OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond | Paper Citation Record

Observation ecd715b1-7218-406c-b391-10ef39050499 · outbound

This paper cites HadaCore: Tensor Core Accelerated Hadamard Transform Kernel.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond HadaCore: Tensor Core Accelerated Hadamard Transform Kernel

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.636770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f0ec5982-051f-459b-a0f8-1ecd4a32c86f · outbound

This paper cites gpt-oss-120b & gpt-oss-20b Model Card.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond gpt-oss-120b & gpt-oss-20b Model Card

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.646425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation dc9d6ca1-9a3a-4a0b-8368-cba5d646fb61 · outbound

This paper cites Systematic Outliers in Large Language Models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Systematic Outliers in Large Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.649938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e453f698-d8ce-43a5-bc72-6cf5c451dc05 · outbound

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

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Quarot: Outlier-free 4-bit inference in rotated llms.Advances in Neural Information Processing Systems, 37:100213– 100240

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.825069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 372b029d-5e0d-4ea3-9de4-dea3e5a0e476 · outbound

This paper cites Qwen3-VL Technical Report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Qwen3-VL Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.643352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c4e106a4-4bce-42d6-a1de-70d10ee4f0eb · outbound

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

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Longbench: A bilingual, multitask benchmark for long context understanding

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.828383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4fffa210-298a-4631-936c-69201901db9e · outbound

This paper cites Bondarenko, M.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Bondarenko, M

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.832499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cb595ec9-f028-46c7-b7b4-e4442ae1acb7 · outbound

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

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 2026-08-12T06:34:41.77262+00:00.

Observation 06428fef-c58c-42c6-a6b8-fcb1a7fb8627 · outbound

This paper cites Qwen3-Coder-Next Technical Report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Qwen3-Coder-Next Technical Report

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.499287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1c6ca095-1675-457f-95ac-493db3a39fb1 · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.841929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8f723870-2de1-4691-9464-f77518348e75 · outbound

This paper cites SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.629942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 73d3b5e2-2f43-45ef-9027-377a3abfea1f · outbound

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

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.530075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ef738569-2595-40ac-9497-d8d2453f9d6d · outbound

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

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.533040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5bcaaeb4-84f8-49a7-a303-44f426b2c0d2 · outbound

This paper cites Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.507093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 43ede9d8-fd69-4010-9872-b811597985ab · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 15

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.856033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation db8efc28-cf26-440c-ae0f-fac15c49d79e · outbound

This paper cites PolarQuant: Quantizing KV Caches with Polar Transformation.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond PolarQuant: Quantizing KV Caches with Polar Transformation

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.520404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e7dd9bfb-1645-4a45-8391-4e62b0b989f8 · outbound

This paper cites A survey on large language model acceleration based on kv cache management.Transactions on Machine Learning Research.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond A survey on large language model acceleration based on kv cache management.Transactions on Machine Learning Research

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.852150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a0a8bdb8-ffe2-42b5-a22f-bbfd492ab9fd · outbound

This paper cites Zipcache: Accurate and efficient kv cache quantization with salient token identification.Advances in Neural Information Processing Systems, 37:68287–68307.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Zipcache: Accurate and efficient kv cache quantization with salient token identification.Advances in Neural Information Processing Systems, 37:68287–68307

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.836400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4daea65d-389a-4ad0-b273-bf6a71929406 · outbound

This paper cites WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.513467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation be774772-dbd5-4fb3-9085-aabc51df1645 · 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.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Kvquant: Towards 10 million context length llm inference with kv cache quantization.Advances in Neural Information Processing Systems, 37:1270–1303

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.903582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cb9e9641-d8ca-4f91-8a30-39d0f78b9340 · outbound

This paper cites The llama 3 herd of models.preprint.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond The llama 3 herd of models.preprint

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.863091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 30cd14bb-fe5f-4d76-b91f-8a1eacb2baae · outbound

This paper cites Isoquant: Hardware-aligned so (4) isoclinic rotations for llm kv cache compres- sion.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Isoquant: Hardware-aligned so (4) isoclinic rotations for llm kv cache compres- sion

