Pith. sign in

Paper Citation Record · LEDGER

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

As of 22 August 2026, this Paper Citation Record lists 50 of 50 outbound references and 19 inbound Pith citation observations for arXiv:2412.14838.

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

pith.paper-citation-record.v1
2412.14838 v4

Coverage vector

measured 50 of 50 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:57:18.009163Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 19 of 19 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:05:31.660385Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

50 of 50 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved50
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation cdb955a1-b0b5-47d1-a8a5-4cdc195befa6 · outbound

This paper cites GPT-4 Technical Report.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.870572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.870572Z digest=sha256:e28308fd586b8bb223e7c87072357f3e2cb0d3049392847389a3b9ea0090757b

Observation 706b6b14-9c0f-45c9-b578-76fc6858aec2 · outbound

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

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.874582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.874582Z digest=sha256:ff5947790d6245d67e73ccca9d64481bb25ae95179c6cfd9fa4aaf7aa9deb5c3

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

This paper cites Reducing Transformer Key-Value Cache Size with Cross-Layer Attention.

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.

source=arxiv_source observed=2026-08-11T11:57:17.878098Z digest=sha256:8f5b4639933e7c051fec8971d75cbdd9a77d2f7f62cc58a11f3139d6a480d556

Observation fcb38d2c-4ed8-421c-ae19-bdb01d058638 · outbound

This paper cites InternLM2 Technical Report.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs InternLM2 Technical Report

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.881513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.881513Z digest=sha256:f20019ce2cf0afd0cc6d34d29efbb3db8aad8591293b5d877af9a52e3a4d6d6a

Observation fc6c33ed-3696-45de-a284-234da01e05e6 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.884414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.884414Z digest=sha256:cc25b1c2a9d0864f485c29ad46e73034134259aa950390d657eaa61f0b0dec4b

Observation 8f2ee744-cd52-4df2-bab6-34c6e73cd618 · outbound

This paper cites A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.887697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.887697Z digest=sha256:152cc751d9ad472d141949001466844a45ddffdd0fe1b7e401c259d0e38ebbf4

Observation da181182-e139-424a-8ae6-ff3b5bb27b5b · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.891117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.891117Z digest=sha256:b0216b581d300a5b740426b0bc227b6a79fbc4652fd7a7c6804bfa088766689e

Observation 9eeea77d-5771-4b4c-afbc-1eea4624781a · outbound

This paper cites The Llama 3 Herd of Models.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs The Llama 3 Herd of Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.893463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.893463Z digest=sha256:760e0420fdacbf6602a4cd3d5487021ef7cd741d3cee8259fc84ae8a636fa76c

Observation 39f96a5e-a148-4668-bc5e-6a0aefb2f9f0 · outbound

This paper cites LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.895511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.895511Z digest=sha256:9252d8a2011592eadf0e63858ff3319797fb05588e30200a427c869e5d49e5c6

Observation bf3d5d62-be2d-49ca-85d3-62ce75bb2042 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.898001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.898001Z digest=sha256:9d0843b203d49def267d58b291f877e1bd5dd783085f1ae857db8ce8bd24a26d

Observation e96f5069-b44e-46d6-a78d-0e5166988836 · outbound

This paper cites Not All Layers of LLMs Are Necessary During Inference.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Not All Layers of LLMs Are Necessary During Inference

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.900026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.900026Z digest=sha256:1c54e66932af19929b19404bbaa5cf57293428abcb6500d4b30ec09a4daccb88

Observation d5bd29c0-2f1e-4cc3-ba5e-580e449cd887 · outbound

This paper cites Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.902607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.902607Z digest=sha256:0cad423fe227b791501362f198d462b89cfc1e631d3333b66331fc0f7f88f19b

Observation 16030a24-627d-42f6-9656-a4b7149b6626 · outbound

This paper cites LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.905006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.905006Z digest=sha256:6390ec4d778f0c97495d0c917011f70515655f56e23772bd0a7e8b32460b71d4

Observation 50b8a3ee-b0bc-45c3-9d79-05cfab5eb574 · outbound

This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.908466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.908466Z digest=sha256:50985b436aca2c2966813f8f9681ef909c1b2c48e6ca48e0cbbf6372bced8ba7

Observation 0aeeb0e4-34a3-42cc-84ff-e0c7c299c49b · outbound

This paper cites SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.911628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.911628Z digest=sha256:19c0028342fca8d206b45f8d5dcdb19628af666324056f552586e1a31b30a6d8

Observation b5a1ee5d-f479-425a-8b47-f3b269595229 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 16

Resolution
unresolved
raw_fallback, observed 2026-08-11T11:57:18.281370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-11T11:57:17.914969Z digest=sha256:68ca7a7d87694bdadf8d18bcc2c57195a330917a12aa42f37ed2a86e96c55704

Observation 66a70b2b-11bf-4217-aaa8-f384189b3d63 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.918375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.918375Z digest=sha256:79e86f2d35967ce3995ce76b0c76e9c30153c8be27699eab36ac1fb94ef412e3

Observation dcde423f-c079-4156-aff8-96a24c3c45aa · outbound

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

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.920808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.920808Z digest=sha256:f0c780d46bd8ba9d8e21b60e990286dbcbcff33133e2afc06ee49776194e919f

Observation 06355052-a2b9-4a0d-acc1-3491dc617851 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.924476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.924476Z digest=sha256:934973116e10101a820f9c3b6d7f12513915aad62f141855cfa1e9e25c4ec8bc

Observation c5d87ce7-ceb3-4706-8321-03bc6ae9f6c1 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.926957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.926957Z digest=sha256:eaace3c275c88fb03092b450b606aa135987c9c957e7e4090ce0e269e7194987

Observation d422a1f5-7a68-4130-891a-7991790289aa · outbound

This paper cites Mistral 7B.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Mistral 7B

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.929778Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.929778Z digest=sha256:853daf84f2ccd3c68bc920bc441b2e48b17f23c34d27b72e640a851651ebee53

Observation 6a6e4b3a-e6e9-4cfc-8941-5f53e188557a · outbound

This paper cites TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.932449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.932449Z digest=sha256:8c77f3baf5149ea5d2677ee3b54ad1b1a031b425f248accfbc1c911641fd74f4

Observation 8108889f-c38f-4a3f-b0bb-daabff8c9a4b · outbound

This paper cites GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.934982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.934982Z digest=sha256:1e8c8367d9244398a86ed348e11a3e1c62ce5dd77d6b2228b36079cd096ebe2a

Observation f59b676c-47dd-4aff-808c-5d70d6dc3d34 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.937548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.937548Z digest=sha256:b3c040381b7f1e873a7ce02d0463d4d2aa8d4b62ba8dbcbb226685fddbe452c5

Observation aed23925-8fad-42cf-9369-43d9a3d16cc7 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Gonzalez, Hao Zhang, and Ion Stoica

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.940310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.940310Z digest=sha256:d2b16e312207d3b951273a27a3ba069c6f1706ee6e257f9aa492dac9bb0d329d

Observation 4ced5670-84c1-465e-8f22-bd65c121d493 · outbound

This paper cites u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.942638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.942638Z digest=sha256:467253a56e12283b4ab222b829c7cbdf08e9697ef7ff8af1de192a5165ef1fba

Observation f6025d1b-21bb-47d4-aa2e-ae746ad57caf · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.945064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.945064Z digest=sha256:435bc3550c9a05e552150654f22b9bb15c32f670e60b9eb91bde9892c34558dd

Observation e8253be0-29ba-412f-83ab-0006abaaaf90 · outbound

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

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs SnapKV: LLM Knows What You are Looking for Before Generation

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.947905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.947905Z digest=sha256:fa0a469721645aa6a92e6406355ebe33242e6fb114bc3c03605eee905d268ce2

Observation b35376c6-1d3e-4277-9e74-9f3fa2bdc621 · outbound

This paper cites MiniCache: KV Cache Compression in Depth Dimension for Large Language Models.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.950846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.950846Z digest=sha256:4fac325f50b5d5cad8fa090a176dc3a3aa94b474ea9f1fa5ccb7d8200d210350

Observation 966b0862-295b-40b4-8b8a-69ea84e530c8 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.953955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.953955Z digest=sha256:d213c3d0c421056801bae4eea8e89fb2dc6a99ab84ada307f5407c3a18f24dee

Observation f1606a34-41f8-484a-b174-3b72c7b37204 · outbound

This paper cites RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.956598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.956598Z digest=sha256:52a77b93c8ed6c912407ad4e18783575529021cf0c53b972750462b18d324883

Observation c53b51e5-49e8-40c7-a389-c2738ef7a21d · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.959169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.959169Z digest=sha256:4037f51e6560b3efa28198b73b75ebe5c5fcb766208a0e5e66edcc42b1c3a2e5

Observation 37bec7fa-278a-4d27-82e7-ce179aa9f66e · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 33

Resolution
unresolved
raw_fallback, observed 2026-08-11T11:57:18.239280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-11T11:57:17.960970Z digest=sha256:920134ba7849bf36fbb1b349bf8fdc32f6d3d1412ba0e8846d1f5a017c11cca9

Observation deeff9c6-4613-428d-b87c-589864345c4d · outbound

This paper cites Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.963561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.963561Z digest=sha256:23520b56017b0d49d907f286dbfcfb023181620818d6b7d1b2732185ab8c0d6f

Observation e260fb12-963c-4b67-afe4-f6cadc36fb52 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 35

Resolution
unresolved
raw_fallback, observed 2026-08-11T11:57:18.230195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-11T11:57:17.966853Z digest=sha256:daff9ea0ede78829fcd293be896d223a3b880460642e9e24332633f5b92732b2

Observation c692c58b-428a-4649-92b0-2dd0221feab9 · outbound

This paper cites You Only Cache Once: Decoder-Decoder Architectures for Language Models.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs You Only Cache Once: Decoder-Decoder Architectures for Language Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.968732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.968732Z digest=sha256:cfcba3666bfea3d18630687862bb3e55a1585d023b098b5bf25930f29307bde0

Observation ac29efd5-7a41-4629-9a9a-ef4bb57fe537 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.971318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.971318Z digest=sha256:d7c059ed131fe6f3b4cbc293b7ca4e9cca25b52a18ee4abf768262100b313818

Observation 1272e4b9-df22-47f1-a413-cb389c5d48d1 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.974395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.974395Z digest=sha256:3f964a9ac0da4c3833db4d7f6cc8e4e44c124468634f7050c79b1812522fd181

Observation d27004eb-f0f7-426a-85cc-597b7641cce8 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.976917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.976917Z digest=sha256:ebb8257497012f15569bd3bfd3b43d09f2adcd3e43e5109032320634b50e0d2e

Observation ee230812-439b-4d14-a14f-4f940f997033 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-11T11:57:18.214354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-11T11:57:17.979479Z digest=sha256:7abf62c71e57b559b3bb0c71651ec143bd4b9fb664e7c4017498c33409f56462

Observation fd88d297-31d8-4cd9-8805-712413eff0a2 · outbound

This paper cites $\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs $\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.981797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.981797Z digest=sha256:45ca80ccdcc28754d6a34619c4670aa15622fb7e398aa898ae55efef152480cc

Observation 96d2634a-713b-482d-b7ee-8ac97926be2d · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Efficient Streaming Language Models with Attention Sinks

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.984445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.984445Z digest=sha256:c5e0557c489d18f79574df51e7fdde130341c230b64ecf23d9d48c4fefc2eedd

Observation db86fbc9-5fef-41a0-9d82-18e099558748 · outbound

This paper cites Qwen2 Technical Report.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Qwen2 Technical Report

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.987733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.987733Z digest=sha256:76caa548df8b13b07c49d9d4961312cdd69b35954841adc9cf7720516c2046c7

Observation cd78e8c4-faa0-4d68-95c5-8630456d8b1b · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.991083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.991083Z digest=sha256:805fd02256795f2fc1533d3e33f0a1f08abc4e4106672272fb729317c016e915

Observation 80eab4d1-db4a-4f70-bfad-3d4d358a63eb · outbound

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

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.994141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.994141Z digest=sha256:d922e5e8d59ed033d8c6b31117541629f46fe3bbb046a6233ee15e88b7f6f9e8

Observation c133d1b1-33cf-4e7d-94b0-51a80c36f017 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:17.997410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:17.997410Z digest=sha256:4112d7f951cf57e3637c13f7a41b3d604f6990f47fa4e418a5f6095c4c736b5e

Observation df70deed-1e87-4cb5-8b84-b846cd9bb457 · outbound

This paper cites an unresolved cited work.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:18.000165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:18.000165Z digest=sha256:a5d15ed5489c7d28340084d02f4d27a1065cf4015d0321e7702fa4dff6b868f0

Observation 11ce23eb-6e9d-42bc-b96f-f96f3c14d0b5 · outbound

This paper cites Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:18.002556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:18.002556Z digest=sha256:26ca1bb0e8c86d7ac536d6a06226376d3a5c95eb7d2e548fffb1ae02d8bde0f8

Observation 108a1570-4ed8-4914-9298-fd07ecd4c4d9 · outbound

This paper cites URL: " 'urlintro :=.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs URL: " 'urlintro :=

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:18.005775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:18.005775Z digest=sha256:5af436a8722c5105e20c9217dbdb3ac38b67a11c4dbcd4a6202740d3576ff5a4

Observation 28100c0b-d1dd-4fa9-9cb6-b49b2123f5bd · outbound

This paper cites write newline.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs write newline

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-11T11:57:18.009163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T11:57:18.009163Z digest=sha256:ad1694fd8b1de32ccdb949d8aa43400416f5c6c952facdf4efaad506d836da4f

Pith citing papers

Observation 4e5f724b-9e46-495c-888a-7fda1017ab42 · inbound

Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization cites this paper.

Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimization DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-15T20:05:31.660385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-15T20:05:31.660385Z digest=sha256:e0807852310db37ebd513bb8e26d7353789951a9d256202a03172c955ffcfe46

Observation 20efee29-b8eb-44cc-a975-33186125f2c7 · inbound

CaliDrop: KV Cache Compression with Calibration cites this paper.

CaliDrop: KV Cache Compression with Calibration DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-06T13:57:15.839816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T13:57:15.839816Z digest=sha256:0fc5ed6fb6f6b288c56ba391ddd9f491028e4acf4d147e8599151562346dd0c3

Observation bb8e1ff1-35dd-4b7e-bb30-414854bdeb30 · 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 DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-05T17:55:08.261078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T17:55:08.261078Z digest=sha256:3255a9a3b7d625320db802fcbb178973d030207ba72e8de4b3546f6f15dae932

Observation ea16eb07-5299-44a1-9870-516b83da6ff3 · inbound

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation cites this paper.

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 20

Resolution
verified exact
arxiv_id, observed 2026-05-21T13:34:11.370570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-21T13:32:15.598047Z digest=sha256:652918340d22eb96ff7748a120f2449740ca2a4bc9410c35844e74d65fe245f0

Observation af94e715-099d-4c2d-a69c-569597dc15ef · inbound

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation cites this paper.

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-03T03:16:19.908039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-03T03:16:19.908039Z digest=sha256:6aadb5cd840fceeea906dd9c219e154439f9fc2284933bb51cf779725f0ca677

Observation 3dee4f86-afda-4614-8bc4-3ce7403f73b3 · inbound

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models cites this paper.

From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 14

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T16:20:09.970164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-15T16:16:15.819622Z digest=sha256:f0f9bf7ce3dfec9dc86cf510dbd7d13e3bf8bf8beab6eaf3b6a854ce66cac85d

Observation fd5408ee-5436-4d65-8215-22112e7fc78e · inbound

Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs cites this paper.

Don't Waste Bits! Adaptive KV-Cache Quantization for Lightweight On-Device LLMs DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 37

Resolution
verified exact
arxiv_id, observed 2026-05-10T22:55:48.123886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-10T19:31:17.420639Z digest=sha256:30462f18356579aabae551dbc4aa0d3d484c4589e71d35c3de0404b3a5099dcd

Observation ea482e67-46c4-4806-bebd-45fefa3c12a7 · inbound

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing cites this paper.

SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 55

Resolution
verified exact
arxiv_id, observed 2026-05-10T08:32:52.113523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-10T08:32:02.222528Z digest=sha256:16428162f48c1f5e408cb1b0406728427fb0bd24b378af56d04144bb1cbd4cf9

Observation 91571be8-3c29-4401-8a00-d1c468f90051 · inbound

HieraSparse: Hierarchical Semi-Structured Sparse KV Attention cites this paper.

