Paper Citation Record · LEDGER

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

As of 4 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 1 inbound Pith citation observation for arXiv:2512.20136.

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

pith.paper-citation-record.v1
2512.20136 v3

Coverage vector

measured 64 of 64 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-16T20:25:17.992009Z

measured 65 of 65 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-03T06:30:56.289259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T03:11:54.775186Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

64 of 64 outbound references displayed

verified exact25
verified fuzzy38
unresolved1
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation ebc71ff2-319b-4a28-8497-2478cbb06f5b · outbound

This paper cites GPT-4 Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.265540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 01c7122a-7e81-4877-a351-1dfe881994b6 · outbound

This paper cites Flamingo: a visual language model for few-shot learning.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Flamingo: a visual language model for few-shot learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.502459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ac01c28e-30b9-4935-af8d-d00e0c6b83fe · outbound

This paper cites PaLM 2 Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation PaLM 2 Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.258269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3d806be5-de41-453a-a211-155ff6441061 · outbound

This paper cites Reflective multi- agent collaboration based on large language models.Ad- vances in Neural Information Processing Systems, 37:138595– 138631.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Reflective multi- agent collaboration based on large language models.Ad- vances in Neural Information Processing Systems, 37:138595– 138631

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.498766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f5d1ac21-263c-48cb-a25e-21ac944aecbd · outbound

This paper cites Improving language models by retriev- ing from trillions of tokens.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Improving language models by retriev- ing from trillions of tokens

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.510613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0b157ab0-a520-497b-837a-34fb38287fd8 · outbound

This paper cites Activitynet: A large-scale video bench- mark for human activity understanding.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Activitynet: A large-scale video bench- mark for human activity understanding

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.559049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3628fb65-e495-4341-bb6d-2d35fc8dc40f · outbound

This paper cites Vggsound: A large-scale audio-visual dataset.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Vggsound: A large-scale audio-visual dataset

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.526616Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 66d8fc06-43f1-4723-b18b-46a7dff9a9c5 · outbound

This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.262237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 17a1a4e2-e901-466a-a145-e7c44e24a1e0 · outbound

This paper cites Kimi-Audio Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Kimi-Audio Technical Report

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.269283Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 2bd43eac-8385-4758-ab82-9b0c06ce13fa · outbound

This paper cites The llama 3 herd of models.arXiv e-prints, pages arXiv–2407.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation The llama 3 herd of models.arXiv e-prints, pages arXiv–2407

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.522361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation eb62cacc-468e-4310-8528-48266d70e890 · outbound

This paper cites From Local to Global: A Graph RAG Approach to Query-Focused Summarization.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation From Local to Global: A Graph RAG Approach to Query-Focused Summarization

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.220989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a999c17f-170f-4c42-a97b-b6bf7cb49eea · outbound

This paper cites A sur- vey on rag meeting llms: Towards retrieval-augmented large language models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation A sur- vey on rag meeting llms: Towards retrieval-augmented large language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.545059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation be601260-7efe-46b2-b5b9-d19ffd62c988 · outbound

This paper cites Precise zero-shot dense retrieval without relevance labels.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Precise zero-shot dense retrieval without relevance labels

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.529297Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 16f9baef-e03b-415f-be5f-d082e9b2f90d · outbound

This paper cites Gemmeke, Daniel P.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Gemmeke, Daniel P

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.534559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 05c97855-fd89-4dbe-8748-630fdbd1235e · outbound

This paper cites Recap: Retrieval- augmented audio captioning.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Recap: Retrieval- augmented audio captioning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.518467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 7e6f03c9-d710-4731-9bb6-5bf1c2b7dbae · outbound

This paper cites The Llama 3 Herd of Models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation The Llama 3 Herd of Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.217526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 90eaa30a-3dc2-421e-8163-1e0d1e4eb8ce · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.210683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fade3ec8-69bd-4cea-a632-4796c00f10d4 · outbound

This paper cites LightRAG: Simple and fast retrieval-augmented gen- eration.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation LightRAG: Simple and fast retrieval-augmented gen- eration

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.542813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation db5ea8c2-97cb-4bb4-b9b2-0e3058a42460 · outbound

This paper cites 1, 2, 6, 4.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation 1, 2, 6, 4

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.530872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9b4754f4-fa6a-43c9-9e69-528e4cc7a23b · outbound

This paper cites From RAG to memory: Non-parametric continual learning for large language models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation From RAG to memory: Non-parametric continual learning for large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.596502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 13d65aaf-45a3-46f1-b499-77a449869c30 · outbound

This paper cites Realm: retrieval-augmented language model pre-training.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Realm: retrieval-augmented language model pre-training

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.549699Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ff1badcb-8211-41d2-88e5-8a15bd1340f4 · outbound

This paper cites GPT-4o System Card.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation GPT-4o System Card

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.234443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5f59d159-b01e-489e-9ec7-cc11c16596b9 · outbound

This paper cites Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-17T12:49:05.460002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation efd35ec6-d71b-4fb9-b12d-7ad98d8b43b5 · outbound

This paper cites VideoRAG: Retrieval-augmented generation over video corpus.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation VideoRAG: Retrieval-augmented generation over video corpus

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.508862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3873a045-b778-4f88-88bd-46b136797b74 · outbound

This paper cites Billion-scale similarity search with gpus.IEEE Transactions on Big Data, 7(3):535–547.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Billion-scale similarity search with gpus.IEEE Transactions on Big Data, 7(3):535–547

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.536907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 171d9ac2-4559-4bde-aef4-0b9a9c91cae9 · outbound

This paper cites Audiocaps: Generating captions for audios in the wild.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Audiocaps: Generating captions for audios in the wild

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.500648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 3616e33c-4a6c-4932-82b0-88746133997b · outbound

This paper cites Vista: Visual-textual knowledge graph representation learning.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Vista: Visual-textual knowledge graph representation learning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.491304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0104258a-cce6-44cb-8bee-d25ed7c7864e · outbound

This paper cites Multimodal Reasoning with Multimodal Knowledge Graph.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Multimodal Reasoning with Multimodal Knowledge Graph

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.207309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cad07230-741b-4873-afcf-010b89c2d03c · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks.Ad- vances in Neural Information Processing Systems, 33:9459– 9474.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Retrieval- augmented generation for knowledge-intensive nlp tasks.Ad- vances in Neural Information Processing Systems, 33:9459– 9474

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.547169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation febaa49d-ec5e-4d4b-80f8-0c5e54940461 · outbound

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

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation LLaVA-OneVision: Easy Visual Task Transfer

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.251519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 0a78cc6a-bf21-4150-8576-b4cd8d77157d · outbound

This paper cites LLaV A-neXT- interleave: Tackling multi-image, video, and 3d in large mul- timodal models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation LLaV A-neXT- interleave: Tackling multi-image, video, and 3d in large mul- timodal models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.490100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a0e2be57-b18e-4b8a-88f2-9e32f423fa52 · outbound

This paper cites Blip- 2: bootstrapping language-image pre-training with frozen image encoders and large language models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Blip- 2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.577568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c81b54ef-41af-4d25-ab60-c02569ce7b6e · outbound

This paper cites Visual instruction tuning.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Visual instruction tuning

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.579926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d23aff66-2564-4f95-b5b1-be69231c341d · outbound

This paper cites Valor: Vision-audio- language omni-perception pretraining model and dataset.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Valor: Vision-audio- language omni-perception pretraining model and dataset

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.554939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f1b6f107-a39f-4d35-92ba-bcc8c4af9fdd · outbound

This paper cites Aligning vision to language: Annotation-free multimodal knowledge graph construction for enhanced llms reasoning.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Aligning vision to language: Annotation-free multimodal knowledge graph construction for enhanced llms reasoning

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.497186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d64e4f6c-adfd-4d9d-a61b-0a86101133c0 · outbound

This paper cites Grounding dino: Marrying dino with grounded pre-training for open-set object detection.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Grounding dino: Marrying dino with grounded pre-training for open-set object detection

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.563246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f0191c5b-aef7-4af7-8d78-624d16505200 · outbound

This paper cites Video-chatgpt: Towards detailed video un- derstanding via large vision and language models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Video-chatgpt: Towards detailed video un- derstanding via large vision and language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.567377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5b40edea-6589-489b-97fe-bed2b8995da7 · outbound

This paper cites Vat-kg: Knowledge-intensive multimodal knowl- edge graph dataset for retrieval-augmented generation.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Vat-kg: Knowledge-intensive multimodal knowl- edge graph dataset for retrieval-augmented generation

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.203969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1a95fa81-f997-4363-99ca-1965f646a01f · outbound

This paper cites Learning transferable visual models from natural language supervision.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Learning transferable visual models from natural language supervision

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.472471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ee02ce6a-c3a4-4670-a90e-0edcae3362ac · outbound

This paper cites Accept the modality gap: An exploration in the hyperbolic space.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Accept the modality gap: An exploration in the hyperbolic space

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.478819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 6fb04597-f0d8-4ea7-b587-a965539b72a1 · outbound

This paper cites VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.244972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 330b2476-5970-4725-a9d2-c44bc26f5d1c · outbound

This paper cites Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Retrieval-Augmented Generation: A Comprehensive Survey of Architectures, Enhancements, and Robustness Frontiers

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.241113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 2ea44df0-79b2-4af5-b8f2-11a8cfd4c88a · outbound

This paper cites SALMONN: Towards Generic Hearing Abilities for Large Language Models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation SALMONN: Towards Generic Hearing Abilities for Large Language Models

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-18T02:29:46.683133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 74e20f80-5d56-4a03-8af0-8d2b05932104 · outbound

This paper cites Qwen2 Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Qwen2 Technical Report

Reference 44

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.187836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation d4bc0700-3728-435e-b9dd-3646eee0b222 · outbound

This paper cites Multi-Agent Collaboration Mechanisms: A Survey of LLMs.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.191023Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation b8f2eff0-467a-4585-b54d-525701fff4bf · outbound

This paper cites Audiobench: A universal benchmark for audio large language models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Audiobench: A universal benchmark for audio large language models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.570947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation efbf87df-353b-4bae-904b-4948c44fc270 · outbound

This paper cites Kepler: A unified model for knowledge embedding and pre-trained lan- guage representation.Transactions of the Association for Computational Linguistics, 9:176–194.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Kepler: A unified model for knowledge embedding and pre-trained lan- guage representation.Transactions of the Association for Computational Linguistics, 9:176–194

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.467335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e357d86e-f27e-469b-b969-f2402bb632bb · outbound

This paper cites Internvideo2: Scaling foundation models for mul- timodal video understanding.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Internvideo2: Scaling foundation models for mul- timodal video understanding

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.574241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 9bc6fa6b-fa7e-4a4f-874c-47ad5c2c48ef · outbound

This paper cites Large-scale con- 10 trastive language-audio pretraining with feature fusion and keyword-to-caption augmentation.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Large-scale con- 10 trastive language-audio pretraining with feature fusion and keyword-to-caption augmentation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.475629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 188ee25a-d08a-4aaf-913c-ea9854d41d6a · outbound

This paper cites Qwen2.5-Omni Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Qwen2.5-Omni Technical Report

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.193908Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 1273e86d-6d85-45ee-9fa5-390eef4c42ba · outbound

This paper cites Qwen3-Omni Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Qwen3-Omni Technical Report

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.248350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 8e8e55f7-fa37-42cd-8562-5e7d4a864ed7 · outbound

This paper cites Towards weakly supervised text-to-audio grounding.IEEE Transac- tions on Multimedia.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Towards weakly supervised text-to-audio grounding.IEEE Transac- tions on Multimedia

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.506632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation fd5b61c6-309c-47d6-848f-1f678949a7c8 · outbound

This paper cites Qwen3 Technical Report.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Qwen3 Technical Report

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.231638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 669ead28-4e11-4136-96c9-e40aeaa34652 · outbound

This paper cites MiniCPM-V: A GPT-4V Level MLLM on Your Phone.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:28:24.237628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 545b065d-d6c2-48d6-9371-e382bf36434e · outbound

This paper cites UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-20T00:04:08.732725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 5d802b19-69e6-48f5-b875-d35a6ab86319 · outbound

This paper cites M2conceptbase: A fine-grained aligned concept-centric multimodal knowledge base.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation M2conceptbase: A fine-grained aligned concept-centric multimodal knowledge base

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.538153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation a4a1f017-2af4-47e1-8f6c-57967a49eae6 · outbound

This paper cites Extract, define, canonicalize: An llm-based framework for knowledge graph construction.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Extract, define, canonicalize: An llm-based framework for knowledge graph construction

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.582595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation f26c989e-ae64-444d-83f1-6a9a6caf0fbe · outbound

This paper cites A survey of graph retrieval-augmented generation for customized large language models.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation A survey of graph retrieval-augmented generation for customized large language models

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.224621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation e364adb5-8a67-4636-b742-b3a6124340b0 · outbound

This paper cites dogs”→“dog.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation dogs”→“dog

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.585083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation c1ec6a64-2a89-4114-8a30-ed8bb9e44d8a · outbound

This paper cites an unresolved cited work.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-05-17T01:21:25.587781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation ce6755d8-8e4a-4f38-83ed-4ea65e0ff0a5 · outbound

This paper cites – Do NOT contradict the primary evidence; if conflict exists, ignore the triple.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation – Do NOT contradict the primary evidence; if conflict exists, ignore the triple

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.590736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation cc5b0d66-6dee-49cf-ac7a-e1b7ae20a331 · outbound

This paper cites Query : {QUERY} Retrieved Triples : {TRIPLES_BLOCK} Triple Format : [i] head={h} | relation={r} | tail={t} || head_description={hd} | tail_description={td} Answer : Table 13.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Query : {QUERY} Retrieved Triples : {TRIPLES_BLOCK} Triple Format : [i] head={h} | relation={r} | tail={t} || head_description={hd} | tail_description={td} Answer : Table 13

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.228279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 89d0a112-df36-4569-995e-62d449123e4d · outbound

This paper cites an unresolved cited work.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation Unresolved cited work

Reference 63

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:28:24.255076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Observation 47b36e24-9673-4a99-9eac-42beba4e4cd4 · outbound

This paper cites The audio contains the sound of a bird chirping.

M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation The audio contains the sound of a bird chirping

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T01:21:25.594022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.

Pith citing papers

Observation 1ac6d1cd-77ac-4133-9142-06e9b910f280 · inbound

DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation cites this paper.

DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation M$^3$KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T03:11:54.775186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.