Pith Number

pith:VXPIXCCE

pith:2026:VXPIXCCEPMR7YESB5V4ACRJR6H

not attested not anchored not stored refs resolved

Accelerating Rectified Flow Models via Trajectory-Aware Caching

Hongliang Lu, Kai Liu, Naiyang Guan, Renjing Pei, Xiao Liu, Yulun Zhang, Zhikai Chen, Zhixin Wang

TACache accelerates rectified flow sampling by decomposing velocity changes into parallel and orthogonal parts to safely skip steps and reconstruct velocities from history.

arxiv:2605.16789 v1 · 2026-05-16 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{VXPIXCCEPMR7YESB5V4ACRJR6H}

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

TACache achieves up to 4.14 speedup on text-to-image generation and 2.11 speedup on text-to-video generation, with consistent improvements over prior cache-based methods on all reference-based fidelity metrics.

C2weakest assumption

The assumption that offline cumulative variation thresholds on magnitude and direction indicators from the orthogonal decomposition can reliably bound skip intervals across diverse samples, and that combining these with a sample's historical orthogonal direction accurately reconstructs skipped velocities without model evaluations or accumulated error.

C3one line summary

TACache accelerates rectified flow sampling up to 4.14x for text-to-image and 2.11x for text-to-video via offline skip scheduling from cumulative variation thresholds and online velocity reconstruction using historical orthogonal directions.

References

28 extracted · 28 resolved · 7 Pith anchors

[1] FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space 2025 · arXiv:2506.15742

[2] DiCache: Let diffusion model determine its own cache 2026

[3] Emerging Properties in Unified Multimodal Pretraining 2025 · arXiv:2505.14683

[4] Acceleration-aware sampling for few-step rectified flow models, 2025 2025

[5] GenEval: An object-focused framework for evaluating text-to-image alignment.NeurIPS, 2023 2023

Receipt and verification

First computed	2026-05-20T00:03:22.109290Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

adde8b88447b23fc1241ed78014531f1ec86b8c9c1982434ae1373a94d94f224

Aliases

arxiv: 2605.16789 · arxiv_version: 2605.16789v1 · doi: 10.48550/arxiv.2605.16789 · pith_short_12: VXPIXCCEPMR7 · pith_short_16: VXPIXCCEPMR7YESB · pith_short_8: VXPIXCCE

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/VXPIXCCEPMR7YESB5V4ACRJR6H \
  | 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: adde8b88447b23fc1241ed78014531f1ec86b8c9c1982434ae1373a94d94f224

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "96056b7ee058090a981fd859442aecdddf2215cc6f6508d6a601712bd0ef3f95",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T03:44:58Z",
    "title_canon_sha256": "852de7766eb839ac65f37719741b09a4b65cc277cec960f4b95745b232ccea84"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16789",
    "kind": "arxiv",
    "version": 1
  }
}