Pith Number

pith:TH2SU6U2

pith:2024:TH2SU6U2C4OGFAHMX7DPACH67S

not attested not anchored not stored refs resolved

3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

Chenyuan Hu, Gu Zhang, Huazhe Xu, Kangning Zhang, Muhan Wang, Yanjie Ze

A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations.

arxiv:2403.03954 v7 · 2024-03-06 · cs.RO · cs.CV · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{TH2SU6U2C4OGFAHMX7DPACH67S}

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

DP3 successfully handles most tasks with just 10 demonstrations and surpasses baselines with a 24.2% relative improvement. In 4 real robot tasks, DP3 demonstrates precise control with a high success rate of 85%, given only 40 demonstrations of each task, and shows excellent generalization abilities in diverse aspects, including space, viewpoint, appearance, and instance.

C2weakest assumption

That the compact 3D visual representation extracted from sparse point clouds is sufficient to capture all task-relevant geometry and generalizes across the reported variations without requiring additional modalities or task-specific tuning.

C3one line summary

DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.

References

86 extracted · 86 resolved · 3 Pith anchors

[1] Dexterous functional grasping 2023

[2] Is Conditional Generative Modeling all you need for Decision-Making? 2022 · arXiv:2211.15657

[3] Dexterous imitation made easy: A learning-based framework for efficient dexterous manip- ulation 2023

[4] Layer normalization 2016

[5] Dexart: Benchmarking generalizable dexterous manipu- lation with articulated objects 2023

Formal links

3 machine-checked theorem links

Cited by

57 papers in Pith

LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation

DSSP: Diffusion State Space Policy with Full-History Encoding

EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control

From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model

FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation

Receipt and verification

First computed	2026-05-17T23:38:53.898288Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6

Aliases

arxiv: 2403.03954 · arxiv_version: 2403.03954v7 · doi: 10.48550/arxiv.2403.03954 · pith_short_12: TH2SU6U2C4OG · pith_short_16: TH2SU6U2C4OGFAHM · pith_short_8: TH2SU6U2

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/TH2SU6U2C4OGFAHMX7DPACH67S \
  | 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: 99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "674c6b880643042c8489509f171589c244982c96ccb748278b06b3613277ad0b",
    "cross_cats_sorted": [
      "cs.CV",
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2024-03-06T18:58:49Z",
    "title_canon_sha256": "38c87db59baade0db5b3588d7a24aa23e5df235f6d265dcabba1e958f2f7f57a"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2403.03954",
    "kind": "arxiv",
    "version": 7
  }
}