NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache | Paper Citation Record

Observation 04021691-f782-4ee0-911a-c5d942775906 · outbound

This paper cites GPT-4 Technical Report.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:19.441861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c064fde5-75fc-4a2e-b708-2129e03f7fad · outbound

This paper cites Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213– 100240, 2025.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213– 100240, 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:26.876599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d1864e14-059f-4226-8a0c-6a126f8d17bb · outbound

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

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache LongBench: A bilingual, multitask benchmark for long context understanding

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:26.751190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 88c24244-3562-4128-9757-43225bc40b2e · outbound

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

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:19.668535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba5f5ffe-9949-4414-a9f7-cecf98a97fd4 · outbound

This paper cites Palu: Kv- cache compression with low-rank projection.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Palu: Kv- cache compression with low-rank projection

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:26.582959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 91388cae-ec1a-4f50-b9c5-1d2c76dc15a4 · outbound

This paper cites an unresolved cited work.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:19.764346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be3bddb7-379b-45c4-ad85-3dab61ece3b6 · outbound

This paper cites PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:19.813220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 589311a8-858a-4cf4-86fd-0d9430dc88b7 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:19.966304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523759e0-e41f-47d2-b35d-306f8731b9da · outbound

This paper cites SDR: Efficient Neural Re-ranking using Succinct Document Representation.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache SDR: Efficient Neural Re-ranking using Succinct Document Representation

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:42:23.794083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e6527f5f-df86-49c4-b3d3-88fdb0cc812f · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache QLoRA: Efficient Finetuning of Quantized LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.170685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation daa42476-cae2-4cc7-a772-afad805be48b · outbound

This paper cites Extreme Compression of Large Language Models via Additive Quantization.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Extreme Compression of Large Language Models via Additive Quantization

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.242101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20dde1d7-2727-4da2-8f76-345abae103fd · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.321754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b40e5c0-9aa5-4cf1-b909-8b9a77f3007a · outbound

This paper cites A framework for few-shot language model evaluation, 07 2024.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache A framework for few-shot language model evaluation, 07 2024

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:26.414042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3b8af31b-88bf-48d7-8a27-2733d47331b5 · outbound

This paper cites The Llama 3 Herd of Models.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.499175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e792160-6fcd-460f-ab99-611bae593cf0 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.623145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96eb77fc-124f-4476-92df-21cf9a40f843 · outbound

This paper cites Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions.SIAM review, 53(2):217–288, 2011.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions.SIAM review, 53(2):217–288, 2011

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.725384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 735a74b6-9c5a-4958-af5b-36956bc96a53 · outbound

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

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.783045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a3d52a4-87ed-4ce3-9d03-863457c7e3e0 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Measuring Massive Multitask Language Understanding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.854098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca32f2e-10e1-42c3-a799-bdc70c0a2837 · outbound

This paper cites Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303, 2024.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.904104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67e9cea5-60b0-4f83-a1c7-19a6a6315861 · outbound

This paper cites OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:20.965959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ffa03f2-aeb4-406d-82c3-eb69fd9ac9d4 · outbound

This paper cites an unresolved cited work.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.019251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c33b91b4-7076-4fed-839a-2d4ea3d92494 · outbound

This paper cites SqueezeLLM: Dense-and-Sparse Quantization.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache SqueezeLLM: Dense-and-Sparse Quantization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.069575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 510a1e5d-fb85-4824-9e6c-b785a122dce8 · outbound

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

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Efficient memory management for large language model serving with pagedattention

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.150721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93600400-dce6-4a09-8da9-685a63ff55d3 · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474, 2020

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.194134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d7e3402-796f-45cc-8aba-8a6650c27255 · outbound

This paper cites Snapkv: Llm knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970, 2024.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Snapkv: Llm knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.275247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e30a4de3-986a-4d57-bf11-6c0d9001326c · outbound

This paper cites MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.377519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ff29666-6aef-41c8-840f-82f242a95a2f · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of Machine Learning and Systems, 6:87–100, 2024.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of Machine Learning and Systems, 6:87–100, 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:26.198825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0c0a7fbb-d6e8-41a6-9cc4-bf018e610764 · outbound

This paper cites VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.528632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d3692ca-f0bf-41ec-ae6a-a95c3ae19497 · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache SpinQuant: LLM quantization with learned rotations

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.563050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86282d67-e22d-4b85-a153-824487fbbdd5 · outbound

This paper cites KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.631333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef42813c-e02f-4efe-a7e1-e6948ece603f · outbound

