Paper Citation Record · LEDGER

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 30 inbound Pith citation observations for arXiv:2405.12981.

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

pith.paper-citation-record.v1
2405.12981 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 30 of 30 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 30 of 30 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T17:22:46.999943Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation c00b63c8-c9a6-4544-978d-b68ed14a0472 · inbound

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation cites this paper.

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-23T18:33:19.446287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ec66c560-a6b2-4182-a552-453dd9e2a2e0 · inbound

PoM: Efficient Image and Video Generation with the Polynomial Mixer cites this paper.

PoM: Efficient Image and Video Generation with the Polynomial Mixer Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T17:22:46.999943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baa5f6ec-1d50-4f0b-9471-2fe7120524d9 · inbound

Hymba: A Hybrid-head Architecture for Small Language Models cites this paper.

Hymba: A Hybrid-head Architecture for Small Language Models Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T16:20:32.344744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24e3e211-2a95-4ad7-ae8a-add9f701ff2f · inbound

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning cites this paper.

CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-12T12:13:55.149273Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 592c3a29-2acc-4656-848d-50800257f37c · inbound

MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache cites this paper.

MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T11:37:07.553067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ff2fb3-099b-47c4-8c1a-56e45b31dc06 · inbound

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity cites this paper.

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T23:46:01.984234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0785f33-eacf-4f05-ab0a-3c3e6e476661 · inbound

UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices cites this paper.

UniForm: A Reuse Attention Mechanism Optimized for Efficient Vision Transformers on Edge Devices Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T23:37:44.871522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3572522b-9059-4164-93e1-a936006ebe83 · inbound

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression cites this paper.

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T13:52:48.622944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5c07440-d1ed-432c-a602-7b2ea45b4c59 · inbound

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs cites this paper.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T11:57:17.878098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 357356ce-20ee-44fa-b58b-cab024cf6828 · inbound

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression cites this paper.

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T05:32:29.385894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6d12d0e-1a79-4b0e-8f87-f82d9fe68267 · inbound

Multi-matrix Factorization Attention cites this paper.

Multi-matrix Factorization Attention Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T00:55:03.777756Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc63f34-a742-404f-b05d-86d8dcaa63a1 · inbound

A Survey on Large Language Model Acceleration based on KV Cache Management cites this paper.

A Survey on Large Language Model Acceleration based on KV Cache Management Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 205

Resolution: unresolved; no resolver link, observed 2026-08-11T00:38:48.814000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0982b95-36e1-4cb1-8f07-7655903b600f · inbound

Foundations of Large Language Models cites this paper.

Foundations of Large Language Models Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T20:14:58.581590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a8512ca-d088-4f2a-b192-7d6577b5871b · inbound

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models cites this paper.

Sigma: Differential Rescaling of Query, Key and Value for Efficient Language Models Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-10T15:50:21.846487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60eeb619-40af-4ecb-9862-e62d815b8235 · inbound

Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression cites this paper.

Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-23T04:17:31.245179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 1db8d200-bea1-4583-a4f8-07dca902121d · inbound

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach cites this paper.

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-12T15:39:41.169681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d4937893-d0a2-45b9-8c82-11ad5be1b371 · inbound

Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents cites this paper.

Position: Episodic Memory is the Missing Piece for Long-Term LLM Agents Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-08T14:13:37.965936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30d4b816-ebab-44fb-b757-ee0633875c68 · inbound

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache cites this paper.

QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T04:28:03.903083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bbe0a22-fc85-4ac7-81a7-82c15fcbdcf7 · inbound

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections cites this paper.

MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T22:34:07.961504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd97bfa7-81dd-4579-b112-b259b2a85479 · inbound

Hardware-Efficient Attention for Fast Decoding cites this paper.

Hardware-Efficient Attention for Fast Decoding Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T13:32:29.855424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6a8c350-03bf-426b-891a-a5d23d81a1fd · inbound

KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding cites this paper.

KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional Embedding Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T17:20:25.790122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 345bb7a4-d061-4786-9478-af7175703411 · inbound

CaliDrop: KV Cache Compression with Calibration cites this paper.

CaliDrop: KV Cache Compression with Calibration Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T13:57:15.661526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d5022ab-4df1-4ddb-b02e-098ef4e89e67 · inbound

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference cites this paper.

TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill and Decode Inference Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T17:55:09.661574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0afe267d-674f-4f95-8d75-5f91593e0c76 · inbound

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing cites this paper.

Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:58:12.051857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 75f6d43b-16fc-4490-bdf2-28c20b0612d6 · inbound

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models cites this paper.

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-11T02:45:57.887306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3673d03d-8509-48e2-be5b-673b600ca091 · inbound

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models cites this paper.

Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:03:50.629580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 3a38211c-62ab-4de3-a429-0a1f48999f38 · inbound

Do Value Vectors in Deep Layers Need Context from the Residual Stream? cites this paper.

Do Value Vectors in Deep Layers Need Context from the Residual Stream? Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 64

Resolution: verified exact; arxiv_id, observed 2026-07-01T23:16:23.469169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 306faa8c-84e0-49b9-808f-58f778b2b301 · inbound

Do Value Vectors in Deep Layers Need Context from the Residual Stream? cites this paper.

Do Value Vectors in Deep Layers Need Context from the Residual Stream? Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T12:41:19.361685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94bdc96c-9f3f-447c-be23-74ce6c3bbf63 · inbound

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents cites this paper.

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:36:44.309590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 347be885-1d25-4ac8-91f9-9c10bb0815f5 · inbound

SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling cites this paper.

SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling Reducing Transformer Key-Value Cache Size with Cross-Layer Attention

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T09:51:03.342951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.