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.523391Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 40471e3a-fd86-4eab-96cd-5acd8235482b · outbound

This paper cites Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Massive Values in Self-Attention Modules are the Key to Contextual Knowledge Understanding

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.496041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ae4bd46a-6c61-4509-a8f0-db1293093714 · outbound

This paper cites Llmtest_needleinahaystack.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Llmtest_needleinahaystack

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.920696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3a4d22bc-069a-4117-8628-a0acf34ca726 · outbound

This paper cites See what you are told: Visual attention sink in large multimodal models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond See what you are told: Visual attention sink in large multimodal models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.923036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7245277d-0ffc-4d4e-93d7-97cd83fdbd29 · outbound

This paper cites Kumar, Š.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Kumar, Š

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.924971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 74527fd8-9233-4f79-bd50-8345ac59ce47 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond LLaVA-OneVision: Easy Visual Task Transfer

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.619781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 35a2ed9b-acca-44d0-8f7b-cb2d4e5a932e · outbound

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

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond A Survey on Large Language Model Acceleration based on KV Cache Management

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.590441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 348b6ba1-7a44-4b8c-91ef-076c5be59bb4 · outbound

This paper cites Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.596260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0e9b1aea-0cfa-418b-9d84-1a22915e00ad · outbound

This paper cites Tweo: Transformers without extreme outliers enables fp8 training and quantization for dummies.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Tweo: Transformers without extreme outliers enables fp8 training and quantization for dummies

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.587263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8c20e483-49f1-455d-82de-47881dc9ae30 · 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.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of machine learning and systems, 6:87–100

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.906007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ba2c2f48-799b-41f3-ba21-f4716cc82faa · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.909825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 617d7a4b-47d0-4881-95e5-b1d67744347b · outbound

This paper cites Minicache: Kv cache compression in depth dimension for large language models.Advances in Neural Information Processing Systems, 37:139997–140031.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Minicache: Kv cache compression in depth dimension for large language models.Advances in Neural Information Processing Systems, 37:139997–140031

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.901311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 03ce1c3d-475b-4de0-8d96-1f1fe8906514 · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.908020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c818df99-2831-417f-8934-ab7d1403d2a2 · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.918678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 31e624b1-d012-4bf7-8b9e-146df961e10e · outbound

This paper cites Kv cache compression for inference efficiency in llms: A review.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Kv cache compression for inference efficiency in llms: A review

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.891294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b91442be-f4f7-4525-84c3-a320476ca5cf · outbound

This paper cites Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Ocrbench: on the hidden mystery of ocr in large multimodal models.Science China Information Sciences, 67(12):220102

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.897321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6cd8ccc9-250e-469a-8368-1e925f9d6fa6 · outbound

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

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.560931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8ca60cd6-996b-4faa-a111-123943c07090 · outbound

This paper cites Docvqa: A dataset for vqa on document images.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Docvqa: A dataset for vqa on document images

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.927325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 91dc4cb1-e57f-4aa3-afc3-70b4f16c5811 · outbound

This paper cites A White Paper on Neural Network Quantization.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond A White Paper on Neural Network Quantization

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.516687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 79a29c3a-2d08-4297-a222-ae5f83f0d284 · outbound

This paper cites Rotorquant: Clifford algebra vector quantization for llm kv cache compression.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Rotorquant: Clifford algebra vector quantization for llm kv cache compression

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.882780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fe7a6def-692f-4b84-9627-e2d5cf0b8371 · outbound

This paper cites Head-aware kv cache compression for efficient visual autoregressive modeling.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Head-aware kv cache compression for efficient visual autoregressive modeling

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.880169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0e824b0b-5c16-4fd6-95cc-d135cbd340d2 · outbound

This paper cites Gated attention for large language models: Non-linearity, sparsity, and attention-sink-free.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Gated attention for large language models: Non-linearity, sparsity, and attention-sink-free

