Pith Number

pith:XE4DZ72W

pith:2024:XE4DZ72WMHQWO2RL4XB2E2ZYSN

not attested not anchored not stored refs resolved

RoboDreamer: Learning Compositional World Models for Robot Imagination

Chuang Gan, Dit-Yan Yeung, Jiaben Chen, Siyuan Zhou, Yandong Li, Yilun Du

RoboDreamer factorizes video generation using language primitives to create plans for unseen robot tasks.

arxiv:2404.12377 v1 · 2024-04-18 · 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{XE4DZ72WMHQWO2RL4XB2E2ZYSN}

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 approach can successfully synthesize video plans on unseen goals in the RT-X, enables successful robot execution in simulation, and substantially outperforms monolithic baseline approaches to video generation.

C2weakest assumption

That natural language instructions can be reliably parsed into lower-level primitives whose separate models compose into coherent, realistic videos without introducing artifacts or losing task-relevant details.

C3one line summary

RoboDreamer factorizes video generation using language primitives to achieve compositional generalization in robot world models, outperforming monolithic baselines on unseen goals in RT-X.

References

65 extracted · 65 resolved · 12 Pith anchors

[7] Unsupervised learning of compositional energy concepts 2021

[8] B., Dieleman, S., Fergus, R., Sohl-Dickstein, J., Doucet, A., and Grathwohl, W 2023

[12] G., Tapaswi, M., Laptev, I., and Schmid, C 2023

[15] Diffusion-based generation, optimization, and planning in 3d scenes 2023

[17] R., and Davison, A 2020

Formal links

2 machine-checked theorem links

Cited by

27 papers in Pith

GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation

Beyond Syntax: Action Semantics Learning for App Agents

IGen: Scalable Data Generation for Robot Learning from Open-World Images

ProPhy: Progressive Physical Alignment for Dynamic World Simulation

RISE: Self-Improving Robot Policy with Compositional World Model

Receipt and verification

First computed	2026-05-17T23:38:50.211982Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b9383cff5661e1676a2be5c3a26b38935c6a5cae241ad73df8473f74c3e799dc

Aliases

arxiv: 2404.12377 · arxiv_version: 2404.12377v1 · doi: 10.48550/arxiv.2404.12377 · pith_short_12: XE4DZ72WMHQW · pith_short_16: XE4DZ72WMHQWO2RL · pith_short_8: XE4DZ72W

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/XE4DZ72WMHQWO2RL4XB2E2ZYSN \
  | 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: b9383cff5661e1676a2be5c3a26b38935c6a5cae241ad73df8473f74c3e799dc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "0aa12db3538b1b684f3c6617c97b68a99d7954b94c3f0e293508d2cddd1ee5ff",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2024-04-18T17:58:03Z",
    "title_canon_sha256": "857a47855d259cc296814b1c63587a86ee8d37905cfeb28ac34dabab669fa6c2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2404.12377",
    "kind": "arxiv",
    "version": 1
  }
}