Paper Citation Record · LEDGER

Activation Quantization of Vision Encoders Needs Prefixing Registers

As of 10 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2510.04547.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2510.04547 v5

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T11:31:31.024002Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T00:43:44.921189Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-10T00:44:48.403705Z

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cf9a2423-4647-4732-9f06-0288dde5d6d8 · outbound

This paper cites Quarot: Outlier- free 4-bit inference in rotated llms.Advances in Neural In- formation Processing Systems, 2024.

Activation Quantization of Vision Encoders Needs Prefixing Registers Quarot: Outlier- free 4-bit inference in rotated llms.Advances in Neural In- formation Processing Systems, 2024

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:26.606920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 691e77f4-2bb8-4375-bd14-9cae4ec94940 · outbound

This paper cites Understanding and overcoming the chal- lenges of efficient transformer quantization.

Activation Quantization of Vision Encoders Needs Prefixing Registers Understanding and overcoming the chal- lenges of efficient transformer quantization

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:26.714960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476f6391-cb8e-431e-ad82-d862293e4519 · outbound

This paper cites Food-101–mining discriminative components with random forests.

Activation Quantization of Vision Encoders Needs Prefixing Registers Food-101–mining discriminative components with random forests

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:26.871668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c53b06-a0cf-49df-887f-57ea08141abc · outbound

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

Activation Quantization of Vision Encoders Needs Prefixing Registers PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.030374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3546a92-d3cc-4a3b-8bf5-78f3784f5d62 · outbound

This paper cites Reproducible scal- ing laws for contrastive language-image learning.

Activation Quantization of Vision Encoders Needs Prefixing Registers Reproducible scal- ing laws for contrastive language-image learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.188083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bb8dfb7-d1f7-4d20-8a40-ee49367ebb9e · outbound

This paper cites Low-bit quantization of neural networks for efficient infer- ence.

Activation Quantization of Vision Encoders Needs Prefixing Registers Low-bit quantization of neural networks for efficient infer- ence

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.358692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a27d3050-1193-4c57-9147-172f1f750d41 · outbound

This paper cites Vision transformers need registers.

Activation Quantization of Vision Encoders Needs Prefixing Registers Vision transformers need registers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.543544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ca321b7-4f34-4af0-91c8-ccf9d548af08 · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

Activation Quantization of Vision Encoders Needs Prefixing Registers Imagenet: A large-scale hierarchical image database

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.676870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bf37be2-5ecd-41ab-924e-eba8118774a1 · outbound

This paper cites GPT3.int8(): 8-bit matrix multiplication for transformers at scale.

Activation Quantization of Vision Encoders Needs Prefixing Registers GPT3.int8(): 8-bit matrix multiplication for transformers at scale

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.795004Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 840e8366-e382-4912-a643-842aecb1faf2 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Activation Quantization of Vision Encoders Needs Prefixing Registers An image is worth 16x16 words: Transformers for image recognition at scale

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:27.922868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14d126d-8cfd-474f-bada-57d6f3bae130 · outbound

This paper cites The Llama 3 Herd of Models.

Activation Quantization of Vision Encoders Needs Prefixing Registers The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.040256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f55fbad7-3fa2-43d5-9eaf-fbca32fcdc70 · outbound

This paper cites When attention sink emerges in language models: An empirical view.

Activation Quantization of Vision Encoders Needs Prefixing Registers When attention sink emerges in language models: An empirical view

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.160933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a379cc5-ae60-49e6-98af-026275aa428d · outbound

This paper cites Atten- tion score is not all you need for token importance indica- tor in kv cache reduction: Value also matters.

Activation Quantization of Vision Encoders Needs Prefixing Registers Atten- tion score is not all you need for token importance indica- tor in kv cache reduction: Value also matters

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.283607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 913965a2-e521-479c-82fc-9df5c436d060 · outbound

This paper cites Vision transformers don’t need trained registers.

Activation Quantization of Vision Encoders Needs Prefixing Registers Vision transformers don’t need trained registers

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.393870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cc45355-91b8-4824-8bd4-6434f29d3fad · outbound

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

Activation Quantization of Vision Encoders Needs Prefixing Registers See what you are told: Visual attention sink in large multimodal models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.480682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eafd1022-cdb5-4c56-8767-5d765fa3fa86 · outbound

This paper cites Openvla: An open- source vision-language-action model.

Activation Quantization of Vision Encoders Needs Prefixing Registers Openvla: An open- source vision-language-action model

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.547383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d7e7b16-e13a-4d75-8623-268484082187 · outbound

This paper cites BERT busters: Outlier dimensions that disrupt transformers.

Activation Quantization of Vision Encoders Needs Prefixing Registers BERT busters: Outlier dimensions that disrupt transformers

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.623629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5726217-8480-430d-9c05-9e61661f31de · outbound

This paper cites 3d object representations for fine-grained categorization.

Activation Quantization of Vision Encoders Needs Prefixing Registers 3d object representations for fine-grained categorization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.704939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07c6a7dd-50ae-4e5e-a0a1-abb3980e56bd · outbound

This paper cites Repq- vit: Scale reparameterization for post-training quantization of vision transformers.

Activation Quantization of Vision Encoders Needs Prefixing Registers Repq- vit: Scale reparameterization for post-training quantization of vision transformers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.782100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d54a2076-0b40-456d-a412-83d15cae875d · outbound

This paper cites AWQ: Activation-aware weight quantization for on-device LLM compression and acceler- ation.

Activation Quantization of Vision Encoders Needs Prefixing Registers AWQ: Activation-aware weight quantization for on-device LLM compression and acceler- ation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.838901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bd27dd6-91a3-4953-83d6-aa548a13b886 · outbound

This paper cites Microsoft coco: Common objects in context.

Activation Quantization of Vision Encoders Needs Prefixing Registers Microsoft coco: Common objects in context

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:28.931119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1611594c-ed0c-44f4-a439-303df007cc30 · outbound

This paper cites Noisyquant: Noisy bias-enhanced post-training activation quantization for vision transformers.

Activation Quantization of Vision Encoders Needs Prefixing Registers Noisyquant: Noisy bias-enhanced post-training activation quantization for vision transformers

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.024922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f1c21e7-5260-4618-8dcd-5fb50a183af9 · outbound

This paper cites Post-training quantization for vision trans- former.Advances in Neural Information Processing Systems,.

Activation Quantization of Vision Encoders Needs Prefixing Registers Post-training quantization for vision trans- former.Advances in Neural Information Processing Systems,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.104623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70d1ab92-6986-4ee7-85dc-b438b8a08d5d · outbound

This paper cites Spin- quant: LLM quantization with learned rotations.

Activation Quantization of Vision Encoders Needs Prefixing Registers Spin- quant: LLM quantization with learned rotations

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.227279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffe15873-87bf-4702-baf9-177afbc04be7 · outbound

This paper cites Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers.

Activation Quantization of Vision Encoders Needs Prefixing Registers Artifacts and Attention Sinks: Structured Approximations for Efficient Vision Transformers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.345098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7921278-5a8e-4740-807c-f6778204048d · outbound

This paper cites Automated flower classification over a large number of classes.

Activation Quantization of Vision Encoders Needs Prefixing Registers Automated flower classification over a large number of classes

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.424619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b87999bc-df5c-407f-aa37-3c221f2559e6 · outbound

This paper cites an unresolved cited work.

Activation Quantization of Vision Encoders Needs Prefixing Registers Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.525589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8dae8f19-6f51-4d33-b35d-4247a62cbf62 · outbound

This paper cites an unresolved cited work.

Activation Quantization of Vision Encoders Needs Prefixing Registers Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.632457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09d59209-f1ff-43b3-b214-73b06e039de1 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Activation Quantization of Vision Encoders Needs Prefixing Registers Learning transferable visual models from natural language supervi- sion

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.707763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6604e520-b58a-4334-8838-4dcff8208d4f · outbound

This paper cites DINOv3.

Activation Quantization of Vision Encoders Needs Prefixing Registers DINOv3

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.827005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b5daa76-3506-4471-b719-541c91fd5383 · outbound

This paper cites Prefixing attention sinks can mitigate activation outliers for large language model quantization.

Activation Quantization of Vision Encoders Needs Prefixing Registers Prefixing attention sinks can mitigate activation outliers for large language model quantization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.920081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fef2cf91-f1cf-4666-848c-22982b995fa7 · outbound

This paper cites Massive activations in large language models.

Activation Quantization of Vision Encoders Needs Prefixing Registers Massive activations in large language models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:29.999905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation debb88d2-7ee9-48f9-995c-ca3963c93481 · outbound

This paper cites All bark and no bite: Rogue dimensions in transformer language models obscure representational quality.

Activation Quantization of Vision Encoders Needs Prefixing Registers All bark and no bite: Rogue dimensions in transformer language models obscure representational quality

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.068980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d596823-80b8-463c-834a-116c5c7b743e · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

Activation Quantization of Vision Encoders Needs Prefixing Registers SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.145248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff7822f-a195-407e-88ca-d8711c1f23a2 · outbound

This paper cites Fima-q: Post-training quantization for vi- sion transformers by fisher information matrix approxima- tion.

Activation Quantization of Vision Encoders Needs Prefixing Registers Fima-q: Post-training quantization for vi- sion transformers by fisher information matrix approxima- tion

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.268133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca1dafbf-086d-4748-a6ea-f03cec3ceac4 · outbound

This paper cites Aphq-vit: Post-training quan- tization with average perturbation hessian based reconstruc- tion for vision transformers.

Activation Quantization of Vision Encoders Needs Prefixing Registers Aphq-vit: Post-training quan- tization with average perturbation hessian based reconstruc- tion for vision transformers

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.330013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddc472a1-3165-49a3-8fac-2ba75b9afdc2 · outbound

This paper cites SmoothQuant: Accurate and ef- ficient post-training quantization for large language models.

Activation Quantization of Vision Encoders Needs Prefixing Registers SmoothQuant: Accurate and ef- ficient post-training quantization for large language models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.423544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d1dcf76-8894-4e08-80f8-40d7a517fcfc · outbound

This paper cites Efficient streaming language models with attention sinks.

Activation Quantization of Vision Encoders Needs Prefixing Registers Efficient streaming language models with attention sinks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.490953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6203aa4a-5d77-475c-8394-258a4f2da44f · outbound

This paper cites Noise or signal: The role of image back- grounds in object recognition.

Activation Quantization of Vision Encoders Needs Prefixing Registers Noise or signal: The role of image back- grounds in object recognition

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.577927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a80e300-3a05-4307-b5c3-afbdf1e202a4 · outbound

This paper cites Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs.

Activation Quantization of Vision Encoders Needs Prefixing Registers Mitigating Quantization Errors Due to Activation Spikes in GLU-Based LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.644179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7855009e-1a87-4611-85ad-8c52484a4743 · outbound

This paper cites DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers.

Activation Quantization of Vision Encoders Needs Prefixing Registers DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.707206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21d0e597-5b79-4d57-960a-b7a67d190536 · outbound

This paper cites Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization.

Activation Quantization of Vision Encoders Needs Prefixing Registers Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.775304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df6a712-28f0-452c-845e-aa5c5a4b8e58 · outbound

This paper cites Sigmoid loss for language image pre-training.

Activation Quantization of Vision Encoders Needs Prefixing Registers Sigmoid loss for language image pre-training

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:30.887867Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 098a7e42-6498-4971-b54a-4c87f3385676 · outbound

This paper cites w/ outliers.

Activation Quantization of Vision Encoders Needs Prefixing Registers w/ outliers

Reference 44

Resolution: malformed identifier; no resolver link, observed 2026-08-04T11:31:30.958049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 758f99cb-786c-4edf-8d75-ce5f5ec2fa0f · outbound

This paper cites 7 As reported in Tab.

Activation Quantization of Vision Encoders Needs Prefixing Registers 7 As reported in Tab

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T11:31:31.024002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d04c8671-f049-409a-93b0-74199586b173 · inbound

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs cites this paper.

Sink-Token-Aware Pruning for Fine-Grained Video Understanding in Efficient Video LLMs Activation Quantization of Vision Encoders Needs Prefixing Registers

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-09T02:19:37.991895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.