Pith Number

pith:4KFEMSFZ

pith:2026:4KFEMSFZXVKKVLX2SZ4RNRZ6WH

not attested not anchored not stored refs resolved

JEDI: Joint Embedding Diffusion World Model for Online Model-Based Reinforcement Learning

Dianbo Liu, Haozhe Ma, Jing Yu Lim, Rushi Shah, Samson Yu, Tze-Yun Leong, Zarif Ikram

JEDI trains an end-to-end latent diffusion world model by learning predictive latents directly from the diffusion denoising loss inside a JEPA framework.

arxiv:2605.13013 v1 · 2026-05-13 · 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{4KFEMSFZXVKKVLX2SZ4RNRZ6WH}

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

JEDI is the first online end-to-end latent diffusion world model. It learns its latent space directly from the diffusion denoising loss with a JEPA framework... Empirically, JEDI is competitive on Atari100k and outperforms the baseline with separately trained latents... JEDI uses 43% less VRAM, over 3× faster world-model sampling, and 2.5× faster training.

C2weakest assumption

That training latents end-to-end from the diffusion denoising loss inside the JEPA framework avoids the predictive information bottleneck of conventional JEPA objectives and yields representations that are both predictive and efficient for online MBRL.

C3one line summary

JEDI is the first online end-to-end latent diffusion world model that trains latents from denoising loss rather than reconstruction, achieving competitive Atari100k results with 43% less VRAM and over 3x faster sampling than pixel diffusion baselines.

References

92 extracted · 92 resolved · 17 Pith anchors

[1] Dyna, an integrated architecture for learning, planning, and reacting.ACM Sigart Bulletin, 2(4):160–163 1991

[2] World Models 2018 · arXiv:1803.10122

[3] Dream to Control: Learning Behaviors by Latent Imagination 1912 · arXiv:1912.01603

[4] Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models 2024 · arXiv:2402.17177

[5] Genie 2: A large-scale foundation world model.URL: https://deepmind 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:00.222191Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

e28a4648b9bd54aaaefa967916c73eb1c3405e39f598951dd15a098508ea06d3

Aliases

arxiv: 2605.13013 · arxiv_version: 2605.13013v1 · doi: 10.48550/arxiv.2605.13013 · pith_short_12: 4KFEMSFZXVKK · pith_short_16: 4KFEMSFZXVKKVLX2 · pith_short_8: 4KFEMSFZ

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/4KFEMSFZXVKKVLX2SZ4RNRZ6WH \
  | 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: e28a4648b9bd54aaaefa967916c73eb1c3405e39f598951dd15a098508ea06d3

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "290ca9412f9ef4ab54eca3f7ef1b9d819478dfe49e44f04e95302711915c4974",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T05:07:32Z",
    "title_canon_sha256": "c814de03040f53e2e8e811ce7caa1e18fdc876c632131e48255a62973a710941"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13013",
    "kind": "arxiv",
    "version": 1
  }
}