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.885000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f4e45f87-398a-4fd3-9441-4ad2b3c5a16a · outbound

This paper cites Accurate kv cache quantization with outlier tokens tracing.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Accurate kv cache quantization with outlier tokens tracing

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.887063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 41d962c0-fc9c-4511-8c8c-77d62cc30e1e · outbound

This paper cites RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.552003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b6528dfe-9198-4bf9-9b15-d9d4aedac85d · outbound

This paper cites Unveiling super experts in mixture-of-experts large language models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unveiling super experts in mixture-of-experts large language models

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.566981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d689c19e-40d5-4345-90c1-b317885daa5a · outbound

This paper cites Akvq-vl: Attention-aware kv cache adaptive 2-bit quantization for vision-language models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Akvq-vl: Attention-aware kv cache adaptive 2-bit quantization for vision-language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.889109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 12675734-b3e5-423b-9e90-db51772bc204 · outbound

This paper cites Xstreamvggt: Extremely memory-efficient streaming vision geometry grounded transformer with kv cache compression.Journal of the Society for Information Display.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Xstreamvggt: Extremely memory-efficient streaming vision geometry grounded transformer with kv cache compression.Journal of the Society for Information Display

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.877496Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ade11d7c-0e74-4014-a1cb-322d12922c7a · outbound

This paper cites KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.564169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4c0a1a53-3f16-4983-80fb-9df02a31f889 · outbound

This paper cites Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.543129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 394692bc-6410-4042-a7aa-acc161029fe6 · outbound

This paper cites Massive Activations in Large Language Models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Massive Activations in Large Language Models

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.583961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0f4301aa-4fea-4566-b488-53b207df054c · outbound

This paper cites Plug-and-play 1.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Plug-and-play 1

Reference 52

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.632939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9fe4a42a-9aa2-448a-a3e9-2f9a8264f3c0 · outbound

This paper cites Kimi Linear: An Expressive, Efficient Attention Architecture.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Kimi Linear: An Expressive, Efficient Attention Architecture

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.546337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a5cdca0f-404a-464f-bb97-e58c1b8d5b5c · outbound

This paper cites Longcat-flash-omni technical report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Longcat-flash-omni technical report

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.610161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eabeff5c-908d-4f95-b590-969378227d5e · outbound

This paper cites Longcat-next: Lexicalizing modalities as discrete tokens.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Longcat-next: Lexicalizing modalities as discrete tokens

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.613463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1ec59c8a-f67d-4f39-a356-4538c960826b · outbound

This paper cites Longcat-video technical report.arXiv preprint arXiv:2510.22200.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Longcat-video technical report.arXiv preprint arXiv:2510.22200

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.569855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e3459f03-ba0e-41c6-acde-a10435ae50ae · outbound

This paper cites Longcat-flash-thinking-2601 technical report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Longcat-flash-thinking-2601 technical report

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.555273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 42b774b1-87ae-462e-a334-67bfa78d7e3f · outbound

This paper cites Introducing LongCat-flash-thinking: A technical report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Introducing LongCat-flash-thinking: A technical report

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.510629Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ff86933c-1abb-4b62-a5b1-d8bcdb3aaad9 · outbound

This paper cites Longcat-flash technical report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Longcat-flash technical report

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.623225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4aadfc4a-679b-46cc-80cd-91613848ca31 · outbound

This paper cites LongCat-Image Technical Report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond LongCat-Image Technical Report

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.616421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 832b6e7a-707f-43ee-8f83-3d2df668885f · outbound

This paper cites Attention reallocation: Towards zero-cost and controllable hallucination mitigation of mllms.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Attention reallocation: Towards zero-cost and controllable hallucination mitigation of mllms

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.867383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 688d1003-c064-4455-821b-1566d3f28439 · outbound

This paper cites Turboquant+.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Turboquant+

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.874404Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4b8ad9c6-85ff-4bbd-826f-55ae12a1ff6e · outbound

This paper cites Vaswani, N.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Vaswani, N

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.872294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 582d8f86-0f0a-450d-bd0b-cd617692a39d · outbound