This paper cites an unresolved cited work.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:42:25.985348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8a2d3072-513e-4c5a-8db2-9ed89116cbc4 · outbound

This paper cites Cake: Cascading and adaptive kv cache eviction with layer preferences.arXiv preprint arXiv:2503.12491, 2025.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Cake: Cascading and adaptive kv cache eviction with layer preferences.arXiv preprint arXiv:2503.12491, 2025

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.756963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c80056c-736e-482b-884d-e635ae7bda2a · outbound

This paper cites Coqa: A conversational question answering challenge.Transactions of the Association for Computational Linguistics, 7:249–266, 2019.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Coqa: A conversational question answering challenge.Transactions of the Association for Computational Linguistics, 7:249–266, 2019

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:21.846993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93d8bf7c-4959-4bc8-8d67-58a6147bd157 · outbound

This paper cites Hanson-wright inequality and sub-gaussian concentra- tion.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Hanson-wright inequality and sub-gaussian concentra- tion

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:25.738176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8a99de4a-d23d-4050-850c-d43e52fedb8c · outbound

This paper cites an unresolved cited work.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:42:25.616849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9e15ebc8-9549-4bb6-a683-c712d4cb7235 · outbound

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

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:22.125724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0a527a4-b230-468f-bd55-1992104ff61b · outbound

This paper cites QuIP#: Even better LLM quantization with hadamard incoherence and lattice codebooks.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache QuIP#: Even better LLM quantization with hadamard incoherence and lattice codebooks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:25.408508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 07b96d21-7971-43bc-ac17-0773479f1a63 · outbound

This paper cites Attention is all you need.Advances in neural information processing systems, 30, 2017.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Attention is all you need.Advances in neural information processing systems, 30, 2017

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:22.302830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e1376b-fe23-4b48-b5f8-6a7a9f9b03e5 · outbound

This paper cites BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:22.378319Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 487e206a-3751-47e3-9ec8-a14135340265 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Chain-of-thought prompting elicits reasoning in large language models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:22.452938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d96754ce-5019-4912-aa00-8454d5ad2387 · outbound

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

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:22.512307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87d1acc8-019d-4a99-bedb-7d94516415f0 · outbound

This paper cites Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:42:23.446611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 96f64d5c-4832-4640-93ca-2772e53b30f5 · outbound

This paper cites Kv cache is 1 bit per channel: Efficient large language model inference with coupled quantization.Advances in Neural Information Processing Systems, 37:3304–3331, 2024.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Kv cache is 1 bit per channel: Efficient large language model inference with coupled quantization.Advances in Neural Information Processing Systems, 37:3304–3331, 2024

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:25.245202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b3f8a2f2-0842-4cc6-93e4-361c804c15e6 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:25.047251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4c769c61-a318-4598-9404-46aaa563c585 · outbound

This paper cites Decompose Σ = Cov(X) =D+A , D= diag(Σ),A ii = 0,∥A∥ F ≤Γ.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Decompose Σ = Cov(X) =D+A , D= diag(Σ),A ii = 0,∥A∥ F ≤Γ

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:24.860495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 005a9e7c-b858-409e-88b6-4d08833ba59f · outbound

This paper cites an unresolved cited work.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:42:24.627060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9ae2d4ba-a8d4-4bcd-a9df-c8af1065cd99 · outbound

This paper cites Then hTDh= 1−¯ε, f(h) :=h TAh= 1 d sTAs, and Var(Yi) = (1−¯ε) +f(h).

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Then hTDh= 1−¯ε, f(h) :=h TAh= 1 d sTAs, and Var(Yi) = (1−¯ε) +f(h)

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:24.481106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3ff43d2c-dac1-43d0-9560-f3cb61434e5a · outbound

This paper cites Applying the Hanson-Wright inequality [34], for anyu >0 Pr |sTAs|> u ≤2 exp −c u2/Γ2 wherecis a universal constant.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Applying the Hanson-Wright inequality [34], for anyu >0 Pr |sTAs|> u ≤2 exp −c u2/Γ2 wherecis a universal constant

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:24.295084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 94c89684-f3fd-4a5a-9186-136648659cb3 · outbound

This paper cites Exponent becomes −ln(2/α) ; hence Pr(|f(h)|> t)≤α.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Exponent becomes −ln(2/α) ; hence Pr(|f(h)|> t)≤α

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:42:24.086439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9145d042-9aea-4cae-9d61-0018c71de493 · outbound

This paper cites an unresolved cited work.

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache Unresolved cited work

Reference 50

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T14:42:23.342602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers