Paper Citation Record · LEDGER

D-Attn: Decomposed Attention for Large Vision-and-Language Models

As of 11 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 2 inbound Pith citation observations for arXiv:2502.01906.

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

pith.paper-citation-record.v1
2502.01906 v2

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T14:05:14.472756Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-30T18:36:56.248838Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T14:55:48.338931Z

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy16
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3b031cd4-e97c-437e-8af5-2f2722b14244 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.290681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adceb6f2-2f75-4290-bab9-57dc011072c9 · outbound

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

D-Attn: Decomposed Attention for Large Vision-and-Language Models Flamingo: a visual language model for few-shot learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.295768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80e6294c-3685-4764-ba54-1a13bfcc929e · outbound

This paper cites OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.300189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88d3230d-c0d5-4073-8b1f-2d8c5e271075 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.304523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e7d843-7f38-41b1-83b1-2eb4595de604 · outbound

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

D-Attn: Decomposed Attention for Large Vision-and-Language Models ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.308714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa9ddf79-68dd-418a-90bc-41a8155328d9 · outbound

This paper cites Are We on the Right Way for Evaluating Large Vision-Language Models?.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Are We on the Right Way for Evaluating Large Vision-Language Models?

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.312984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3ff51b0-5a65-494f-881f-e2d71c255733 · outbound

This paper cites InstructBLIP: Towards general-purpose vision-language models with instruction tuning.

D-Attn: Decomposed Attention for Large Vision-and-Language Models InstructBLIP: Towards general-purpose vision-language models with instruction tuning

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.211198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 192e3792-14de-446e-9c37-4b189678d361 · outbound

This paper cites Flashattention: Fast and memory-efficient exact at- tention with io-awareness.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Flashattention: Fast and memory-efficient exact at- tention with io-awareness

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.321948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9cd7b00-ac84-40cc-88ef-97ac92ff8c1d · outbound

This paper cites Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.326040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17e4642b-7869-4e3d-8473-003ef59eb356 · outbound

This paper cites The Llama 3 Herd of Models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models The Llama 3 Herd of Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.330494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8464cba-c180-44c0-9735-26aad1a99455 · outbound

This paper cites Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Mme: A compre- hensive evaluation benchmark for multimodal large language models, 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.191778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ea370fc4-6ddb-4a39-9fae-a7d71f1b706e · outbound

This paper cites Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Making the v in vqa matter: Elevating the role of image understanding in visual question answer- ing

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.180349Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f001ea89-c505-4f05-8e3e-aa88ff44479f · outbound

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

D-Attn: Decomposed Attention for Large Vision-and-Language Models Gqa: A new dataset for real-world visual reasoning and compositional question answering

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.168505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 09fd5c60-7e62-45a1-a745-39ff9e9c0b50 · outbound

This paper cites Mistral 7B.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Mistral 7B

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.347857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6589d66-e0a2-47d8-8bc5-26891dcdeee7 · outbound

This paper cites Obelics: An open web-scale filtered dataset of interleaved image-text documents.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Obelics: An open web-scale filtered dataset of interleaved image-text documents

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.157328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e9b0923e-e273-4b18-816d-c3bf85ffb1f5 · outbound

This paper cites What matters when building vision-language models?.

D-Attn: Decomposed Attention for Large Vision-and-Language Models What matters when building vision-language models?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.356190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 173997d1-1f41-4af4-a811-6f1d730820b3 · outbound

This paper cites SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension.

D-Attn: Decomposed Attention for Large Vision-and-Language Models SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.359838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e54a25f-f822-42c6-aa14-b949d6a8f2cb · outbound

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

D-Attn: Decomposed Attention for Large Vision-and-Language Models LLaVA-OneVision: Easy Visual Task Transfer

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.363667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08265120-3b95-49cb-970a-de14a62c02b2 · outbound

This paper cites CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts.

D-Attn: Decomposed Attention for Large Vision-and-Language Models CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.367567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 223e6291-37bf-4480-abcf-566f856630a3 · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.371060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 417357ba-842f-48af-a660-a44b75d72d6d · outbound

This paper cites Vila: On pre-training for vi- sual language models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Vila: On pre-training for vi- sual language models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.145461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d4add187-c6aa-4103-beff-e29fcc2406c8 · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Llava-next: Im- proved reasoning, ocr, and world knowledge, 2024

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.134058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 433b69d9-cffa-421c-946e-a6b537f2c9ed · outbound

This paper cites Visual instruction tuning.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Visual instruction tuning

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.122663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 159aa463-374d-4d50-bf25-dc282f902de0 · outbound

This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.

D-Attn: Decomposed Attention for Large Vision-and-Language Models MMBench: Is Your Multi-modal Model an All-around Player?

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.386562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 454579ff-d616-4d8e-a4ae-2d84fc731b64 · outbound

This paper cites Learn to explain: Multimodal reasoning via thought chains for science question answering.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Learn to explain: Multimodal reasoning via thought chains for science question answering

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.390358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2087160c-c19c-4a68-b326-69fbe4f4b50f · outbound

This paper cites Generation and comprehension of unambiguous object descriptions.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Generation and comprehension of unambiguous object descriptions

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.103440Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0a838e0a-a8ac-4e61-a576-cb261aadd4cf · outbound

This paper cites Im2text: Describing images using 1 million captioned pho- tographs.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Im2text: Describing images using 1 million captioned pho- tographs

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.091372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 298d547f-edea-4791-9c8a-c3972b2f4acd · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Learning transferable visual models from natural language supervi- sion

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.401848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f977e5a-79b0-4a48-ba80-7f0ccac233ef · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Direct preference optimization: Your language model is secretly a reward model

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.072188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 02a2530b-e778-49ae-a070-33c3f99b6b96 · outbound

This paper cites Deepspeed: System optimizations enable train- ing deep learning models with over 100 billion parame- ters.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Deepspeed: System optimizations enable train- ing deep learning models with over 100 billion parame- ters

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.060526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ee7fec9c-38a3-423e-bd96-273086dfc69c · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.412579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de7d92c9-5105-4721-ad2a-f8374590bd50 · outbound

This paper cites Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Conceptual captions: A cleaned, hypernymed, im- age alt-text dataset for automatic image captioning

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.042113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9960457e-7d6a-4517-b50a-bbd2e35a012f · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.420713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b44540fb-c5fc-4b17-b7b3-8a751062a856 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.424620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba9cbdde-fc6f-4357-a5c5-a4c2309de7d8 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.429018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f04384-5289-4c8e-bff2-5b4a4ec89be1 · outbound

This paper cites Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.433108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03869c0e-baec-44e3-8b76-a4125807fb12 · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.030824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ca2618b5-70a5-477b-9beb-1d596975b5e7 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models LLaMA: Open and Efficient Foundation Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.441568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3841db45-5b6e-4a84-b4cb-5a59cc3f7c75 · outbound

This paper cites Attention is all you need.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Attention is all you need

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.445639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9376278d-7200-45de-a595-6f5db885139e · outbound

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

D-Attn: Decomposed Attention for Large Vision-and-Language Models Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.450118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1abfd77-5bdb-42aa-813c-93b7497d5419 · outbound

This paper cites xgen-mm (blip-3): A family of open large multimodal models.

D-Attn: Decomposed Attention for Large Vision-and-Language Models xgen-mm (blip-3): A family of open large multimodal models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.454269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fd189c9-7df5-44e4-9779-fc85c463905f · outbound

This paper cites Sigmoid loss for language image pre-training.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Sigmoid loss for language image pre-training

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.458648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5354be34-96a8-4711-963a-93cfce087c8d · outbound

This paper cites Root mean square layer nor- malization.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Root mean square layer nor- malization

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:15.004175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a6dbfcef-af61-40a4-b18e-79bfe137ddfb · outbound

This paper cites InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output.

D-Attn: Decomposed Attention for Large Vision-and-Language Models InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T14:05:14.467898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a114ea8-42d5-4c90-a50d-934f99259a63 · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023.

D-Attn: Decomposed Attention for Large Vision-and-Language Models Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:05:14.992477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

Observation 5edf4a9f-7223-4950-9f63-3642631244a3 · inbound

RAVE: Re-Allocating Visual Attention in Large Multimodal Models cites this paper.

RAVE: Re-Allocating Visual Attention in Large Multimodal Models D-Attn: Decomposed Attention for Large Vision-and-Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-20T11:13:13.456501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6161ec78-0fa6-4416-991c-7ef33d749c76 · inbound

RAVE: Re-Allocating Visual Attention in Large Multimodal Models cites this paper.

RAVE: Re-Allocating Visual Attention in Large Multimodal Models D-Attn: Decomposed Attention for Large Vision-and-Language Models

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-07-01T14:55:48.340671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.