This paper cites Look-m: Look-once optimization in kv cache for efficient multimodal long-context inference.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Look-m: Look-once optimization in kv cache for efficient multimodal long-context inference

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.839421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4c45a02f-890f-42af-86ff-9d77e382ba3b · outbound

This paper cites arXiv preprint arXiv:2603.21065 , year=.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond arXiv preprint arXiv:2603.21065 , year=

Reference 65

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.573075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 33612b44-44b1-474a-a5fb-8b01832ffd3f · outbound

This paper cites Outlier suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Outlier suppression+: Accurate quantization of large language models by equivalent and effective shifting and scaling

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.849032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ee050c57-a5f3-4bd4-b748-f7a2d3473e1e · outbound

This paper cites Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.626143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5388d479-76ff-47b1-9524-51736dd6518a · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Efficient Streaming Language Models with Attention Sinks

Reference 68

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.540158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3caf9b96-20eb-41e8-a37d-e11192a8847d · outbound

This paper cites Smoothquant: Accurate and efficient post-training quantization for large language models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Smoothquant: Accurate and efficient post-training quantization for large language models

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.914330Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f647178f-60cc-4b65-8008-7726a2f16f14 · outbound

This paper cites Exploring layer-wise information effectiveness for post-training quantization in small language models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Exploring layer-wise information effectiveness for post-training quantization in small language models

Reference 70

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.558157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e514ea86-2909-4e40-b8ea-cbf5bb78be7e · outbound

This paper cites Dope: Denoising rotary position embedding.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Dope: Denoising rotary position embedding

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.606398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 420a5449-9e48-40a2-a9e9-93f82d155e9a · outbound

This paper cites Qwen3-Omni Technical Report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Qwen3-Omni Technical Report

Reference 72

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.549036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ca4f729e-d93f-480f-a792-9f706fa4e5c6 · outbound

This paper cites Qwen3 Technical Report.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Qwen3 Technical Report

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.526422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 348bb6e0-25a0-40e5-aa8b-cca2c47d56e6 · outbound

This paper cites TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-20T08:09:22.519591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 57f43763-10b1-4b62-b726-af0825c80b33 · outbound

This paper cites Qjl: 1-bit quantized jl transform for kv cache quan- tization with zero overhead.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Qjl: 1-bit quantized jl transform for kv cache quan- tization with zero overhead

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.845275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b43ac74d-020a-4f09-9408-5d9282b6ecbb · outbound

This paper cites Beyond outliers: A data-free layer-wise mixed- precision quantization approach driven by numerical and structural dual-sensitivity.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Beyond outliers: A data-free layer-wise mixed- precision quantization approach driven by numerical and structural dual-sensitivity

Reference 76

Resolution: verified exact; arxiv_id, observed 2026-05-20T07:58:07.593304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7d4959ab-dc1e-4bff-b233-1d56600a080d · outbound

This paper cites Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Reference 77

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.575931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 8a1e7efe-6c2c-4ea8-a541-4d9f132d3480 · outbound

This paper cites Streaming 4D Visual Geometry Transformer.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Streaming 4D Visual Geometry Transformer

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.599763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6cb40198-ed7b-470f-adce-4f181def8767 · outbound

This paper cites Softpick: No Attention Sink, No Massive Activations with Rectified Softmax.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Softpick: No Attention Sink, No Massive Activations with Rectified Softmax

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-05-20T07:58:07.603107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation de7fd090-7471-49a4-b117-d6aa9124400a · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.911799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 74a1fb18-76d9-4dfb-88a5-fa41b456d603 · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.899153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5e618dff-44b0-4622-888b-b8051cc05af4 · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.893374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0136603d-faf1-4b64-91f2-f0f40dccad9f · outbound

This paper cites an unresolved cited work.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-05-20T07:58:07.916455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ae80a254-32b3-4b48-bd17-8d3e5e7698c8 · outbound

This paper cites from the wild.

OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond from the wild

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T07:58:07.895396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers