Pith Number

pith:WZ34WRPF

pith:2024:WZ34WRPFD24Y2BKDMFRBPVSYWP

not attested not anchored not stored refs resolved

GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Dingkun Long, Meishan Zhang, Mingxin Li, Min Zhang, Pengjun Xie, Wenjie Li, Wen Xie, Xin Zhang, Yanzhao Zhang, Ziqi Dai

Training an MLLM on synthetically balanced fused text-image data produces a single dense retriever that leads on universal multimodal search tasks.

arxiv:2412.16855 v2 · 2024-12-22 · cs.CL · cs.IR

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{WZ34WRPFD24Y2BKDMFRBPVSYWP}

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

Experimental results show that our method achieves state-of-the-art performance among existing UMR methods.

C2weakest assumption

That the synthetic fused-modal training dataset is of high quality and sufficiently diverse to unlock the full potential of MLLMs for universal multimodal retrieval without introducing biases or artifacts.

C3one line summary

GME achieves state-of-the-art results in universal multimodal retrieval by training on a balanced synthetic multimodal dataset.

References

86 extracted · 86 resolved · 9 Pith anchors

[1] Overview of touch ´e 2020: Argument retrieval - extended abstract 2020

[2] A full-text learning to rank dataset for medical information retrieval 2016

[3] Tom B. Brown, Benjamin Mann, Nick Ryder, Melanie Sub- biah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakan- tan, Pranav Shyam, Girish Sastry, Amanda Askell, Sand- hini Agarwal, Ariel Herbert-V oss, 2020

[4] Webqa: Multihop and multimodal QA 2022

[5] Training Deep Nets with Sublinear Memory Cost 2016 · arXiv:1604.06174

Formal links

2 machine-checked theorem links

Cited by

33 papers in Pith

From Head to Tail: Asymmetric Knowledge Transfer in Long-tail Recommendation with Generative Semantic IDs

End-to-End Semantic ID Generation for Generative Advertisement Recommendation

FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation

TriAlignGR: Triangular Multitask Alignment with Multimodal Deep Interest Mining for Generative Recommendation

Do Composed Image Retrieval Benchmarks Require Multimodal Composition?

Receipt and verification

First computed	2026-05-17T23:38:53.247396Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b677cb45e51eb98d0543616217d658b3dd0c9b77e6a47833ac9b256373655b97

Aliases

arxiv: 2412.16855 · arxiv_version: 2412.16855v2 · doi: 10.48550/arxiv.2412.16855 · pith_short_12: WZ34WRPFD24Y · pith_short_16: WZ34WRPFD24Y2BKD · pith_short_8: WZ34WRPF

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/WZ34WRPFD24Y2BKDMFRBPVSYWP \
  | 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: b677cb45e51eb98d0543616217d658b3dd0c9b77e6a47833ac9b256373655b97

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "748847fa281d19d5e0a56770ec05a9bba758fa4e7ad976dc2000ca0e11f1851a",
    "cross_cats_sorted": [
      "cs.IR"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CL",
    "submitted_at": "2024-12-22T04:40:24Z",
    "title_canon_sha256": "ea6af16b54e7eb7912e00c33bd2c62ddb3a35dd38ab597b5206a3f4fbb5d0b62"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2412.16855",
    "kind": "arxiv",
    "version": 2
  }
}