
}