Pith Number

pith:IYT27EWK

pith:2026:IYT27EWKNPMDLIXJZD4Z3KVH5Q

not attested not anchored not stored refs resolved

SToRe3D: Sparse Token Relevance in ViTs for Efficient Multi-View 3D Object Detection

Charles Cossette, Lezhou Feng, Lingting Ge, Sandro Papais

SToRe3D prunes ViT tokens and 3D queries via mutual relevance heads to reach 3x faster multi-view detection with only marginal accuracy loss.

arxiv:2605.14110 v1 · 2026-05-13 · 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{IYT27EWKNPMDLIXJZD4Z3KVH5Q}

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

SToRe3D achieves up to 3x faster inference with marginal accuracy loss, establishing real-time large-scale ViT-based 3D detection while maintaining accuracy on planning-critical agents.

C2weakest assumption

That the mutual 2D-3D relevance heads reliably identify driving-critical content and that storing filtered features does not introduce unacceptable reactivation overhead or accuracy degradation under varying scene conditions.

C3one line summary

SToRe3D delivers up to 3x faster inference for multi-view 3D object detection in ViTs by selecting relevant 2D tokens and 3D queries via mutual relevance heads with only marginal accuracy loss.

References

71 extracted · 71 resolved · 9 Pith anchors

[1] GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints · arXiv:2305.13245

[2] Token merging: Your vit but faster 2023

[3] nuscenes: A multi- modal dataset for autonomous driving 2020

[4] End- to-end object detection with transformers 2020

[5] Pointbev: A sparse approach for bev predictions 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:12.011011Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

4627af92ca6bd835a2e9c8f99daaa7ec0b6ec5e0195d9c1215f197c35a9e6ff0

Aliases

arxiv: 2605.14110 · arxiv_version: 2605.14110v1 · doi: 10.48550/arxiv.2605.14110 · pith_short_12: IYT27EWKNPMD · pith_short_16: IYT27EWKNPMDLIXJ · pith_short_8: IYT27EWK

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/IYT27EWKNPMDLIXJZD4Z3KVH5Q \
  | 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: 4627af92ca6bd835a2e9c8f99daaa7ec0b6ec5e0195d9c1215f197c35a9e6ff0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c737199c220c3db37617317a9be54b30b0602e2b84612c2aba9b7309bec89bf6",
    "cross_cats_sorted": [
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-13T20:53:03Z",
    "title_canon_sha256": "ec4506124253a3de3252722be03a18ffc73bbfe1d7525492bb96a4e8bd936298"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14110",
    "kind": "arxiv",
    "version": 1
  }
}