Paper Citation Record · LEDGER

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast

As of 6 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2605.08314.

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

pith.paper-citation-record.v1
2605.08314 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-12T00:59:43.488204Z

measured 32 of 32 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-19T15:35:25.103868Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-19T15:37:37.215780Z

Reference resolution

31 of 31 outbound references displayed

verified exact12
verified fuzzy19
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 57f051cf-fece-485c-a0cd-c26758d65b88 · outbound

This paper cites ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-20T13:49:33.894132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c8ff150d-342d-4c1e-bc17-984812adf0ca · outbound

This paper cites SVD-LLM: Truncation-aware singular value decomposition for large language model compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast SVD-LLM: Truncation-aware singular value decomposition for large language model compression

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.906128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2cc59db5-155d-4424-b3fe-22585d5406f5 · outbound

This paper cites Accurate and efficient singular value decomposition for LLMs via decay-aware rank allocation and feature-preserved weight update.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Accurate and efficient singular value decomposition for LLMs via decay-aware rank allocation and feature-preserved weight update

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.902294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 832e14ef-f3b0-40df-a8ad-4acabf162488 · outbound

This paper cites Gf-svd:Globalknowledge-infusedsingularvaluedecompositionoflargelanguagemodels.Information Fusion, page 103774.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Gf-svd:Globalknowledge-infusedsingularvaluedecompositionoflargelanguagemodels.Information Fusion, page 103774

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.904206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 35aae4e1-84c9-4e6b-b977-45cf078b2def · outbound

This paper cites Saes-svd: Self-adaptive suppression of accumulated and local errors for svd-based llm compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Saes-svd: Self-adaptive suppression of accumulated and local errors for svd-based llm compression

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.559585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 48b59115-9651-422d-8432-52e4057fda94 · outbound

This paper cites DipSVD: Dual-importance protected SVD for efficient LLM compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast DipSVD: Dual-importance protected SVD for efficient LLM compression

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.911340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation febd66eb-90ac-4a63-b9c3-8c6bd15518c7 · outbound

This paper cites Modegpt:Modulardecompositionforlargelanguagemodelcompression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Modegpt:Modulardecompositionforlargelanguagemodelcompression

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.925811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1154a2f1-6760-471f-9522-d087166cefc3 · outbound

This paper cites SVD-LLMv2:Optimizingsingular value truncation for large language model compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast SVD-LLMv2:Optimizingsingular value truncation for large language model compression

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.923995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1fc085b1-dee0-45ac-98c8-68ed693e5009 · outbound

This paper cites Dobi-svd: Differentiable svd for LLM compression and some new perspectives.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Dobi-svd: Differentiable svd for LLM compression and some new perspectives

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.927648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation da39ce24-eb5b-4a53-bd9b-a527d31a942b · outbound

This paper cites AdaSVD: Adaptive singular value decomposition for large language models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast AdaSVD: Adaptive singular value decomposition for large language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.929385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae1393c9-a8a8-46af-bfc7-8df356d97a85 · outbound

This paper cites Layer-wisedynamicrankforcompressing large language models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Layer-wisedynamicrankforcompressing large language models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.519766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2252d99c-f38f-48bc-88a6-31e38ab62154 · outbound

This paper cites Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.524701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 212cbc6b-e8ea-4824-a079-42261294164d · outbound

This paper cites Data-awarelow-rankcompression for large {nlp} models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Data-awarelow-rankcompression for large {nlp} models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.920049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 44f59588-9b72-459c-97b0-96c75767b4ae · outbound

This paper cites Adaptive rank selections for low-rank approximation of language models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Adaptive rank selections for low-rank approximation of language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.916519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9a78fc8d-3cc2-4a59-982a-a90173837b45 · outbound

This paper cites Language model compression with weighted low-rank factorization.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Language model compression with weighted low-rank factorization

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.548872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b36a9964-d035-46c9-9975-596dd2334891 · outbound

This paper cites Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Generalized Fisher-Weighted SVD: Scalable Kronecker-Factored Fisher Approximation for Compressing Large Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-07-17T00:20:38.751091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d1c8e946-ce32-44f0-a260-0504e260f081 · outbound

This paper cites Efficient one-shot compression via low-rank local feature distillation.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Efficient one-shot compression via low-rank local feature distillation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.918389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ea6f77e1-6073-4434-8a60-72bdfa948ca9 · outbound

This paper cites Dobi-svd: Differen- tiablesvdforllmcompressionandsomenewperspectives.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Dobi-svd: Differen- tiablesvdforllmcompressionandsomenewperspectives

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.921871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fd7b9590-4a85-4f3e-a912-8beb5b72b3d5 · outbound

This paper cites Aa-svd: Anchored and adaptive svd for large language model compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Aa-svd: Anchored and adaptive svd for large language model compression

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.534108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7a0de046-1c0d-41d0-808a-0174984ded94 · outbound

This paper cites Zero sum svd: Balancing loss sensitivity for low rank llm compression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Zero sum svd: Balancing loss sensitivity for low rank llm compression

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.564527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation be3ff320-1f61-43fd-bd74-b91e8b21d444 · outbound

This paper cites Abdelfattah, and Kai-Chiang Wu.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Abdelfattah, and Kai-Chiang Wu

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.932684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c136ed24-8591-49dd-b7a3-8a79b3aedca4 · outbound

This paper cites xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast xKV: Cross-Layer KV-Cache Compression via Aligned Singular Vector Extraction

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-28T02:04:08.438618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1b763f91-f068-413c-a0d8-82af8bd1fcc2 · outbound

This paper cites Qsvd: Efficient low-rank approximation for unified query-key-value weight compression in low-precision vision-language models.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Qsvd: Efficient low-rank approximation for unified query-key-value weight compression in low-precision vision-language models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.574354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 347326f6-2de4-4b54-a3a3-55255101d7bd · outbound

This paper cites Eigen attention: Attention in low-rankspaceforkvcachecompression.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Eigen attention: Attention in low-rankspaceforkvcachecompression

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.931010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 22000344-12d1-4a3f-9616-74d57476fa4f · outbound

This paper cites Blind restoration of high-resolution ultrasound video.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Blind restoration of high-resolution ultrasound video

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.907946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c37f2696-628f-48b2-957e-c8f6c0f1901b · outbound

This paper cites Sada:Stability-guidedadaptivediffusionacceleration.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Sada:Stability-guidedadaptivediffusionacceleration

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.909613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ed508b06-597f-41fc-8973-43403649c53f · outbound

This paper cites Acceleratingdenoisinggenerativemodelsisaseasyaspredicting second-order difference.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Acceleratingdenoisinggenerativemodelsisaseasyaspredicting second-order difference

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.913024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7964839a-4ca7-42b4-a804-0fbedde5af2c · outbound

This paper cites Zeus: Accelerating diffusion models with only second-order predictor.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Zeus: Accelerating diffusion models with only second-order predictor

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.544330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f6982b45-32d9-41ed-9bdd-7e9a8105d1fd · outbound

This paper cites Efficient localization and spatial distribution modelingofcanopypalmsusinguavimagery.IEEETransactionsonGeoscienceandRemoteSensing.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Efficient localization and spatial distribution modelingofcanopypalmsusinguavimagery.IEEETransactionsonGeoscienceandRemoteSensing

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.914827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 616849df-c74d-42ee-af31-d78b574e37a4 · outbound

This paper cites Scalable dual coordinate descent for kernel methods.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Scalable dual coordinate descent for kernel methods

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-14T09:02:22.900449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f01b762f-393d-4d68-bc81-facdb3ae7f54 · outbound

This paper cites Enhanced cyclic coordinate descent methods for elastic net penalized linear models.Advances in Neural Information Processing Systems, 38:137240–137281.

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast Enhanced cyclic coordinate descent methods for elastic net penalized linear models.Advances in Neural Information Processing Systems, 38:137240–137281

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-12T08:31:26.569261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 42280baa-3908-4190-a0fa-e6bfd89f77af · inbound

ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest cites this paper.

ELDOR: A Dataset and Benchmark for Illegal Gold Mining in the Amazon Rainforest FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast

Reference 127

Resolution: verified exact; local_arxiv, observed 2026-05-19T15:37:37.218149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.