LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding | Paper Citation Record

Observation 959d079c-d81d-457b-b730-c0597f54713c · outbound

This paper cites LongBench: A bilingual, multitask benchmark for long context understanding.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding LongBench: A bilingual, multitask benchmark for long context understanding

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.599287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bfc83ab-cfa0-4dc1-b86d-6a03fe53ac7c · outbound

This paper cites RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.602883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88edf86c-4b9d-40e6-bfd6-61030eb40ecf · outbound

This paper cites Longformer: The Long-Document Transformer.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Longformer: The Long-Document Transformer

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.605941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd2a06c7-b6e3-4a44-bf38-7a295f928a31 · outbound

This paper cites R-KV: Redundancy-aware KV cache compression for reasoning models.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding R-KV: Redundancy-aware KV cache compression for reasoning models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.609016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24c27a4f-b41a-4cb0-9434-542160ff4baf · outbound

This paper cites Runtime-Certified Bounded-Error Quantized Attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Runtime-Certified Bounded-Error Quantized Attention

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.611913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9efb6cf7-0d03-46c7-bd1f-c19c47410427 · outbound

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

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Palu: Compressing KV-Cache with Low-Rank Projection

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.614843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8c0567-ff9a-46fc-b902-333781a667e8 · outbound

This paper cites Value-Aware Stochastic KV Cache Eviction for Reasoning Models.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Value-Aware Stochastic KV Cache Eviction for Reasoning Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.619336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 105a00ad-7f73-4dd8-960c-490ae7a98afb · outbound

This paper cites MagicPIG: LSH sampling for efficient LLM generation.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding MagicPIG: LSH sampling for efficient LLM generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.622393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 787f2b05-3c08-4b5c-83b6-d1a1e38031e1 · outbound

This paper cites Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.624951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf45fbee-d439-4b21-8200-1a204d6aed2e · outbound

This paper cites Generating Long Sequences with Sparse Transformers.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Generating Long Sequences with Sparse Transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.628245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bd23b9f-fc37-48dc-8cc2-2631cb030d7a · outbound

This paper cites DeepSeek-V4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding DeepSeek-V4: Towards highly efficient million-token context intelligence.arXiv preprint arXiv:2606.19348, 2026

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.631097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f14d6af5-3a8f-4761-ad5d-786073bccf16 · outbound

This paper cites vAttention: Verified Sparse Attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding vAttention: Verified Sparse Attention

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.633572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7af074a-ce98-491a-ad7b-294fc8fb8aef · outbound

This paper cites Kascade: A practical sparse attention method for long-context LLM inference, 2025.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Kascade: A practical sparse attention method for long-context LLM inference, 2025

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.636314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a79ae37-134a-419b-9838-285db21d3a9e · outbound

This paper cites Expected attention: KV cache compression by estimating attention from future queries distribution, 2025.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Expected attention: KV cache compression by estimating attention from future queries distribution, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.638817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 576f0597-61dd-4d3d-bb0f-3d1c41622851 · outbound

This paper cites The approximation of one matrix by another of lower rank.Psychometrika, 1(3): 211–218, 1936.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding The approximation of one matrix by another of lower rank.Psychometrika, 1(3): 211–218, 1936

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.641335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4301edce-d036-4326-a5ac-7512a5da7da9 · outbound

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

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.643900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f24662f-4ecb-4e8a-8539-5011aac93f39 · outbound

This paper cites SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.646757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaab944d-c458-444a-a56e-f7e5f59bbc3a · outbound

This paper cites The Llama 3 Herd of Models.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding The Llama 3 Herd of Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.649772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64abe1e-c04d-4ccd-b828-ada98883c038 · outbound

This paper cites Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.652489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb8a54c-fef2-44d7-bffc-93230c7d777b · outbound

This paper cites ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.655479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 774ad2d5-f9fb-48ef-8bbf-3ca35b8fef0f · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Measuring mathematical problem solving with the MATH dataset

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.658299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8018d232-67d2-497e-93f9-0e6a4ca29532 · outbound

This paper cites SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding SVDq: 1.25-bit and 410x Key Cache Compression for LLM Attention

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.660856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5e1e7c3-cf4f-4b72-9352-3f3c2b20fe4e · outbound

This paper cites KVQuant: Towards 10 million context length LLM inference with KV cache quantization.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding KVQuant: Towards 10 million context length LLM inference with KV cache quantization

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.663751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34800a76-c8d5-494c-93f1-e544608b5d5d · outbound

This paper cites Multipole attention for efficient long context reasoning.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Multipole attention for efficient long context reasoning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.666428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65566cb2-fd52-4269-92f0-99ac7392a2ec · outbound

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

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.668924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14757c3e-1a75-4357-91d4-012f5450664d · outbound

This paper cites Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.671759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb3acca-ace5-466f-a1ee-345b70edc513 · outbound

This paper cites MInference 1.0: Accelerating pre-filling for long-context LLMs via dynamic sparse attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding MInference 1.0: Accelerating pre-filling for long-context LLMs via dynamic sparse attention

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.674420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 516b3f31-b1e3-4d4f-a77e-dd5e6e19b868 · outbound

This paper cites Lee, Sangdoo Yun, and Hyun Oh Song.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Lee, Sangdoo Yun, and Hyun Oh Song

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.676916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a346038-c55e-4124-bf64-fa3a8adbaf57 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Efficient memory management for large language model serving with pagedattention

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.679444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04a72802-65a1-421c-ac88-b62ee91cb951 · outbound

This paper cites InfiniGen: Efficient generative inference of large language models with dynamic KV cache management.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding InfiniGen: Efficient generative inference of large language models with dynamic KV cache management

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.681959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffff939-3524-4b72-b215-9f3326ba376a · outbound

This paper cites Rakhshan, and Guillaume Rabusseau.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Rakhshan, and Guillaume Rabusseau

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.684394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bae6cc65-27c4-4f78-b7bb-8094a25943fe · outbound

This paper cites Efficient low rank attention for long-context inference in large language models.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Efficient low rank attention for long-context inference in large language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.686847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 806acae9-9c8d-4f33-881f-b309b9aff0f1 · outbound

This paper cites Snapkv: LLM knows what you are looking for before generation.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Snapkv: LLM knows what you are looking for before generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.689334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 542fa98f-0031-4df5-8222-cfe9b0fafef2 · outbound

This paper cites Let’s verify step by step.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Let’s verify step by step

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.691973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc221710-858e-4c41-88a6-e2e7264ce6fe · outbound

This paper cites Twilight: Adaptive attention sparsity with hierarchical top-p pruning.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Twilight: Adaptive attention sparsity with hierarchical top-p pruning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.694489Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f953dad-68ab-447c-8805-5da810eadb73 · outbound

This paper cites RetrievalAttention: Accelerating long-context LLM inference via vector retrieval.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding RetrievalAttention: Accelerating long-context LLM inference via vector retrieval

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.696980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e0d35b9-7965-439c-b3f0-21a020d041ed · outbound

This paper cites ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.699513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f52fbd-9abb-48af-8f7f-82002a348382 · outbound

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

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.702163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff8b9d3c-845f-47c7-9d77-745d50a3c062 · outbound

This paper cites KIVI: A tuning-free asymmetric 2bit quantization for KV cache.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding KIVI: A tuning-free asymmetric 2bit quantization for KV cache

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.704874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78245182-d1d3-4e19-9e05-613aed85bdd3 · outbound

This paper cites MoBA: Mixture of Block Attention for Long-Context LLMs.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding MoBA: Mixture of Block Attention for Long-Context LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.707395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deb03427-f860-4341-bbe7-00aa29be4af6 · outbound

This paper cites TriAttention: Efficient Long Reasoning with Trigonometric KV Compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.710201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f7380e-cb26-4594-8697-62cd46e165ea · outbound

This paper cites Landmark Attention: Random-Access Infinite Context Length for Transformers.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Landmark Attention: Random-Access Infinite Context Length for Transformers

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.713173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ac1f2ad-c643-4606-8f66-82abbc90c30e · outbound

This paper cites SALS: Sparse attention in latent space for KV cache compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding SALS: Sparse attention in latent space for KV cache compression

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.715929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18f71b2b-c7d9-42c9-b8ee-0e1a11a0fbc7 · outbound

This paper cites The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.718361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2774982c-d33a-435e-a1c2-e43837eae884 · outbound

This paper cites Qwen3.5: Towards native multimodal agents.https://qwen.ai/blog?id=qwen3.5, 2026.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Qwen3.5: Towards native multimodal agents.https://qwen.ai/blog?id=qwen3.5, 2026

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.720982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34034361-9ed1-4385-9431-18af41f3191b · outbound

This paper cites SparQ attention: Bandwidth-efficient LLM inference.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding SparQ attention: Bandwidth-efficient LLM inference

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.723462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6288f059-36a3-481d-a87d-9ad3c4cd5bdd · outbound

This paper cites Eigen attention: Attention in low-rank space for KV cache compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Eigen attention: Attention in low-rank space for KV cache compression

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.726565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09739156-8774-4047-9d85-b6e8cb20a7b8 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Fast Transformer Decoding: One Write-Head is All You Need

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.729328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5393c3b5-e078-4c43-8730-3640dc0c7287 · outbound

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

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Loki: Low-rank Keys for Efficient Sparse Attention

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.732389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea58ec9e-d60a-44c2-8139-1c3909ba88a2 · outbound

This paper cites LongFlow: Efficient KV Cache Compression for Reasoning Models.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding LongFlow: Efficient KV Cache Compression for Reasoning Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.735297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb77442-e559-441b-916b-5bdf1a8bbaa1 · outbound

This paper cites ShadowKV: KV cache in shadows for high-throughput long-context LLM inference.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding ShadowKV: KV cache in shadows for high-throughput long-context LLM inference

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.738457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6baaa99-e09f-489d-b42e-91aa819d0403 · outbound

This paper cites Quest: Query-aware sparsity for efficient long-context LLM inference.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Quest: Query-aware sparsity for efficient long-context LLM inference

