Pith Number

pith:H2OIZBHN

pith:2025:H2OIZBHNFCOWRFZW4Y7BC2YRF5

not attested not anchored not stored refs pending

A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models

Ming-Ming Cheng, Peng-Tao Jiang, Qibin Hou, Qilong Wang, Quan-Sheng Zeng, Yunheng Li, Zuxuan Wu

arxiv:2508.01548 v1 · 2025-08-03 · 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{H2OIZBHNFCOWRFZW4Y7BC2YRF5}

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.

Cited by

5 papers in Pith

Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models

Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction

Beyond Surrogate Gradients: Fully Differentiable Token Pruning for Vision-Language Models

See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding

Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing Understanding

Receipt and verification

First computed	2026-07-05T11:47:40.947242Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

3e9c8c84ed289d689736e63e116b112f417a2271f30077f58706a07b52d99ffc

Aliases

arxiv: 2508.01548 · arxiv_version: 2508.01548v1 · doi: 10.48550/arxiv.2508.01548 · pith_short_12: H2OIZBHNFCOW · pith_short_16: H2OIZBHNFCOWRFZW · pith_short_8: H2OIZBHN

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/H2OIZBHNFCOWRFZW4Y7BC2YRF5 \
  | 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: 3e9c8c84ed289d689736e63e116b112f417a2271f30077f58706a07b52d99ffc

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "1c8d14b66f7f5f7b1c758ac386b2fe67873b397c1112a08c2b7a5abfe4b6554a",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2025-08-03T02:15:43Z",
    "title_canon_sha256": "52df525c70f002cf6fea61834d184b321d5c75d2811072973cb9fe3ab5253f42"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2508.01548",
    "kind": "arxiv",
    "version": 1
  }
}