S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching | Paper Citation Record

Observation ca2a51f1-dc47-4964-b012-a1dd5f9f0bb0 · outbound

This paper cites Kevin , booktitle =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Kevin , booktitle =

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.561317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e1fa7008-189f-4fb4-bba0-5b632d58e9ab · outbound

This paper cites 2024 , editor =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , editor =

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.552353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e7b7ec31-5c22-4b54-bd2e-b448b6e85b72 · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.542818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7e9824e8-b48f-43ef-93ae-9df6a097b267 · outbound

This paper cites an unresolved cited work.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-05T00:47:33.533711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d93c28b2-5366-48b0-a9d4-d6fef32114d0 · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.523579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 31e0af22-f551-476d-8f3b-e5b3456b72d2 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.513273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f785353b-b64f-48bf-96ec-a800fc0197e8 · outbound

This paper cites Proceedings of the 29th Symposium on Operating Systems Principles , pages =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Proceedings of the 29th Symposium on Operating Systems Principles , pages =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:30.522015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f72b195-05a8-451c-9fc5-10980d5e10a4 · outbound

This paper cites Efficiently Scaling Transformer Inference , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Efficiently Scaling Transformer Inference , url =

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.503277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 34f22967-12aa-472d-a5b1-e8a94f101ad8 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching The Twelfth International Conference on Learning Representations , year=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:30.642285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691181d7-76e6-4e10-a699-5d0c256355da · outbound

This paper cites 2024 , editor =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , editor =

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.486938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 96442abc-715c-44ae-a3cc-53420fa48f49 · outbound

This paper cites H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models , url =

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.477607Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2e66f4d1-c7a2-4348-8d72-6b12f51579d6 · outbound

This paper cites 2024 , editor =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , editor =

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:30.772071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315d3c13-3af7-47d1-8473-d589b788d116 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.462746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation fc685669-20f4-4d6e-80e2-b0f2b4b0d6b6 · outbound

This paper cites and Shao, Yakun Sophia and Keutzer, Kurt and Gholami, Amir , booktitle =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching and Shao, Yakun Sophia and Keutzer, Kurt and Gholami, Amir , booktitle =

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:30.908861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4efd74d8-1899-4f24-8fdd-f644d4fedfbb · outbound

This paper cites and Yun, Sangdoo and Song, Hyun Oh , booktitle =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching and Yun, Sangdoo and Song, Hyun Oh , booktitle =

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.453891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ea932172-06f1-4298-93f3-455e419356f4 · outbound

This paper cites Loki: Low-rank Keys for Efficient Sparse Attention , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Loki: Low-rank Keys for Efficient Sparse Attention , url =

Reference 16

Resolution: verified exact; doi, observed 2026-08-05T00:47:32.100165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation df09c94c-20a3-4ce6-a6f1-65a2e37b81c4 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.442368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b68f624-eca7-4138-a384-590c1a896021 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.157053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca55959d-29a0-4e12-b011-b13db87215f3 · outbound

This paper cites 2024 , author =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , author =

Reference 19

Resolution: verified exact; doi, observed 2026-08-05T00:47:32.090511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b3a6af6-52e2-4d19-87cd-8f13514c7c5c · outbound

This paper cites 2026 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2026 , eprint=

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.427262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6cc58662-430f-4c55-bcaf-fd6bc5a20143 · outbound

This paper cites Abdelfattah and Kai-Chiang Wu , booktitle=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Abdelfattah and Kai-Chiang Wu , booktitle=

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.417990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e8740fea-53b0-4c24-be2a-e12fcd0340e4 · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.367991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf4062ff-7a99-4c79-8afc-ef5f93d21879 · outbound

This paper cites 2024 , editor =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , editor =

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.403455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3e4fafd8-1e05-41ee-9c5f-9aeb43f9330c · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.393921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f66d6096-c301-4ba1-8c61-be6d6923eda6 · outbound

This paper cites SALS: Sparse Attention in Latent Space for KV Cache Compression , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching SALS: Sparse Attention in Latent Space for KV Cache Compression , url =

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.384386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8e24b6fc-0ff5-4abf-9065-984f1311bed9 · outbound

This paper cites Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time , url =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.526700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c51682d-3c34-4618-ad94-2fad194bcc89 · outbound

This paper cites 2025 , editor =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , editor =

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.368853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d3cde837-4a31-49dc-be5e-25b8df999b73 · outbound

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

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching SnapKV: LLM Knows What You are Looking for Before Generation , url =

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.595810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 297468be-f0bf-4f6d-919d-493c27fad5e5 · outbound

This paper cites 2025 , editor =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , editor =

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.359766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac85239f-4b9c-49f3-9575-a74715efe852 · outbound

This paper cites A Survey on Large Language Model Acceleration based on.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching A Survey on Large Language Model Acceleration based on

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.640761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d0a32dc-d528-42fe-83d6-2749609e6e03 · outbound

This paper cites TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T00:47:32.072537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 26d06a1f-419d-4fe6-af05-97961f8874d8 · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.696023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e77e86eb-76bd-4672-9a29-1e985c1a81c4 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.742981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12398503-5aad-4fdd-b980-7705109d5de5 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.827827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 911b9607-27fc-4daa-9bb8-971bce9163c9 · outbound

This paper cites 2024 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , eprint=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.919885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1324181c-58d3-4484-8999-a4a7a9fd2ffd · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.930519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d05ff1e-a8a5-4f52-b8bc-87d96f1dd72d · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.933372Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76237b90-9156-45dd-a47e-fe8e91a18f00 · outbound

This paper cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks , url =

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T00:47:33.304877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 31729932-8273-437a-9dd1-7b2a879a886c · outbound

This paper cites , title =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching , title =

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.938854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63a5ca5f-cfd3-4774-b22e-1a478a9b066f · outbound

This paper cites A survey on large language model based autonomous agents , volume=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching A survey on large language model based autonomous agents , volume=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.941752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7181d6cf-2876-4a95-8292-7c6c2ddea353 · outbound

This paper cites 2024 , url=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2024 , url=

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.944785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4aeca21c-c425-42fe-9cd6-f7e7ae10cf88 · outbound

This paper cites doi:10.5281/zenodo.12608602 , url =.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching doi:10.5281/zenodo.12608602 , url =

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.947516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d68c2270-0178-4736-a90f-6f3cd1f9fee9 · outbound

This paper cites 2025 , eprint=.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching 2025 , eprint=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.950471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aadf500-030a-4a9e-850d-aa4f0f002a10 · outbound

This paper cites an unresolved cited work.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.953029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea66798-269a-441b-a43a-97c5d74ddecd · outbound

This paper cites an unresolved cited work.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Unresolved cited work

Reference 45

Resolution: unresolved; raw_fallback, observed 2026-08-05T00:47:33.272395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a1a32da-7355-4dad-b092-a368df3dad70 · outbound

This paper cites L ong B ench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching L ong B ench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.958173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3b524cf-cd6c-453e-84be-d0436fd6c546 · outbound

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

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching GQA : Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.960879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 918e888f-f2c2-43d1-99d5-985f397752f9 · outbound

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

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching Eigen Attention: Attention in Low-Rank Space for KV Cache Compression

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.963464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c67b08-8044-4825-ad91-e8865d1d5c47 · outbound

This paper cites L ong B ench: A Bilingual, Multitask Benchmark for Long Context Understanding.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching L ong B ench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.966230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0439dece-eeb8-4b13-a1d5-772af7b3d403 · outbound

This paper cites P yramid I nfer: Pyramid KV Cache Compression for High-throughput LLM Inference.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching P yramid I nfer: Pyramid KV Cache Compression for High-throughput LLM Inference

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T00:47:31.969053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3daff83b-c04f-4e36-b613-66003eebc1d1 · outbound

This paper cites T a DA : Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching T a DA : Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering

Reference 51

Resolution: verified exact; doi, observed 2026-08-05T00:47:32.014256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 055b864d-2ecd-4d65-b460-3e0c9ad73c2d · outbound

This paper cites TALE : Token-Adaptive Low-Rank KVC ache Approximation with Reconstruction Elimination.

S$^4$R: Selective Sampling, Subspaces, and Sparse Reconstruction for Compressed Long-Context KV Caching TALE : Token-Adaptive Low-Rank KVC ache Approximation with Reconstruction Elimination

Reference 52

Resolution: verified exact; doi, observed 2026-08-05T00:47:32.004466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers