pith. sign in
Pith Number

pith:SSGN4R6L

pith:2026:SSGN4R6LIKKYFLZTTJP2ICRFMD
not attested not anchored not stored refs resolved

Fast-WAM: Do World Action Models Need Test-time Future Imagination?

Hang Zhao, Tianyuan Yuan, Yicheng Liu, Zibin Dong

World Action Models achieve competitive performance without generating future observations at test time.

arxiv:2603.16666 v2 · 2026-03-17 · cs.CV · cs.AI

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{SSGN4R6LIKKYFLZTTJP2ICRFMD}

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

Fast-WAM remains competitive with imagine-then-execute variants, while removing video co-training causes a much larger performance drop. It achieves competitive results with state-of-the-art methods on simulation benchmarks (LIBERO and RoboTwin) and real-world tasks, without embodied pretraining, running in real time with 190ms latency.

C2weakest assumption

That the proposed Fast-WAM variants successfully disentangle the contribution of video modeling during training from explicit future generation at inference, allowing a controlled comparison of the two factors.

C3one line summary

Fast-WAM shows that explicit future imagination at test time is not required for strong WAM performance; video modeling during training provides the main benefit.

References

41 extracted · 41 resolved · 30 Pith anchors

[1] mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs 2025 · arXiv:2512.15692
[2] Video Generators are Robot Policies 2025 · arXiv:2508.00795
[3] Causal World Modeling for Robot Control 2026 · arXiv:2601.21998
[4] World action models are zero-shot policies
[5] World Action Models are Zero-shot Policies · arXiv:2602.15922

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

Receipt and verification
First computed 2026-05-18T02:45:49.533935Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

948cde47cb429582af339a5fa40a2560e2e14364cd856a55a1aa17f870c450df

Aliases

arxiv: 2603.16666 · arxiv_version: 2603.16666v2 · doi: 10.48550/arxiv.2603.16666 · pith_short_12: SSGN4R6LIKKY · pith_short_16: SSGN4R6LIKKYFLZT · pith_short_8: SSGN4R6L
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/SSGN4R6LIKKYFLZTTJP2ICRFMD \
  | 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: 948cde47cb429582af339a5fa40a2560e2e14364cd856a55a1aa17f870c450df
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "44e9f3d67425464f251e16eccbb9f2cf49bd5c87dad154d9f4bb2e0486218d79",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-03-17T15:33:43Z",
    "title_canon_sha256": "2de1c9d7f8c5b27c97c726e2efd13279dba35af91b2527fba96388b03aae1c41"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.16666",
    "kind": "arxiv",
    "version": 2
  }
}