Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T09:58:29.057357Z
Paper Citation Record · LEDGER
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
As of 6 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 100 inbound Pith citation observations for arXiv:2406.02069.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T14:00:43.056432Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
40 of 40 outbound references displayed
- verified exact18
- verified fuzzy15
- unresolved2
- parse uncertain0
- malformed identifier1
- metadata mismatch4
External citation measurements
2
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation d76ccab1-98d3-4d5a-a01b-e10038b9ff84 · outbound
This paper cites GPT-4 Technical Report.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling GPT-4 Technical Report
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T09:58:29.134040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c7d1b727-7603-48ff-94d0-a383b66ef2fc · outbound
This paper cites LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T20:22:11.032040Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 36fb42a2-82c2-44de-8e31-e2539c974c31 · outbound
This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.106770Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4d823fe4-7ab2-4c79-b664-8b09f7daa877 · outbound
This paper cites MagicPIG: LSH Sampling for Efficient LLM Generation.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling MagicPIG: LSH Sampling for Efficient LLM Generation
Reference 4
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.115168Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9be4d397-a07c-4c49-ae6d-126368d84810 · outbound
This paper cites Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A Smith, and Matt Gardner.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A Smith, and Matt Gardner
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.242922Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 12ac178d-1ee8-49ab-847e-d5558564a844 · outbound
This paper cites LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-15T08:31:04.851790Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c935123c-84ea-458a-80dd-3a8a694ba6a4 · outbound
This paper cites Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference
Reference 7
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.127993Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f1607adb-bc9e-43da-b492-4e9f81aac032 · outbound
This paper cites Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model , url =.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model , url =
Reference 8
- Resolution
- verified exact
- doi, observed 2026-05-12T09:58:29.092124Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3333bdbb-2141-4ced-9349-a34185d0fc54 · outbound
This paper cites Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Reference 9
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T11:11:21.895994Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f9307598-04bc-492a-8519-778f8954d24f · outbound
This paper cites Samsum corpus: A human-annotated dialogue dataset for abstractive summarization.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Samsum corpus: A human-annotated dialogue dataset for abstractive summarization
Reference 10
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.250861Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 18d5fe14-fae6-44b0-b4a8-b0144a8675f2 · outbound
This paper cites LongCoder: A Long-Range Pre-trained Language Model for Code Completion.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling LongCoder: A Long-Range Pre-trained Language Model for Code Completion
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.150738Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7a68cb7e-960f-4615-b7d5-e3fd24d35a13 · outbound
This paper cites LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models
Reference 12
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.156505Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 11cc31d0-fb5a-4b8a-97cf-517dc0b0b918 · outbound
This paper cites Efficient attentions for long document summarization.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Efficient attentions for long document summarization
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.263988Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e85ef8f1-0b06-408d-9742-ae0b7b25b12e · outbound
This paper cites Mistral 7B.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Mistral 7B
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T09:58:29.161133Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9b2ac96e-76a3-4183-bfa8-0a575b874f14 · outbound
This paper cites MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.171156Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dccc4d18-53e0-470f-8c6e-8d12fae31190 · outbound
This paper cites InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.177917Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8305a765-6a57-4243-bdc6-82fdf2f855f1 · outbound
This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling SnapKV: LLM Knows What You are Looking for Before Generation
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-13T12:57:43.256882Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6d84fce4-3ee4-4326-8fae-7ea9674aadbd · outbound
This paper cites Code Llama: Open Foundation Models for Code.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Code Llama: Open Foundation Models for Code
Reference 18
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T09:58:29.190481Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0f564b89-e117-4001-8b73-a4d58afb5382 · outbound
This paper cites Massive Activations in Large Language Models.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Massive Activations in Large Language Models
Reference 19
- Resolution
- verified exact
- arxiv_id, observed 2026-05-16T07:02:54.298502Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation edae8866-c63f-427a-a54e-7dbf1c8815ba · outbound
This paper cites LLaMA: Open and Efficient Foundation Language Models.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling LLaMA: Open and Efficient Foundation Language Models
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T09:58:29.200441Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2eb9a3f7-c326-414a-b4f5-2fbe7a305013 · outbound
This paper cites Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.206330Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c25c24a4-8f2c-4353-ae1c-8b957dc7ce3b · outbound
This paper cites Retrieval Head Mechanistically Explains Long-Context Factuality.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Retrieval Head Mechanistically Explains Long-Context Factuality
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.212025Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation eda72efb-d4c0-4ba1-9ac9-390b89065224 · outbound
This paper cites Efficient Streaming Language Models with Attention Sinks.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Efficient Streaming Language Models with Attention Sinks
Reference 23
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T09:58:29.216384Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1d273cea-bb4c-45d8-9942-948c028785f0 · outbound
This paper cites PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.224557Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6cb252ed-4af6-4136-ad08-e9f4cf9582ae · outbound
This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Hotpotqa: A dataset for diverse, explainable multi-hop question answering
Reference 25
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.247054Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 62bc80b6-48af-46f3-9261-f2c630e0aa02 · outbound
This paper cites Qmsum: A new benchmark for query- based multi-domain meeting summarization.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Qmsum: A new benchmark for query- based multi-domain meeting summarization
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.255249Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a005d97e-ecd6-4d1a-bc46-e3fad4e010b2 · outbound
This paper cites PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.229758Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 49dab320-4689-48e8-af64-e23d0d1ccee4 · outbound
This paper cites attention sink.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling attention sink
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.267681Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4a7d71b4-6bb2-4d37-b645-e1b6cc3ca446 · outbound
This paper cites Figure 5 and Figure 6 demonstrate that the Pyramidal Informa- tion Funneling phenomenon is also evident in both the Mistral model and Mixtral model.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Figure 5 and Figure 6 demonstrate that the Pyramidal Informa- tion Funneling phenomenon is also evident in both the Mistral model and Mixtral model
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.271567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation c6a60026-156a-4939-af5d-4a675a4fc125 · outbound
This paper cites While Lee et al.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling While Lee et al
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.275213Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5d6537ba-72e5-4d12-b9d2-2d2df2ed65b5 · outbound
This paper cites an unresolved cited work.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Unresolved cited work
Reference 31
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T09:58:29.279451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b3d64715-b33b-41c0-9969-3bb0f4d1ae6f · outbound
This paper cites α Single-Document QA Multi-Document QA Summarization Few-shot Learning Synthetic Code Avg.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling α Single-Document QA Multi-Document QA Summarization Few-shot Learning Synthetic Code Avg
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.283943Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 52ca5888-b66d-4714-b8fc-ad319da371fe · outbound
This paper cites β Single-Document QA Multi-Document QA Summarization Few-shot Learning Synthetic Code Avg.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling β Single-Document QA Multi-Document QA Summarization Few-shot Learning Synthetic Code Avg
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.287621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 48e361fa-81e2-4aca-9c0d-eb8caf5745fc · outbound
This paper cites an unresolved cited work.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Unresolved cited work
Reference 34
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T09:58:29.291379Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6ecf3ca3-36eb-4c2b-b0f1-645efed42179 · outbound
This paper cites [Prompt length, Generation length].
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling [Prompt length, Generation length]
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.295445Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3b1f5b9e-f401-4feb-bd27-dc30b653bd74 · outbound
This paper cites [Prompt length, Generation length].
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling [Prompt length, Generation length]
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.299113Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4fbec693-5e8d-4499-b0b3-f2a99c0e74d8 · outbound
This paper cites That’s because the allocation strategy requires very limited additional complexity in the inference/generation phase compared with computation required for generation as Appendix L.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling That’s because the allocation strategy requires very limited additional complexity in the inference/generation phase compared with computation required for generation as Appendix L
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.303404Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 91b3d879-2b91-483b-955d-7804f89b3efe · outbound
This paper cites Attention Recall Rate Experiment.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling Attention Recall Rate Experiment
Reference 38
- Resolution
- malformed identifier
- arxiv_id, observed 2026-05-12T09:58:29.234563Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 42b46a13-dc4e-403d-a034-c93c97340b19 · outbound
This paper cites However, with a larger budget (i.e., 2k KV Cache Size), the improvement decreases.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling However, with a larger budget (i.e., 2k KV Cache Size), the improvement decreases
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.259721Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e240f58e-d419-471e-9083-4693443d7f50 · outbound
This paper cites massive attention.
PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling massive attention
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T09:58:29.238044Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Pith citing papers
Observation 5db3f52e-6649-45e8-9603-4ddd49a703be · inbound
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference cites this paper.
Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T11:16:32.027501Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 666adf94-9fe6-462a-817f-4cb202cab9d2 · inbound
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval cites this paper.
RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 74
- Resolution
- verified exact
- local_arxiv, observed 2026-05-18T08:12:01.920496Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 190f646b-99d6-4527-99ea-26a17bafab65 · 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 PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 39
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T18:33:19.388291Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5c759f4b-a372-4848-b09f-d38b369845d1 · inbound
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration cites this paper.
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T04:02:29.940554Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 073260d5-2cbc-4713-9d53-45eef363d853 · 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 PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-05-23T04:17:31.250437Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dd015a65-76a0-4100-9804-995fade955fd · inbound
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate cites this paper.
TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T08:09:22.359112Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 01914110-32ad-4d4b-85db-ec6ad85e851d · inbound
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference cites this paper.
RetroInfer: A Vector Storage Engine for Scalable Long-Context LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 71be8909-196f-489c-9806-77b6bc72c888 · inbound
CaliDrop: KV Cache Compression with Calibration cites this paper.
CaliDrop: KV Cache Compression with Calibration PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T13:57:15.666030Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1d0e505e-5774-42d4-b0d1-a59251e4c9cf · inbound
FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression cites this paper.
FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 5
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T14:00:43.056432Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8c878f50-e796-4a0e-bff9-99634a5bdaa3 · inbound
CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation cites this paper.
CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-06T05:00:04.815941Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 025b074b-3744-4487-af55-32e841e5e6b2 · inbound
PiKV: KV Cache Management System for Mixture of Experts cites this paper.
PiKV: KV Cache Management System for Mixture of Experts PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T00:00:47.796797Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b5151996-ff67-4cd4-8d85-9bc3cc9ba343 · inbound
GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction cites this paper.
GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T13:44:17.124146Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a57ee57f-005d-44a1-b3a5-f6d6c96c5c2c · inbound
Adaptive KV-Cache Compression without Manually Setting Budget cites this paper.
Adaptive KV-Cache Compression without Manually Setting Budget PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2020
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T11:10:56.529594Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 762a847d-aaed-432f-a10d-9f7845876930 · inbound
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference cites this paper.
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2018
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T10:16:13.114722Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ec5e6bb3-5d9a-4eb8-be3f-f54dad7cc057 · inbound
EvolKV: Evolutionary KV Cache Compression for LLM Inference cites this paper.
EvolKV: Evolutionary KV Cache Compression for LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T20:53:27.311694Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f9f7b201-db2b-4528-bda9-5d54ab196de3 · inbound
EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments cites this paper.
EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T21:54:22.788872Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 93e37d9d-8598-453f-9f87-9c7301c848df · inbound
The Pitfalls of KV Cache Compression cites this paper.
The Pitfalls of KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-18T11:32:35.154557Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8154630b-1f14-4887-8f2f-9687e91c15b0 · inbound
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference cites this paper.
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T14:43:00.828806Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8d2a2249-c81e-45b2-b0c2-beb039d9682b · inbound
CacheClip: Accelerating RAG with Effective KV Cache Reuse cites this paper.
CacheClip: Accelerating RAG with Effective KV Cache Reuse PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T12:41:33.680339Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 095e062d-1ca3-47bf-a3b7-d314d4b98893 · inbound
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference cites this paper.
Long-Context Modeling with Dynamic Hierarchical Sparse Attention for Memory-Constrained LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T07:44:17.063957Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 40bb759f-29fa-4826-a57e-37277ad85db8 · inbound
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference cites this paper.
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-16T13:17:54.905052Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a0d59ee3-8a6d-47c0-ad90-bf2af8c5be53 · inbound
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 29
- Resolution
- verified exact
- local_arxiv, observed 2026-05-16T12:40:54.722220Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 06efd669-e6ad-40c4-93dd-ace01ae12ff1 · inbound
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs cites this paper.
ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T03:37:50.092147Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 23d9454a-000a-499c-97c7-1b22f972b741 · inbound
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation cites this paper.
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T13:34:11.338551Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fc30f8e6-df5d-4382-9704-458e28ff03f8 · inbound
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation cites this paper.
CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T03:16:19.856696Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4149d7af-395d-46ed-867b-6fdde9f92f96 · inbound
Learning to Evict from Key-Value Cache cites this paper.
Learning to Evict from Key-Value Cache PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 7
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T01:18:02.495588Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0b3cbd01-fae1-4787-82c0-913dd87d1f84 · inbound
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context cites this paper.
InfoFlow KV: Information-Flow-Aware KV Recomputation for Long Context PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2025
- Resolution
- unresolved
- no resolver link, observed 2026-08-02T18:47:14.754202Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8dfff70d-83ea-4390-a4e3-b59fe0c0498b · inbound
LightThinker++: From Reasoning Compression to Memory Management cites this paper.
LightThinker++: From Reasoning Compression to Memory Management PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 64
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T17:28:01.768934Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f8c610bf-d118-4b52-98fd-2c9e89832bf9 · inbound
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression cites this paper.
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 2
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 859261f3-bb98-4699-8f3c-3b5712ee5a4e · inbound
cuRAMSES: Scalable AMR Optimizations for Large-Scale Cosmological Simulations cites this paper.
cuRAMSES: Scalable AMR Optimizations for Large-Scale Cosmological Simulations PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 6
- Resolution
- unresolved
- no resolver link, observed 2026-07-13T09:09:32.932051Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d4d2d06-b832-418f-82b8-49a4de90efa1 · inbound
CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference cites this paper.
CodecSight: Leveraging Video Codec Signals for Efficient Streaming VLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1640abe1-e9bf-46d8-86e7-eccb0bfac392 · inbound
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models cites this paper.
AudioKV: KV Cache Eviction in Efficient Large Audio Language Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9cf29f5b-daed-495f-b55f-93113e273f66 · inbound
From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI cites this paper.
From Business Events to Auditable Decisions: Ontology-Governed Graph Simulation for Enterprise AI PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8f13d916-cdf4-4b0f-8e4d-f1bd44c47eea · inbound
Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs cites this paper.
Why Smaller Is Slower? Dimensional Misalignment in Compressed LLMs PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-15T15:41:12.000328Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cb0a69a0-9e79-4605-9788-cc9cd057db81 · inbound
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 148
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 712cd662-7769-4f97-bb3e-41bc8db80015 · inbound
Transactional Attention: Semantic Sponsorship for KV-Cache Retention cites this paper.
Transactional Attention: Semantic Sponsorship for KV-Cache Retention PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6546f922-6a28-4b09-876d-730dce5e5f79 · inbound
HieraSparse: Hierarchical Semi-Structured Sparse KV Attention cites this paper.
HieraSparse: Hierarchical Semi-Structured Sparse KV Attention PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3aff886b-21e0-4aac-81c4-592803206504 · inbound
Graph-Guided Adaptive Channel Elimination for KV Cache Compression cites this paper.
Graph-Guided Adaptive Channel Elimination for KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f2a2bac6-c38c-47a3-a3e9-88900606a684 · inbound
How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers cites this paper.
How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 236f647c-d90b-49da-9bca-9136d4e9e153 · inbound
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing cites this paper.
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5810c075-62f7-4771-8a1b-62be82877a59 · inbound
Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing cites this paper.
Stochastic KV Routing: Enabling Adaptive Depth-Wise Cache Sharing PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T19:58:12.038555Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b2efa000-9188-47a2-8efa-329975d8daef · inbound
Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding cites this paper.
Salca: A Sparsity-Aware Hardware Accelerator for Efficient Long-Context Attention Decoding PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3072c7cd-214a-4941-9706-6cbc1a578cd7 · inbound
eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization cites this paper.
eOptShrinkQ: Near-Lossless KV Cache Compression Through Optimal Spectral Denoising and Quantization PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ce697c96-9e77-48fd-a908-446f3ccfc699 · inbound
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction cites this paper.
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 14
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 576ebfb6-fad7-4eb5-ba6b-d799020bd625 · inbound
Sparse Prefix Caching for Hybrid and Recurrent LLM Serving cites this paper.
Sparse Prefix Caching for Hybrid and Recurrent LLM Serving PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 27343873-201c-4b3f-8e0f-f0cc5a0d9d4b · inbound
Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility cites this paper.
Shallow Prefill, Deep Decoding: Efficient Long-Context Inference via Layer-Asymmetric KV Visibility PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f5d66a73-d766-44f2-a6f2-48d219f62db4 · inbound
Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache cites this paper.
Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 7
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d0835c05-69e5-45b1-953f-d446d681bca4 · inbound
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference cites this paper.
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1b712941-cb9c-4850-b8f7-dde3b848fcaf · inbound
An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference cites this paper.
An Efficient Hybrid Sparse Attention with CPU-GPU Parallelism for Long-Context Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d95ea6f0-1c72-44be-83ea-baf9206524f9 · inbound
RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache cites this paper.
RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e1148e5f-a39e-4e7f-8ed5-81b133bcb0b9 · inbound
Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents cites this paper.
Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 64
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5d92d5f7-92dc-41eb-bef8-75266efcd3b8 · 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 PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation d18feb2c-dc19-4e2c-906a-40e76796fe89 · inbound
Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning cites this paper.
Not All Thoughts Need HBM: Semantics-Aware Memory Hierarchy for LLM Reasoning PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 416e77be-388e-4f64-a49b-e09f86040c65 · inbound
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction cites this paper.
Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 26fb4424-f977-4ec1-8ecb-7966ac01a53e · inbound
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving cites this paper.
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T09:58:29.304691Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 14f2a3b6-2fc2-427b-9c3c-4a4b61e85987 · inbound
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving cites this paper.
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.477467Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8cd7a87a-3ace-459c-806b-9f82c0345f65 · inbound
FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression cites this paper.
FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T01:47:04.493056Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4aad0bad-7043-49f3-be24-12b6859822b8 · inbound
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference cites this paper.
KV-Fold: One-Step KV-Cache Recurrence for Long-Context Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T05:32:19.502490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a86cc061-34ba-4579-91ee-cd756dafd982 · inbound
Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation cites this paper.
Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 30
- Resolution
- verified exact
- local_arxiv, observed 2026-05-14T19:49:25.591746Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 0fdb6fa9-bae4-4d2e-9fe9-3dd310249f95 · inbound
Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility cites this paper.
Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 72
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-15T05:39:47.934459Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ed16ad11-c355-4668-945e-12d5ed9802e7 · inbound
Minimal-Intervention KV Retention via Set-Conditioned Diversity cites this paper.
Minimal-Intervention KV Retention via Set-Conditioned Diversity PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T20:59:01.564827Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 77171088-c208-4680-9028-16625599915c · inbound
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction cites this paper.
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T19:53:42.064916Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 739b33d3-79cc-4ccc-bd3e-027f66b58d5a · inbound
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction cites this paper.
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T19:25:01.134173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 8bc20ac5-dc0c-4ae2-9ad1-57ae2f767a0f · inbound
ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference cites this paper.
ProxyKV: Cross-Model Proxy Pruning for Efficient Long-Context LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T22:49:10.890422Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f096c003-eca4-4da5-9ffd-3636e8a7ba5c · inbound
Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design cites this paper.
Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 33
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T13:03:17.942900Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 385e8fbe-0fba-4de6-a968-0001b21c507a · inbound
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing cites this paper.
FastOCR: Dynamic Visual Fixation via KV Cache Pruning for Efficient Document Parsing PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T14:58:24.848419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation dd57e39b-c936-463d-81b7-a081a09c70a9 · inbound
VeriCache: Turning Lossy KV Cache into Lossless LLM Inference cites this paper.
VeriCache: Turning Lossy KV Cache into Lossless LLM Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-19T22:12:51.107861Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9b244e32-3936-4fa8-a4ff-3e75cb43ac59 · inbound
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization cites this paper.
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 39
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T12:18:16.482638Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation a04faa5c-55ba-42be-9dba-51a6e99f55fa · inbound
Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs cites this paper.
Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T13:13:17.925481Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5991786b-911d-483f-b8fe-2a03898e7ed1 · inbound
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention cites this paper.
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 35
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T10:53:13.596117Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e4381dec-dfae-45a8-befe-f2f3800a298a · inbound
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference cites this paper.
SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-20T20:33:43.342863Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 2a8b4c53-2f14-4f62-9325-ea236ade942c · inbound
AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees cites this paper.
AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T06:23:05.528663Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation cb595ec9-f028-46c7-b7b4-e4442ae1acb7 · inbound
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond cites this paper.
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T07:58:07.640084Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 91cdb1d5-ecfa-4445-999c-bda66ba3e08f · inbound
Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation cites this paper.
Head-Aware Key-Value Compression for Efficient Autoregressive Image Generation PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T06:09:41.645572Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 249f2ae3-c372-4a09-8228-a4ac3cb3492f · inbound
Layer-wise Token Compression for Efficient Document Reranking cites this paper.
Layer-wise Token Compression for Efficient Document Reranking PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-21T03:03:55.870896Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation fa282a29-e98b-4715-ab21-3e41c848d7da · inbound
Layer-wise Token Compression for Efficient Document Reranking cites this paper.