HieraSparse: Hierarchical Semi-Structured Sparse KV Attention DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-05-10T07:16:54.213976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-10T07:15:19.184970Z digest=sha256:9c9292d692e653d6acc44b066fb1d8cfcacfcb3ca979a93be232bc2d76dd1904

Observation 2bd6a4be-be7c-437f-a69b-bf517eedde51 · inbound

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities cites this paper.

Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 211

Resolution
verified exact
arxiv_id, observed 2026-05-11T20:16:10.305729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-08T09:45:57.201837Z digest=sha256:42c9cce651c76e6f9e9f559e0187a8685f304db6f12352e8894ea867bab4bc99

Observation 4ea9d3cb-195e-4348-b96e-e9815ba6a8d0 · inbound

ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing cites this paper.

ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 29

Resolution
verified exact
arxiv_id, observed 2026-05-12T07:26:30.323223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-12T02:52:33.076123Z digest=sha256:57006efbd5ec6b2b5d0cf744d3face47d1ac67c414d8ee0e3e953d30991d78cd

Observation 2b30aa87-2826-4855-bf1a-f389a5bccd30 · inbound

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition cites this paper.

YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 34

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T13:06:59.429187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-06-28T01:33:54.383507Z digest=sha256:e2ee5d5703dfb55e362d0ddf1b004946767711aa9e7e46cbaa18970a2cff9b06

Observation 2e9c34ce-26cb-40d9-90aa-e3a271609d4f · inbound

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving cites this paper.

SpectrumKV: Per-Token Mixed-Precision KV Cache Transfer for Prefill-Decode Disaggregated LLM Serving DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 22

Resolution
malformed identifier
arxiv_id, observed 2026-07-02T22:27:26.309060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-27T18:50:50.066713Z digest=sha256:c3bc2431f180615c3437ac62cde6c29690cde5dc791989632346e38e48e397e6

Observation 5b49ead8-949a-43ce-a411-79add8557bad · inbound

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference cites this paper.

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 6

Resolution
metadata mismatch
arxiv_id, observed 2026-07-02T20:57:22.975598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-06-27T20:04:44.703782Z digest=sha256:2ee5cf44aa64ec52d6924f92a20d1bef4375380d472771a639349b7d9a9fe960

Observation fc489183-a0d4-4e26-94cd-a9ffddf66d45 · inbound

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models cites this paper.

ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 14

Resolution
metadata mismatch
arxiv_id, observed 2026-07-03T05:37:40.355882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-06-27T13:09:37.979051Z digest=sha256:c6236a4f5a826d7b5334beced2e07c2319c5d76a2fcc9470261f50d79a7cb0fe

Observation 2b1e6053-7804-403d-860e-cf5810fad4c0 · inbound

AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor cites this paper.

AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 11

Resolution
verified exact
arxiv_id, observed 2026-07-03T20:18:57.886130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-27T01:23:23.488555Z digest=sha256:6a8b814979914924aebd47f101d8f1ed996a7810948fc319bae07c5407626c56

Observation 04608168-8d5e-441b-8da9-e1fb4b2613fd · inbound

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think cites this paper.

Finetuning Vision-Language-Action Models Requires Fewer Layers Than You Think DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 32

Resolution
verified exact
arxiv_id, observed 2026-07-04T04:29:34.949974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-26T16:59:28.243515Z digest=sha256:ce5ed046da8a45eb7197d6a0b5e08a088122e57c93eedb5ec7aff668d678f3eb

Observation a2b0cd05-6a7d-4054-aa8b-ca6dc843c250 · inbound

MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference cites this paper.

MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-14T10:41:08.967261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-14T10:41:08.967261Z digest=sha256:30308b95e973e41a599bf22e4f4ad8fc98c3699b1d3d07db135250d56b0983fd

Observation f94de7f7-6a0d-4e2d-af5a-46db56a32500 · inbound

RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation cites this paper.

RippleKV: Cross-Layer KV Cache Allocation via Perturbation Propagation DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-14T04:32:59.307426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-14T04:32:59.307426Z digest=sha256:bfd9c1586a6a8b7c0bf0c25e7bf57b81d8ba1a16f1e39f3aa59ae69c8eacfcaa