When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation | Paper Citation Record

Observation a7ece608-b3c8-4f4e-b28e-f914ce82e3b7 · outbound

This paper cites Intriguing Properties of Quantization at Scale.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Intriguing Properties of Quantization at Scale

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-08-14T12:54:27.486110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b35abc59-8425-418b-9447-32a70afa1f1e · outbound

This paper cites GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.453688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f939aea-607c-4e8f-8a70-bb49bd670813 · outbound

This paper cites KurTail : Kurtosis-based LLM Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation KurTail : Kurtosis-based LLM Quantization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.457920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15743e74-29ad-4b19-a5e0-a8e841f4bf01 · outbound

This paper cites SliceGPT: Compress Large Language Models by Deleting Rows and Columns.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.461831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c1869a-de50-4f95-9df4-3db584179cea · outbound

This paper cites QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.465867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd743173-2267-4266-9ce7-b9a89726b606 · outbound

This paper cites Proof-Pile : A pre-training dataset of mathematical texts.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Proof-Pile : A pre-training dataset of mathematical texts

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T12:54:27.527473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4d9ce1c0-307b-4516-af1b-20bb8a53345b · outbound

This paper cites LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.474150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58a35610-9b3d-40cc-b4a9-b34de15deb5a · outbound

This paper cites QuIP: 2-Bit Quantization of Large Language Models With Guarantees.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation QuIP: 2-Bit Quantization of Large Language Models With Guarantees

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.478187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59472f6-0abb-49af-8f0b-c2a7b2b09175 · outbound

This paper cites WUSH: Near-Optimal Adaptive Transforms for LLM Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation WUSH: Near-Optimal Adaptive Transforms for LLM Quantization

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.481877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e41d18f9-bd47-40c0-b3b2-5f61ac22f872 · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.485471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b36f0d59-2b80-45ad-b1ca-bf70afa683f5 · outbound

This paper cites Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-08-14T12:54:27.399667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 16703c8e-5fd8-4ecb-8c3d-083385b11dfa · outbound

This paper cites LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.492981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43f21c0e-4736-4a9f-8242-e14b0fcbb3a6 · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.496587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e5b4fa-4856-4a7d-8f26-ec9b65734d52 · outbound

This paper cites The Llama 3 Herd of Models.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.500171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8271b02-afab-4e8d-b0b4-d7e3fd4ce051 · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.504222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd7cd06e-983c-4f5c-a642-517906c19a3e · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation RULER: What's the Real Context Size of Your Long-Context Language Models?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.507843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab679e37-2974-4fad-ac33-4266e21ecace · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation OstQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.511410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f16433bc-b32b-4c31-a56a-a5c617c6fc45 · outbound

This paper cites Efficient Attentions for Long Document Summarization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Efficient Attentions for Long Document Summarization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.515463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f73f2c21-f5cd-431d-ad29-be80c634de3c · outbound

This paper cites SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.518879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60ddc4fe-f8a0-4f93-9225-b6f8c99ebc83 · outbound

This paper cites Mistral 7B.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Mistral 7B

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.522479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dfc2d5e-6282-450f-bd0b-817c29a23cad · outbound

This paper cites Equivalence tests: A practical primer for t tests, correlations, and meta-analyses.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Equivalence tests: A practical primer for t tests, correlations, and meta-analyses

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.526450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5d9bf4-acf6-4453-bb33-331adf66bcd4 · outbound

This paper cites CommVQ: Commutative Vector Quantization for KV Cache Compression.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation CommVQ: Commutative Vector Quantization for KV Cache Compression

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.530296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7799fd0d-788d-45eb-a838-8e117bdd4229 · outbound

This paper cites ParoQuant : Pairwise rotation quantization for efficient reasoning LLM inference.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation ParoQuant : Pairwise rotation quantization for efficient reasoning LLM inference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.534221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e60e2a8-5809-4727-b738-b683317cbcb9 · outbound

This paper cites DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.537704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 928b7b25-bbc2-4bb4-9636-5b685f410276 · outbound

This paper cites AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.541394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d188b0e-62a2-4556-b79d-8e6675103e1d · outbound

This paper cites SpinQuant: LLM quantization with learned rotations.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation SpinQuant: LLM quantization with learned rotations

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.545886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdb51f31-e303-4aac-aaa1-d7c6294858dc · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.550813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fb78c80-ffc1-4211-98fb-35c0aa29eb6a · outbound

This paper cites Pointer Sentinel Mixture Models.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Pointer Sentinel Mixture Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.554731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d85d81e8-6fec-4b64-90c6-f3709ce29126 · outbound

This paper cites Llama 3.2 1B model card.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Llama 3.2 1B model card

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T12:54:27.517287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8207f51e-9144-4727-87ed-657fe247fd41 · outbound