Layer-wise Token Compression for Efficient Document Reranking PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T09:21:21.703780Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation f50264e5-bb5b-4a79-935f-949786167a21 · inbound
Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression cites this paper.
Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T05:11:06.201039Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation b57415e4-3f09-4c7d-b52a-dd41da64c4f0 · inbound
Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression cites this paper.
Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T17:34:57.881326Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 39be823e-c8cd-4e40-9f5d-f9be27e03428 · inbound
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning cites this paper.
Adaptive Mass-Segmented KV Compression for Long-Context Reasoning PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T05:25:22.830790Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 561e053f-1bfa-4c2e-a060-205e0484a38c · inbound
A Simple Plug-in for Improving Eviction-Based KV Cache Compression cites this paper.
A Simple Plug-in for Improving Eviction-Based KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-25T04:55:24.177510Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 6cb3f8bb-9b81-41a5-a48b-b3de21a55b6d · inbound
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM cites this paper.
CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T11:54:38.177115Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 779c2791-8a71-4f9a-b0ec-d294aed53b9f · inbound
Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression cites this paper.
Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 9
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T00:04:07.002951Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 9ca33049-920e-4a17-8484-c7bf32607a5d · inbound
AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference cites this paper.
AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T08:53:15.969539Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 95b7db54-37c8-4c06-ba88-fe18f0da20d0 · inbound
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs cites this paper.
GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T19:16:00.781888Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 955a8755-56de-4d6d-9c23-c12b5dfdb6c3 · inbound
Linear Scaling Video VLMs for Long Video Understanding cites this paper.
Linear Scaling Video VLMs for Long Video Understanding PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-28T23:02:46.207233Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation ac39024b-6899-4cf5-ace9-682f720164a0 · inbound
MURMUR: An Efficient Inference System for Long-Form ASR cites this paper.
MURMUR: An Efficient Inference System for Long-Form ASR PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 28
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-06-28T17:12:25.090451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3806adf3-9eeb-4303-a6a8-30d858131273 · inbound
MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference cites this paper.
MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T21:56:15.432735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 75494f65-1906-45a1-9eb3-3e04a3ec4105 · inbound
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models cites this paper.
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 22
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T22:16:16.632799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 5d6d97df-07de-4a0b-894f-f5498adc8412 · inbound
Scaling LLM Inference Beyond Amdahl`s Limits via Eliminating Non-Scalable Overheads cites this paper.
Scaling LLM Inference Beyond Amdahl`s Limits via Eliminating Non-Scalable Overheads PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 3
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T01:06:24.213195Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3410da57-d4a8-481d-83f1-904c680b19ef · inbound
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models cites this paper.
TGV-KV: Text-Grounded KV Eviction for Vision-Language Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 26
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T02:16:26.718585Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 95c4c548-b895-44d4-9b0d-9520d6a1d998 · inbound
Value-Aware Stochastic KV Cache Eviction for Reasoning Models cites this paper.
Value-Aware Stochastic KV Cache Eviction for Reasoning Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 40
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T02:06:27.047584Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 25317026-020d-4960-8907-d7d6826142fa · inbound
QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving cites this paper.
QCFuse: Query-Aware Cache Fusion via Compressed View for Efficient RAG Serving PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T12:46:57.486135Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3deba656-f2df-4d11-bf85-e0447395c6e2 · inbound
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching cites this paper.
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T16:27:09.083376Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation aa6355ae-43ab-418c-89db-e8dc9f1a6f14 · 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 PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 1
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T22:27:26.305482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation e4ec9704-176e-4c7a-b4ac-ec10432a4bf8 · 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 PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T20:57:22.978766Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4bbe0573-b390-41d5-932b-32bb4a7b07bc · inbound
FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion cites this paper.
FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T04:37:37.453144Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 3700b887-558b-4063-87a4-e50c7ba484da · 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 PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 13
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T05:37:40.350799Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 1877ac85-e295-4567-b1dd-be8a788a2316 · inbound
Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning cites this paper.
Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 216
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T09:07:48.437587Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 4a1f57b5-08b4-4c4b-ba2b-296680fecd81 · inbound
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models cites this paper.
Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T11:28:04.149706Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.
Observation 7161d225-6218-4fb4-9e81-60fc048e45f0 · inbound
Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression cites this paper.
Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache Compression PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
Reference 10
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T09:17:49.049546Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.