Pith Number

pith:SCF7EQVE

pith:2025:SCF7EQVEK6FTZY5KSXS4Z5R2SK

not attested not anchored not stored refs resolved

Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers

Ali Agha, Jay Patrikar, Ruogu Li, Sebastian Scherer, Shayegan Omidshafiei, Yuheng Qiu, Yutian Chen

A distilled confidence predictor ranks and merges low-uncertainty tokens to accelerate visual geometric transformers up to 21 times without retraining.

arxiv:2511.14751 v2 · 2025-11-18 · cs.CV · 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{SCF7EQVEK6FTZY5KSXS4Z5R2SK}

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

When applied to VGGT and Pi3, Co-Me achieves up to 21.5x and 20.4x speedup, making visual geometric transformers practical for real-time 3D perception and reconstruction.

C2weakest assumption

That a distilled lightweight confidence predictor can reliably rank tokens by uncertainty in a manner that matches regions emphasized by the transformer, enabling substantial acceleration without degrading performance across multi-view and streaming setups.

C3one line summary

Co-Me distills a confidence predictor to selectively merge low-confidence tokens in visual geometric transformers, delivering up to 21.5x speedup on VGGT and 20.4x on Pi3 while preserving spatial coverage and performance.

References

44 extracted · 44 resolved · 2 Pith anchors

[1] Large-scale data for multiple-view stereopsis.International Journal of Computer Vision, pages 1–16, 2016 2016

[2] Token merging for fast sta- ble diffusion

[3] Token merging: Your vit but faster, 2023 2023

[4] Learning to rank using gradient descent 2005

[5] Must3r: Multi-view network for stereo 3d reconstruc- tion, 2025 2025

Receipt and verification

First computed	2026-05-17T23:39:00.734159Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

908bf242a4578b3ce3aa95e5ccf63a92a0679976428f6443052c6f4c1669e621

Aliases

arxiv: 2511.14751 · arxiv_version: 2511.14751v2 · doi: 10.48550/arxiv.2511.14751 · pith_short_12: SCF7EQVEK6FT · pith_short_16: SCF7EQVEK6FTZY5K · pith_short_8: SCF7EQVE

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/SCF7EQVEK6FTZY5KSXS4Z5R2SK \
  | 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: 908bf242a4578b3ce3aa95e5ccf63a92a0679976428f6443052c6f4c1669e621

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2aace5a36849de6fde91afc753105b5554fc5a4e04de5e821ea7947722357a4e",
    "cross_cats_sorted": [
      "cs.RO"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-11-18T18:52:22Z",
    "title_canon_sha256": "40221f17d47a6be85094c05fdf06a5182eca98f2189ae5158aac26e397e62cba"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2511.14751",
    "kind": "arxiv",
    "version": 2
  }
}