Paper Citation Record · LEDGER

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache

As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2506.11886.

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

pith.paper-citation-record.v1
2506.11886 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T01:10:40.475653Z

measured 38 of 38 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-08T03:16:00.868964Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T22:11:14.344298Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d32e9be9-ef2c-4430-b9bf-712937b1c710 · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.064168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02d1bb4c-cd57-4c9d-8c14-2494a8bd2552 · outbound

This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.133228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb386be-fb77-4d39-a4b4-f5461bb4da0b · outbound

This paper cites PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.220840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77689f63-3157-4247-bc97-f1a0c49a8c57 · outbound

This paper cites Palu: Compressing KV-Cache with Low-Rank Projection.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Palu: Compressing KV-Cache with Low-Rank Projection

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.292088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6253145d-a773-4e12-acdc-ac8697952030 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.380494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6da607bf-3b81-4706-8acf-a729cf6e5bbc · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:42.561101Z

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 b7b21fae-2aca-4a3a-b3b9-908a6c333cce · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:42.280185Z

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 68e19fd9-cb02-46b3-95a7-b72eb6c75299 · outbound

This paper cites SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.672974Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5812b41b-1140-4cc9-be14-481be40d733f · outbound

This paper cites The Llama 3 Herd of Models.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.796301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea84603b-c5ee-4a70-9602-28b9142a0bb8 · outbound

This paper cites Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Challenges in Deploying Long-Context Transformers: A Theoretical Peak Performance Analysis

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:37.895512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99434401-507e-4f4f-b858-2bcab6d94012 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:42.064841Z

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 c5521ef6-9edd-4b9c-ac07-2dcd278e4c3c · outbound

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

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.066968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7240aae5-b597-4d7a-bb9a-2b6eae481e31 · outbound

This paper cites Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.138609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8f7e5ad-7493-4c4b-bf6d-c01e6c2334aa · outbound

This paper cites KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.223015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9fb54cf-ac7a-4c2d-b7a3-31786ecf5f9d · outbound

This paper cites RULER: What's the Real Context Size of Your Long-Context Language Models?.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.303268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46ba7888-c3be-4b12-8c05-e67657da7bb9 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.405115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 967d1b8f-b801-46da-aba6-4b36a56336f4 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.501927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67428f7a-63c7-4a04-9878-4d2b2088ef6b · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache SnapKV: LLM Knows What You are Looking for Before Generation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.578991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adf38444-e51f-42c3-8966-7231c91222ec · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.661837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff632d91-d771-47fd-9d85-475ea280ab99 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.782690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 983d1a8a-e6be-4680-8311-397d95ee450b · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:41.831696Z

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 e7937253-4c7a-41ec-a915-1dfb34afc9f8 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:38.969894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fe3750d-4734-40d0-9fae-ead55c535cea · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:41.661866Z

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 65c08443-1b49-4777-a6b1-5d70180bcccb · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:41.507829Z

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 e0282b44-b765-4fb5-93e1-2489826ff66e · outbound

This paper cites GPT-4 Technical Report.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache GPT-4 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:39.240473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ef5c277-ceb2-4d3a-bfd5-2dad65f6b045 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:41.342504Z

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 b6e55613-4df6-4cc7-995d-c7e0a46085b8 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:39.380955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95c0db8f-a94d-4cb8-afae-3c29ab962c30 · outbound

This paper cites Eigen Attention: Attention in Low-Rank Space for KV Cache Compression.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:39.489964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97ed5edf-350d-439e-8607-810faf00b50a · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:39.600677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 061adc09-550a-45d4-b832-eb41ae823006 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:39.727024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd2bb41e-d2cc-4fd1-b1fc-e96016993a50 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:39.831267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4246cb51-bf02-4602-aaf7-32b841f3ddb0 · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:10:41.137032Z

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 e068253c-41e4-4b36-8de6-4d1079fbc21c · outbound

This paper cites PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:40.035816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a93da625-3f42-4cc3-8641-7cc93e498190 · outbound

This paper cites Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:40.143705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05e59751-bd21-4913-9283-e5589a22469d · outbound

This paper cites an unresolved cited work.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:40.236359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ae29bc8-1ccb-45ae-bb41-224307ebc67d · outbound

This paper cites online" 'onlinestring :=.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache online" 'onlinestring :=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:40.350849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1ff873-8178-4325-85f1-4dc287ea332c · outbound

This paper cites write newline.

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache write newline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T01:10:40.475653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 6c197b14-e90d-4b7e-87a7-c398ac0bdf04 · inbound

When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon cites this paper.

When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:11:14.347967Z

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.