Paper Citation Record · LEDGER

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

As of 2 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2503.23733.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2503.23733 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T22:47:09.500229Z

measured 34 of 34 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-01T06:32:01.292127+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T16:24:17.633259Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-01T18:16:15.623592Z

Reference resolution

33 of 33 outbound references displayed

verified exact12
verified fuzzy20
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 82e4d519-b3cd-4177-9bd5-294ff76d67a4 · outbound

This paper cites Model composition for multimodal large language models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Model composition for multimodal large language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.715269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 7329112e-3775-44ca-9fb1-2e88d6b4ebda · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:12.992624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c7d65c77-bfd0-477b-832c-baf1a767b69e · outbound

This paper cites Vlmevalkit: An open-source toolkit for evaluating large multi-modality models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Vlmevalkit: An open-source toolkit for evaluating large multi-modality models

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.740388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation a94917f3-a105-4b4a-8666-92e62bd52667 · outbound

This paper cites Open llm leaderboard v2.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Open llm leaderboard v2

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.731162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation dcc21b0b-6df2-42b4-9700-8a40762306f8 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:13.051119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 884112f5-272d-4b8c-b1bb-14c493c604eb · outbound

This paper cites Arcee's MergeKit: A Toolkit for Merging Large Language Models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Arcee's MergeKit: A Toolkit for Merging Large Language Models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-22T22:47:13.022569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c5df0ac0-9014-4138-9d89-0905bc5c14d3 · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Vizwiz grand challenge: Answering visual questions from blind people

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.785828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 41cec851-faf3-49cf-b7bf-c6f8af1032d0 · outbound

This paper cites CogVLM2: Visual Language Models for Image and Video Understanding.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization CogVLM2: Visual Language Models for Image and Video Understanding

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:13.016745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation d20748b5-2538-45d9-8b50-325555e13912 · outbound

This paper cites Gqa: A new dataset for real-world visual reasoning and compositional question answering.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.726684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 82640ac1-ffbd-4479-a5da-c8bde8f070f8 · outbound

This paper cites Editing Models with Task Arithmetic.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Editing Models with Task Arithmetic

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:13.005216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 13cfe3bf-7d2b-4ebb-89b1-f0d069fede3b · outbound

This paper cites Seed-bench: Bench- marking multimodal large language models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Seed-bench: Bench- marking multimodal large language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.793889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation d137d4cd-56cc-4c3c-b96d-177e51004655 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization LLaVA-OneVision: Easy Visual Task Transfer

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:13.034098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c4541fd2-edff-4e88-8ec7-b424820fe260 · outbound

This paper cites A Survey on Benchmarks of Multimodal Large Language Models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization A Survey on Benchmarks of Multimodal Large Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T22:47:13.058347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 8a4357ea-8570-498d-b038-5800dfc20fd6 · outbound

This paper cites Improved baselines with visual instruction tuning.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Improved baselines with visual instruction tuning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.797697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation cb342305-57b1-4715-8a9b-1a366456e06e · outbound

This paper cites OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:13.010209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation bdb624a3-e15c-4445-b2b1-42649ed6d01a · outbound

This paper cites Ok-vqa: A visual question answering benchmark requiring external knowledge.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Ok-vqa: A visual question answering benchmark requiring external knowledge

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.722612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 4e5cef5e-c9ee-462d-b030-c441c77872b4 · outbound

This paper cites Sentence-bert: Sentence embeddings using siamese bert-networks.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Sentence-bert: Sentence embeddings using siamese bert-networks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.750210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 639b056f-abdf-4642-8c14-41dbee70ea8d · outbound

This paper cites Towards vqa models that can read.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Towards vqa models that can read

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.745262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 23aea47c-a2ae-4363-9638-2a59da00ecab · outbound

This paper cites An Empirical Study of Multimodal Model Merging.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization An Empirical Study of Multimodal Model Merging

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-22T22:47:13.040070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 1d1d72b1-1777-45e9-bf90-cafc92cabbba · outbound

This paper cites Llama: Open and efficient foundation lan- guage models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Llama: Open and efficient foundation lan- guage models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.763870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 1cfe4624-dc0c-4770-b73c-65252017603e · outbound

This paper cites Attention is all you need.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Attention is all you need

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.772701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation feac4b98-aa29-417b-bdcc-ad9493c80b13 · outbound

This paper cites Knowledge fusion of large language models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Knowledge fusion of large language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.776973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 87ebef6d-0948-4c8b-b146-0fcb5f3a8c6a · outbound

This paper cites Knowledge fusion of chat llms: A preliminary technical report.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Knowledge fusion of chat llms: A preliminary technical report

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.759292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 1b9df78e-03da-496a-9040-1165a22a67c3 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:12.999223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c078eb9a-f62e-4e13-9c20-2097f5044aab · outbound

This paper cites CogVLM: Visual Expert for Pretrained Language Models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization CogVLM: Visual Expert for Pretrained Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-22T22:47:13.045306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation b0c7f121-436d-4b55-a9f6-79add888a4af · outbound

This paper cites TIES-Merging: Resolving interfer- ence when merging models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization TIES-Merging: Resolving interfer- ence when merging models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.789663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation fa4e1a20-fc46-42d9-a7d9-5ef92fd5ca88 · outbound

This paper cites Qwen2 technical report.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Qwen2 technical report

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.718835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 129400fc-d295-4990-ab27-19d67d031d2a · outbound

This paper cites mplug- owi2: Revolutionizing multi-modal large language model with modality collaboration.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization mplug- owi2: Revolutionizing multi-modal large language model with modality collaboration

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.736134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 4397b508-5be1-4c81-969a-c27683e33dbf · outbound

This paper cites Language models are super mario: Absorbing abilities from homologous models as a free lunch.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Language models are super mario: Absorbing abilities from homologous models as a free lunch

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.802378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 51a6a79a-ee0e-4468-b69c-1d80b82e1068 · outbound

This paper cites MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for ex- pert agi

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.754647Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 88f81d22-ffae-48c0-8737-c81fe23a0e1e · outbound

This paper cites Lmms- eval: Reality check on the evaluation of large multimodal models.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Lmms- eval: Reality check on the evaluation of large multimodal models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T22:47:13.780982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation 2bc6c25b-e314-44f7-816f-3abda1d72bd0 · outbound

This paper cites MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization MetaGPT: Merging Large Language Models Using Model Exclusive Task Arithmetic

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-22T22:47:13.028887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Observation c65b7fac-bd4c-44c1-9b52-c4655d24a360 · outbound

This paper cites an unresolved cited work.

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization Unresolved cited work

Reference 33

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T22:47:13.768589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.

Pith citing papers

Observation b953f338-90a0-467f-9b43-0ba5adb2c7c0 · inbound

Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective cites this paper.

Rethinking Heterogeneous LLM Merging: A Weighted Model Averaging Perspective AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-08-01T16:28:38.980406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-01T06:32:01.292127+00:00.