pith. sign in
Pith Number

pith:S4H6UNB3

pith:2024:S4H6UNB3RG2NF7OXXPN7QU2DJV
not attested not anchored not stored refs resolved

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities

Dacheng Tao, Enneng Yang, Guibing Guo, Jie Zhang, Li Shen, Xiaochun Cao, Xingwei Wang

Model merging combines trained models without new data or heavy retraining, and this survey organizes the methods into a fresh taxonomy while mapping their uses in language models and many other settings.

arxiv:2408.07666 v5 · 2024-08-14 · cs.LG · cs.AI · cs.CL · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{S4H6UNB3RG2NF7OXXPN7QU2DJV}

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

This survey provides a comprehensive overview of model merging methods and theories, their applications in various domains and settings, and future research directions. Specifically, we first propose a new taxonomic approach that exhaustively discusses existing model merging methods.

C2weakest assumption

The proposed taxonomy is exhaustive and the reviewed literature accurately represents the current state of model merging techniques without significant omissions or mischaracterizations.

C3one line summary

The paper introduces a new taxonomy for model merging methods and reviews their applications in LLMs, MLLMs, continual learning, multi-task learning, and other subfields while outlining open challenges.

References

299 extracted · 299 resolved · 15 Pith anchors

[1] Javier Abad, Konstantin Donhauser, Francesco Pinto, and Fanny Yang. 2024. Strong Copyright Protection for Language Models via Adaptive Model Fusion.ICML(2024) 2024
[2] GPT-4 Technical Report 2023 · arXiv:2303.08774
[3] Linara Adilova, Asja Fischer, and Martin Jaggi. 2024. Layerwise linear mode connectivity.ICLR(2024) 2024
[4] Emanuele Aiello, Lili Yu, Yixin Nie, Armen Aghajanyan, and Barlas Oguz. 2024. Jointly training large autoregressive multimodal models.ICLR(2024) 2024
[5] Samuel Ainsworth, Jonathan Hayase, and Siddhartha Srinivasa. 2023. Git Re-Basin: Merging Models modulo Permu- tation Symmetries. InICLR 2023

Formal links

1 machine-checked theorem link

Cited by

25 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:12.879582Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

970fea343b89b4d2fdd7bbdbf853434d56243a9020826c011b83d010fd033e7a

Aliases

arxiv: 2408.07666 · arxiv_version: 2408.07666v5 · doi: 10.48550/arxiv.2408.07666 · pith_short_12: S4H6UNB3RG2N · pith_short_16: S4H6UNB3RG2NF7OX · pith_short_8: S4H6UNB3
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/S4H6UNB3RG2NF7OXXPN7QU2DJV \
  | 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: 970fea343b89b4d2fdd7bbdbf853434d56243a9020826c011b83d010fd033e7a
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "2bf84cfa927f14e59dc85889c7a67959759abcc20b49a854d0576b261863614f",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CL",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2024-08-14T16:58:48Z",
    "title_canon_sha256": "7ad0ce19dce4c2a8a359d088a94f8ef4dd2c41719dfc0b8983cc770c74ad4003"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2408.07666",
    "kind": "arxiv",
    "version": 5
  }
}