Paper Citation Record · LEDGER

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook

As of 16 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2412.06875.

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

pith.paper-citation-record.v1
2412.06875 v1

Coverage vector

measured 43 of 43 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T19:32:44.358848Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

43 of 43 outbound references displayed

verified exact0
verified fuzzy20
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 947eccc3-b64a-4b40-8711-1acd7ee3e520 · outbound

This paper cites Metaquant: Learning to quantize by learning to penetrate non-differentiable quantization.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Metaquant: Learning to quantize by learning to penetrate non-differentiable quantization

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.844044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5ece04c2-c9f9-4e66-84a8-c3498454a5c8 · outbound

This paper cites DKM: Differentiable K-Means Clustering Layer for Neural Network Compression.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook DKM: Differentiable K-Means Clustering Layer for Neural Network Compression

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.203028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e5adb19-976d-4e9f-aaa7-43811b0da268 · outbound

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

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Imagenet: A large-scale hierarchical image database

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.206644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ffc83a7-313b-4f01-9841-e2bdc6c53a12 · outbound

This paper cites VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.210234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff75e391-63f5-4fad-a1d6-0d5f20288dc6 · outbound

This paper cites Hawq-v2: Hessian aware trace-weighted quantization of neural networks.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Hawq-v2: Hessian aware trace-weighted quantization of neural networks

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.826502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4a89bcf7-a78b-48bc-9f1a-3b0b7c8c1cd5 · outbound

This paper cites Training with quantization noise for extreme model com- pression.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Training with quantization noise for extreme model com- pression

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.815126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d1c6958f-2951-40d0-b759-42759093d662 · outbound

This paper cites Deep neural network com- pression by in-parallel pruning-quantization.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Deep neural network com- pression by in-parallel pruning-quantization

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.803285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b68703e9-4b60-44f7-9db6-ab341b9e95b4 · outbound

This paper cites Compressing Deep Convolutional Networks using Vector Quantization.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Compressing Deep Convolutional Networks using Vector Quantization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.225592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dab58ec3-f606-4aad-8abf-04104ed0c9d9 · outbound

This paper cites an unresolved cited work.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:32:44.790632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7da2b822-67c8-4b58-bc72-30241fb23b2e · outbound

This paper cites Deep residual learning for image recognition.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Deep residual learning for image recognition

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.233568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8230678-3c32-4d0e-9c87-b9e38053e0d2 · outbound

This paper cites Mask r-cnn.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Mask r-cnn

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.238134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 081dbb8d-9b5c-47a5-8233-7bf0f3baa3d3 · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.241948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dffc4793-13cb-41fe-96de-39c75b412df7 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Gans trained by a two time-scale update rule converge to a local nash equilib- rium

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.245891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f671b8f-92b4-4d81-9b52-27ecf2018a70 · outbound

This paper cites an unresolved cited work.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:32:44.758147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation dddd57c4-ee4e-4ea6-b4ae-26c7e2fa895d · outbound

This paper cites Categorical Reparameterization with Gumbel-Softmax.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Categorical Reparameterization with Gumbel-Softmax

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.252836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62c91e27-1796-4ecc-8c14-51b36abdff11 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Adam: A Method for Stochastic Optimization

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.256694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bb9cc10-aa5d-4c8f-8886-56ae3a94413b · outbound

This paper cites Fully quantized network for object detection.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Fully quantized network for object detection

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.746614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 034217a5-3c92-4211-8437-6b4dbb33e7f8 · outbound

This paper cites Q-diffusion: Quantizing diffusion models.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Q-diffusion: Quantizing diffusion models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.734904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5c3c254b-5429-44d4-8d65-f8b7f197b4c3 · outbound

This paper cites Focal Loss for Dense Object Detection.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Focal Loss for Dense Object Detection

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.267670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8973057-3c29-47f9-9b3b-9c5a1c4f3861 · outbound

This paper cites Microsoft coco: Common objects in context.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Microsoft coco: Common objects in context

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.271697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3dc2b82-4f13-485d-b377-8fae4886ae35 · outbound

This paper cites Towards accurate binary convolutional neural network.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Towards accurate binary convolutional neural network

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.717206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 60992459-198f-4539-abab-80698bb0272a · outbound

This paper cites SGDR: Stochastic Gradient Descent with Warm Restarts.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook SGDR: Stochastic Gradient Descent with Warm Restarts

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.279290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f79d98e-9c88-40f7-97f5-a61b65a9feee · outbound

This paper cites Permute, quantize, and fine-tune: Efficient compression of neural networks.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Permute, quantize, and fine-tune: Efficient compression of neural networks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.705495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4f334094-fc35-4519-8aba-941d0d962187 · outbound

This paper cites Profit: A novel training method for sub-4-bit mobilenet models.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Profit: A novel training method for sub-4-bit mobilenet models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.693084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 02e01b34-5458-476a-9287-bc3378099909 · outbound

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

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Learning transferable visual models from natural language supervi- sion

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.290898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a2163b2-6e28-4182-b3e6-30e4ffe24cd2 · outbound

This paper cites Xnor-net: Imagenet classification using bi- nary convolutional neural networks.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Xnor-net: Imagenet classification using bi- nary convolutional neural networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.674168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0c4bf894-aaf3-45fc-a99f-edb8012365dc · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook High-resolution image synthesis with latent diffusion models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.297894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffb220a3-1aa2-499d-9983-d79c86871e43 · outbound

This paper cites Improved techniques for training gans.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Improved techniques for training gans

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.301992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f5be09f-dcae-4e58-a3b8-0edb98e158c5 · outbound

This paper cites Mobilenetv2: Inverted residuals and linear bottlenecks.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Mobilenetv2: Inverted residuals and linear bottlenecks

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.647858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6e460636-3f39-4e66-bcb6-4e4c8ff0faa3 · outbound

This paper cites Learning Discrete Weights Using the Local Reparameterization Trick.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Learning Discrete Weights Using the Local Reparameterization Trick

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.309324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cf53a5-9ce0-4804-b33e-bee748d723eb · outbound

This paper cites Cluster- ing convolutional kernels to compress deep neural networks.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Cluster- ing convolutional kernels to compress deep neural networks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.635425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5fdfdc41-a20e-42bf-9f3f-03e04a9ad90d · outbound

This paper cites And the Bit Goes Down: Revisiting the Quantization of Neural Networks.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook And the Bit Goes Down: Revisiting the Quantization of Neural Networks

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.316534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b56ec7ba-1412-4f73-b5d4-9ed0564e8722 · outbound

This paper cites Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.321142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fefca84e-3e9a-4563-8138-98e339936e7a · outbound

This paper cites Haq: Hardware-aware automated quantization with mixed precision.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Haq: Hardware-aware automated quantization with mixed precision

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.623335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 753d8860-e761-4223-b9aa-f3e5ba4157fa · outbound

This paper cites Quantized convolutional neural networks for mobile devices.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Quantized convolutional neural networks for mobile devices

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.610562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c322cf6d-48eb-45f4-9adc-dac3d82d3865 · outbound

This paper cites Gobo: Quantizing attention-based nlp models for low latency and energy efficient inference.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Gobo: Quantizing attention-based nlp models for low latency and energy efficient inference

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.598952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2249ee6b-4fff-41c2-94fd-8de8b9ce173e · outbound

This paper cites Trained Ternary Quantization.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Trained Ternary Quantization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T19:32:44.334963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45525b1f-b930-4c6d-8295-be3f6512a568 · outbound

This paper cites an unresolved cited work.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-11T19:32:44.586836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 65fec3dc-1f44-4dc7-85b7-e9ccc2dd75a0 · outbound

This paper cites As shown in Figure 5, each type of low-bit network is evenly composed of differ- ent codewords of the same universal codebook.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook As shown in Figure 5, each type of low-bit network is evenly composed of differ- ent codewords of the same universal codebook

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.573087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation be4644f8-2cec-41ec-91c7-2a6ea144f69d · outbound

This paper cites We then evaluate the impact of these codebooks on network performance.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook We then evaluate the impact of these codebooks on network performance

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.560028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 702520ef-7002-493d-a803-05fe2bbf7878 · outbound

This paper cites Random candidate assignments yield the poorest performance, with the accuracy of 2-bit ResNet-18 and 2-bit ResNet-50 dropping to only 39.97% and 44.36%, respec- tively.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Random candidate assignments yield the poorest performance, with the accuracy of 2-bit ResNet-18 and 2-bit ResNet-50 dropping to only 39.97% and 44.36%, respec- tively

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.545417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 0bf46b52-4f47-427d-992b-40d58cbc9f4c · outbound

This paper cites For ResNet-18/50, the primary blocks are ’Ba- sicBlock’ and ’Bottleneck’.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook For ResNet-18/50, the primary blocks are ’Ba- sicBlock’ and ’Bottleneck’

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.532666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 4bee6268-7e30-4d48-bdf8-7ca003a1ccaf · outbound

This paper cites Compared to other state-of-the-art uniform quan- tization methods, the images generated by VQ4ALL are more similar to those produced by the floating-point net- work.

VQ4ALL: Efficient Neural Network Representation via a Universal Codebook Compared to other state-of-the-art uniform quan- tization methods, the images generated by VQ4ALL are more similar to those produced by the floating-point net- work

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T19:32:44.520176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

No inbound Pith citation observations are available.