pith. sign in
Pith Number

pith:BLQDQJEI

pith:2026:BLQDQJEISWHP334A43JMKP6TMH
not attested not anchored not stored refs pending

TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language Models

Congyang Ou, Dawei Yan, Haokui Zhang, Peng Wang, Qingsen Yan, Rong Xiao, Ying Li, Yu Zhang

TRIO reduces visual tokens in vision-language models to 11 percent while retaining 97 percent performance by selecting tokens whose removal leaves the final output unchanged.

arxiv:2602.04657 v3 · 2026-02-04 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{BLQDQJEISWHP334A43JMKP6TMH}

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

On LLaVA-Next-7B, TRIO retains just 11.1% of visual tokens but maintains 97.2% of the original performance, with a 2.75× prefill speedup, 2.14× inference speedup, 6.22× lower FLOPs, and 6.05× reduced KV Cache overhead.

C2weakest assumption

That the designed layer-local proxy loss produces token-level gradient saliency that reliably identifies tokens whose removal leaves the final output essentially unchanged, without requiring full end-to-end gradients or task-specific tuning.

C3one line summary

TRIO keeps 97.2% performance on LLaVA-Next-7B using only 11.1% visual tokens, yielding 2.75x prefill speedup and 6x lower FLOPs via inference-objective gradient guidance.

Receipt and verification
First computed 2026-05-17T23:39:16.348136Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0ae0382488958efdef80e6d2c53fd361f5351c15ead05b1e0d2bfc760240441d

Aliases

arxiv: 2602.04657 · arxiv_version: 2602.04657v3 · doi: 10.48550/arxiv.2602.04657 · pith_short_12: BLQDQJEISWHP · pith_short_16: BLQDQJEISWHP334A · pith_short_8: BLQDQJEI
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BLQDQJEISWHP334A43JMKP6TMH \
  | 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: 0ae0382488958efdef80e6d2c53fd361f5351c15ead05b1e0d2bfc760240441d
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "274d100576cf7ef06b3118ef63ceb4875086938a2e4827733a3a3a6e1290afd5",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-02-04T15:33:10Z",
    "title_canon_sha256": "9ec91120c352d9e8cf72dcdd2ab0f3419da85bff1dcbf048010ee28f72d3ec88"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2602.04657",
    "kind": "arxiv",
    "version": 3
  }
}