This paper cites Llama 3.2 3B model card.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Llama 3.2 3B model card

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T12:54:27.507007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d2e9bc11-2171-46ec-8243-76efe5b39789 · outbound

This paper cites Mistral-7B-v0.3 model card.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Mistral-7B-v0.3 model card

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-14T12:54:27.496531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3fce1869-01f9-488a-8bad-6eb580b0c289 · outbound

This paper cites Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-14T12:54:27.182882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e5507030-1296-4672-8fd3-cde500f5812a · outbound

This paper cites YaRN: Efficient Context Window Extension of Large Language Models.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation YaRN: Efficient Context Window Extension of Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.572452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 602fbf57-7762-458e-b027-fa7371e449fd · outbound

This paper cites Q-ROAR : Outlier-aware rescaling for RoPE position interpolation in quantized long-context LLMs.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Q-ROAR : Outlier-aware rescaling for RoPE position interpolation in quantized long-context LLMs

Reference 34

Resolution: verified exact; raw_fallback, observed 2026-08-14T12:54:27.156656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 6448f3f2-f241-4132-9a17-acd6f7398e7e · outbound

This paper cites Rethinking RoPE scaling in quantized LLM : Theory, outlier, and channel-band analysis with weight rescaling.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Rethinking RoPE scaling in quantized LLM : Theory, outlier, and channel-band analysis with weight rescaling

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.579342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d5cce92-8921-4b3b-93f6-f21aa0ce0107 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Compressive Transformers for Long-Range Sequence Modelling

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.582699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f5c81ea-f5ca-40a7-a532-24e3a972d0cf · outbound

This paper cites Pushing the Limits of Block Rotations in Post-Training Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Pushing the Limits of Block Rotations in Post-Training Quantization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.586145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37b24400-32a6-4aa7-bf9a-240b2eccdf38 · outbound

This paper cites OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.589723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1f88f08-d91c-4632-8cf4-27e9ab01cb44 · outbound

This paper cites DartQuant : Efficient rotational distribution calibration for LLM quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation DartQuant : Efficient rotational distribution calibration for LLM quantization

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.593701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de61ceeb-fba0-43ab-a423-3e6ea55c1470 · outbound

This paper cites RoFormer : Enhanced transformer with rotary position embedding.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation RoFormer : Enhanced transformer with rotary position embedding

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.597427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d95fbdc1-b350-4e4e-931c-2326e589b504 · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.600791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b7a28b2-59b1-4ad8-a9c2-401784380ae3 · outbound

This paper cites FlatQuant: Flatness Matters for LLM Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation FlatQuant: Flatness Matters for LLM Quantization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.604734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 772d053a-e0ab-4e07-b7bf-fd32b065b019 · outbound

This paper cites QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.608490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e06b035f-5455-42b9-a447-a8d42814148c · outbound

This paper cites FPTQuant: Function-Preserving Transforms for LLM Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation FPTQuant: Function-Preserving Transforms for LLM Quantization

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.612471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe5fcabc-05ce-4c14-adad-052dbff2bcb0 · outbound

This paper cites SQuat: Subspace-orthogonal KV Cache Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation SQuat: Subspace-orthogonal KV Cache Quantization

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.616234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56f04a3c-c28b-420f-8654-1eea4d2fb4de · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Outlier Suppression+: Accurate quantization of large language models by equivalent and optimal shifting and scaling

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.620007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d94b800-b48c-4858-b647-134ec90e7847 · outbound

This paper cites PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation PolarQuant: Leveraging Polar Transformation for Efficient Key Cache Quantization and Decoding Acceleration

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.623843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2ac31c7-b9b6-4941-81e4-01e48c264604 · outbound

This paper cites DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation DFRot: Achieving Outlier-Free and Massive Activation-Free for Rotated LLMs with Refined Rotation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.627771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5130a4d-b657-4d64-a736-f9041ef57b40 · outbound

This paper cites SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.631578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ad9794-2fea-403b-b5a9-3651cfbb2874 · outbound

This paper cites Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.635318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a8e2b05-7b8d-4bd4-893b-ad6baf26640a · outbound

This paper cites ButterflyQuant : Ultra-low-bit LLM quantization through learnable orthogonal butterfly transforms.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation ButterflyQuant : Ultra-low-bit LLM quantization through learnable orthogonal butterfly transforms

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.638970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db96c3ec-c7a3-424f-bb42-a5d9a0a0dfdf · outbound

This paper cites ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices.

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.642378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dddfec87-3a34-4383-b6c4-27e584ef77a6 · outbound

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

When Local Variance Optimality Is Not Enough: RoPE-Aligned Q/K Rotations for Dynamic 4-Bit Quantisation TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-14T12:54:26.646214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers