Paper Citation Record · LEDGER

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models

As of 10 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 0 inbound Pith citation observations for arXiv:2502.02406.

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

pith.paper-citation-record.v1
2502.02406 v3

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T12:23:40.585910Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact1
verified fuzzy17
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 23cbddc7-6441-4224-8f25-fc14a084dbc9 · outbound

This paper cites write newline.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.403541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e68b4704-9172-4ff5-a8f0-b34c1ac43dd8 · outbound

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

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Flamingo: a visual language model for few-shot learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.294271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b4c60257-454e-4756-866d-3a71467c3e66 · outbound

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

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.414321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aebbd7d9-714b-4fd8-9d13-9663f9ba0898 · outbound

This paper cites Longformer: The Long-Document Transformer.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Longformer: The Long-Document Transformer

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.420888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5318c903-e261-442d-ae39-3add2963c798 · outbound

This paper cites an unresolved cited work.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-09T12:23:41.283500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 441df307-bd25-4c85-acb1-14b589bc797c · outbound

This paper cites Striped Attention: Faster Ring Attention for Causal Transformers.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Striped Attention: Faster Ring Attention for Causal Transformers

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.430129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e4acc3f-d938-4512-af51-bd0dea97e9e4 · outbound

This paper cites Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.434769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df26055-1cd8-4052-94ac-2ce8b2a4c3f7 · outbound

This paper cites Adapting language models to compress contexts.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Adapting language models to compress contexts

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.266075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7c55aa77-e64d-4ed6-afcb-cd2196b2a9dd · outbound

This paper cites M., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models M., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.443931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be44c55a-50ac-41c7-b535-6ee346f5d340 · outbound

This paper cites Nvlm: Open frontier-class multimodal llms.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Nvlm: Open frontier-class multimodal llms

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.248285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 55554418-4064-4083-ad50-9ffaf6b3814e · outbound

This paper cites Flash A ttention-2: Faster attention with better parallelism and work partitioning.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Flash A ttention-2: Faster attention with better parallelism and work partitioning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.452814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb45b3b9-ddf3-4fa4-8e70-4bd743cb4629 · outbound

This paper cites Y., Ermon, S., Rudra, A., and R \'e , C.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Y., Ermon, S., Rudra, A., and R \'e , C

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.456933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94261df9-98b0-48d8-bc7a-1e5e3ce7da21 · outbound

This paper cites S., Monga, R., Chen, K., Devin, M., Le, Q.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models S., Monga, R., Chen, K., Devin, M., Le, Q

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.224522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation aedfadff-b42b-4e90-9a3d-fa558079e64d · outbound

This paper cites LongNet: Scaling Transformers to 1,000,000,000 Tokens.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models LongNet: Scaling Transformers to 1,000,000,000 Tokens

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.464868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60cc123-5f52-4e57-800f-b4b14048891c · outbound

This paper cites The design and operation of CloudLab.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models The design and operation of CloudLab

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.213838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3224933a-38ff-426d-b9eb-2025c44d3273 · outbound

This paper cites Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.472983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7b5788d-0ecb-4cae-808c-301145995424 · outbound

This paper cites The Llama 3 Herd of Models.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models The Llama 3 Herd of Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.477312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eeeeecb0-6ee5-478b-bb91-1eac35ee2559 · outbound

This paper cites Llava-uhd: An lmm perceiving any aspect ratio and high-resolution images.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Llava-uhd: An lmm perceiving any aspect ratio and high-resolution images

Reference 18

Resolution: verified exact; doi, observed 2026-08-09T12:23:40.634688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1d2b86f3-3ce3-49ee-bac1-a38a8925cbb3 · outbound

This paper cites K., Jia, M., Cao, X., Shah, A., Shrivastava, A., and Lim, S.-N.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models K., Jia, M., Cao, X., Shah, A., Shrivastava, A., and Lim, S.-N

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.203438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e1ddd6bc-bfa5-4fc8-9098-56725910e111 · outbound

This paper cites Video ReCap: Recursive Captioning of Hour-Long Videos.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Video ReCap: Recursive Captioning of Hour-Long Videos

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.491200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63d306a6-146e-47f2-b971-f1a38d53bb57 · outbound

This paper cites A., Tanaka, M., Zhang, C., Zhang, M., Aminadabi, R.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models A., Tanaka, M., Zhang, C., Zhang, M., Aminadabi, R

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.495082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ee31d37-2d85-4086-9cd2-7a58eb10fbae · outbound

This paper cites Reformer: The efficient transformer.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Reformer: The efficient transformer

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.498688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd60d2e3-059a-452a-a70d-ae25d0daed60 · outbound

This paper cites A., Casper, J., Lym, S., McAfee, L., Andersch, M., Shoeybi, M., and Catanzaro, B.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models A., Casper, J., Lym, S., McAfee, L., Andersch, M., Shoeybi, M., and Catanzaro, B

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.186213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7f6189eb-792e-44ad-a149-da35816a6ff4 · outbound

This paper cites A., Casper, J., Lym, S., McAfee, L., Andersch, M., Shoeybi, M., and Catanzaro, B.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models A., Casper, J., Lym, S., McAfee, L., Andersch, M., Shoeybi, M., and Catanzaro, B

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.175383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 83f57cc7-d32f-477a-9dda-d00ed98de030 · outbound

This paper cites M., Kiela, D., Cord, M., and Sanh, V.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models M., Kiela, D., Cord, M., and Sanh, V

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.164568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2460e5a7-2fbb-46b3-a919-30a1280278e6 · outbound

This paper cites MIMIC-IT: Multi-Modal In-Context Instruction Tuning.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models MIMIC-IT: Multi-Modal In-Context Instruction Tuning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.513418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60026c8-84b5-428f-9b58-d1c9ec52e47d · outbound

This paper cites P., Ma, X., Stoica, I., Gonzalez, J.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models P., Ma, X., Stoica, I., Gonzalez, J

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.153717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation be1f82a0-b4b0-4d61-bfd9-1e27e0cb9e6d · outbound

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

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.142932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fd1e80ac-e63a-4310-a9a9-39bf3e74e556 · outbound

This paper cites an unresolved cited work.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-09T12:23:41.132089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d7881f19-2f4d-4c98-a88c-a836db4bedd2 · outbound

This paper cites Ringattention with blockwise transformers for near-infinite context.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Ringattention with blockwise transformers for near-infinite context

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.121090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e6297378-2b6d-428a-b06c-488d05e77eee · outbound

This paper cites NVILA: Efficient Frontier Visual Language Models.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models NVILA: Efficient Frontier Visual Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.532423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8989cd5-06b8-40c3-b946-9947e56522ca · outbound

This paper cites Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.536435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5554898-8713-4103-9a92-9742951063dc · outbound

This paper cites R., Ganger, G.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models R., Ganger, G

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.540566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74ddb37f-4cc6-4e0e-9864-635d472ea920 · outbound

This paper cites Momentor: advancing video large language model with fine-grained temporal reasoning.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Momentor: advancing video large language model with fine-grained temporal reasoning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.110012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation db78e0b2-276a-4709-99f1-bd534e6608c5 · outbound

This paper cites ModServe : Scalable and resource-efficient large multimodal model serving, 2025.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models ModServe : Scalable and resource-efficient large multimodal model serving, 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.548348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06db48e3-66b4-4590-8a0d-9129585b9bbc · outbound

This paper cites Zero: memory optimizations toward training trillion parameter models.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Zero: memory optimizations toward training trillion parameter models

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.098690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 379d8cdf-8b39-4175-8596-df4581f53c59 · outbound

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

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.556139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba04c592-e6b8-4068-9537-dc810042bf83 · outbound

This paper cites Repository-level prompt generation for large language models of code.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Repository-level prompt generation for large language models of code

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.087584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6895e989-0ca5-4de7-a58c-b953c8279411 · outbound

This paper cites PEARL : Prompting large language models to plan and execute actions over long documents.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models PEARL : Prompting large language models to plan and execute actions over long documents

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.075061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a06ddf6a-335b-4569-b1f9-33d6e3a8227d · outbound

This paper cites T., and Cox, D.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models T., and Cox, D

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.567345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 835f1694-a240-4085-bdad-6310f2cb8dbf · outbound

This paper cites N., Kaiser, L., and Polosukhin, I.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models N., Kaiser, L., and Polosukhin, I

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.570913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1dc54ac-ab78-4c1f-acee-58b39e7581c2 · outbound

This paper cites mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.574541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c79bfde-886f-459b-bfcf-e69046163793 · outbound

This paper cites Big bird: transformers for longer sequences.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Big bird: transformers for longer sequences

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T12:23:41.057941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5bd7e58e-7aff-40c9-ac3c-fb150b07ea85 · outbound

This paper cites R epo C oder: Repository-level code completion through iterative retrieval and generation.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models R epo C oder: Repository-level code completion through iterative retrieval and generation

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.582047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da7a0ffc-6d1b-4c9c-9f65-a080c283e80c · outbound

This paper cites Mini GPT -4: Enhancing vision-language understanding with advanced large language models.

LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models Mini GPT -4: Enhancing vision-language understanding with advanced large language models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T12:23:40.585910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.