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.741061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02fc6b07-76db-4b02-96cc-313ceb3ed263 · outbound

This paper cites ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.743571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1366120e-6eef-44b1-808d-fdc969bc4e17 · outbound

This paper cites COBS: Cumulant Order Block Sparse Attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding COBS: Cumulant Order Block Sparse Attention

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.746726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e65cea9-3327-4e76-b100-6617e0255937 · outbound

This paper cites A mathematical theory of top-ksparse attention via total variation distance, 2025.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding A mathematical theory of top-ksparse attention via total variation distance, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.749782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbd7d912-9cc9-43cf-afa1-5c54d7176c1d · outbound

This paper cites SPLA: Block sparse plus linear attention for long context modeling.arXiv preprint arXiv:2601.22379, 2026.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding SPLA: Block sparse plus linear attention for long context modeling.arXiv preprint arXiv:2601.22379, 2026

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.752410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b3e8db-b6d5-4784-8d5b-44d9dc530c8c · outbound

This paper cites Prism: Spectral-Aware Block-Sparse Attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Prism: Spectral-Aware Block-Sparse Attention

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.755340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21c42903-c6bb-47aa-b73f-20a3c4c0d651 · outbound

This paper cites TokenSelect: Efficient long-context inference and length extrapolation for LLMs via dynamic token-level KV cache selection.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding TokenSelect: Efficient long-context inference and length extrapolation for LLMs via dynamic token-level KV cache selection

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.758862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ed4e946-e7ea-498f-8aee-42a4d25a38dd · outbound

This paper cites InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.761477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f01c3bbd-793b-43ec-a26d-5f1b1da8b0f5 · outbound

This paper cites Efficient streaming language models with attention sinks.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Efficient streaming language models with attention sinks

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.764973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b90b59e2-f2af-4706-9a62-2710cc046603 · outbound

This paper cites DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.767862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60e153d1-c2fd-462a-8230-af37e924c857 · outbound

This paper cites Qwen3 Technical Report.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Qwen3 Technical Report

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.771041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf064771-150e-419f-8c46-194fb053990b · outbound

This paper cites No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.774088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb304ee9-3e1a-4e57-9269-b67b116de627 · outbound

This paper cites Adaptive Mass-Segmented KV Compression for Long-Context Reasoning.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Adaptive Mass-Segmented KV Compression for Long-Context Reasoning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.776915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dc332e9-ffdb-43bb-90e4-b8a915f52fd7 · outbound

This paper cites TidalDecode: Fast and accurate LLM decoding with position persistent sparse attention.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding TidalDecode: Fast and accurate LLM decoding with position persistent sparse attention

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.779925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deca8bf0-5b1a-485b-b49e-cecbdb30daac · outbound

This paper cites Self-indexing KVCache: Predicting sparse attention from compressed keys, 2026.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Self-indexing KVCache: Predicting sparse attention from compressed keys, 2026

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.782655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12701088-aa65-445c-b456-6b4edbff2b8d · outbound

This paper cites HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.785240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d35f19ad-4206-4fb0-bf15-52471124beb1 · outbound

This paper cites BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding BLASST: Dynamic BLocked Attention Sparsity via Softmax Thresholding

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.788006Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22443527-7156-4090-adfe-56a04d49be16 · outbound

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

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.790902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 134df698-5dae-4c79-8d7b-b21fcd450986 · outbound

This paper cites Big bird: Transformers for longer sequences.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Big bird: Transformers for longer sequences

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.793719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28ebee9f-58ba-4a69-b2f6-6cc784a6b235 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding GLM-5: from Vibe Coding to Agentic Engineering

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.796378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1473abf-d04b-484b-a419-926e0cb80548 · outbound

This paper cites PQCache: Product Quantization-based KVCache for Long Context LLM Inference.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding PQCache: Product Quantization-based KVCache for Long Context LLM Inference

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.799232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b8fbe2d-954a-4314-b91a-3424b16c5da2 · outbound

This paper cites LazyEviction: Lagged KV eviction with attention pattern observation for efficient long reasoning.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding LazyEviction: Lagged KV eviction with attention pattern observation for efficient long reasoning

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.802040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26379618-dee9-499f-bbb5-d9352f94721a · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.804916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bfb584b-155d-41ad-8434-49a2871f16f4 · outbound

This paper cites Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Tactic: Adaptive Sparse Attention with Clustering and Distribution Fitting for Long-Context LLMs

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.807382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aabcb895-f888-4f90-877b-1a621e302597 · outbound

This paper cites OjaKV: Context-Aware Online Low-Rank KV Cache Compression.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding OjaKV: Context-Aware Online Low-Rank KV Cache Compression

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-31T11:49:11.810189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c14fd66-b31c-4811-b6f9-ee63def766db · outbound

This paper cites Fast KV Compaction via Attention Matching.

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding Fast KV Compaction via Attention Matching

Reference 77

Resolution: malformed identifier; no resolver link, observed 2026-07-31T11:49:11.813142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers