Paper Citation Record · LEDGER

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

As of 20 August 2026, this Paper Citation Record lists 100 of 126 outbound references and 5 inbound Pith citation observations for arXiv:2412.10958.

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

pith.paper-citation-record.v1
2412.10958 v3

Coverage vector

measured 100 of 126 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T15:33:13.575809Z

measured 105 of 105 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:47:30.290200Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T18:13:49.029434Z

Reference resolution

100 of 126 outbound references displayed

verified exact0
verified fuzzy17
unresolved83
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9900d614-266b-49b0-9c1a-3cf57d406d9f · outbound

This paper cites Stochastic Interpolants: A Unifying Framework for Flows and Diffusions.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Stochastic Interpolants: A Unifying Framework for Flows and Diffusions

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.009735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ae505f-851c-45c7-9555-3153ca79891f · outbound

This paper cites Reverse-time diffusion equation mod- els.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Reverse-time diffusion equation mod- els

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.015948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a47f9ab6-2a5e-4bdb-b659-f7f0be16135e · outbound

This paper cites wav2vec 2.0: A framework for self- supervised learning of speech representations.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer wav2vec 2.0: A framework for self- supervised learning of speech representations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.020950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb4694c3-b57d-45a2-8cbc-01694d3b2f55 · outbound

This paper cites All are worth words: A vit backbone for diffusion models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer All are worth words: A vit backbone for diffusion models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.025706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cff7665-d376-49fb-8422-aba97a363f2b · outbound

This paper cites BEiT: BERT Pre-Training of Image Transformers.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer BEiT: BERT Pre-Training of Image Transformers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.030662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0446b61-46d0-40fa-9ebb-20411102d66d · outbound

This paper cites Lumiere: A Space-Time Diffusion Model for Video Generation.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Lumiere: A Space-Time Diffusion Model for Video Generation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.035747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d239d2be-337d-4ce8-a5a8-d0b2430809bc · outbound

This paper cites Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.040831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c011249-fe69-459b-b4eb-e5ff735012db · outbound

This paper cites Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.045915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1d97961-7873-40de-85d4-674af203b838 · outbound

This paper cites Emerg- ing properties in self-supervised vision transformers.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Emerg- ing properties in self-supervised vision transformers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.051769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac6f7a15-4fcb-4bae-86a6-9641906ce980 · outbound

This paper cites an unresolved cited work.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Unresolved cited work

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.056446Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6df8b20-ece5-45ee-a4cc-a076de1ae434 · outbound

This paper cites Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.061018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2096eee0-1f88-45ef-b2c8-ede51a9c376a · outbound

This paper cites An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.065992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f70478c1-0885-4542-a63c-8248a0b35cad · outbound

This paper cites Variational Lossy Autoencoder.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Variational Lossy Autoencoder

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.070829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ca871d-15cf-45a1-bae3-ea3b314ddf6c · outbound

This paper cites Deconstructing Denoising Diffusion Models for Self-Supervised Learning.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Deconstructing Denoising Diffusion Models for Self-Supervised Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.075744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 743c731c-893c-4d8e-9825-f682a0a3ddb8 · outbound

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

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Imagenet: A large-scale hierarchical image database

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.080828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1143e83c-f0eb-464d-b2c7-ae17989a1ed8 · outbound

This paper cites Diffusion models beat gans on image synthesis, 2021.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Diffusion models beat gans on image synthesis, 2021

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.085387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf17e51-38f2-4f8d-bb23-d288308e3388 · outbound

This paper cites Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.090116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b88a35db-2660-4cc3-b414-b32fa1720ea5 · outbound

This paper cites Cogview: Mastering text-to-image generation via transformers.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Cogview: Mastering text-to-image generation via transformers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.094730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92711e0a-465b-4951-a83f-8c60e2581a62 · outbound

This paper cites Peco: Perceptual codebook for bert pre-training of vision transformers.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Peco: Perceptual codebook for bert pre-training of vision transformers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.098832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b22cb5f-27c3-492a-b58a-29d27824802f · outbound

This paper cites Generating images with perceptual similarity metrics based on deep networks.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Generating images with perceptual similarity metrics based on deep networks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.103290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b382bc9e-5250-4a3f-b0bf-9cbff81601ac · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale, 2021.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer An image is worth 16x16 words: Transformers for image recognition at scale, 2021

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.107469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de3dd328-38f8-4409-b8c5-f3f22d24cf55 · outbound

This paper cites A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.111511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4e92bd4-5d54-4b8a-b605-8333561202de · outbound

This paper cites Taming transformers for high-resolution image synthesis.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Taming transformers for high-resolution image synthesis

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.115460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54ed0f68-2ac8-4c76-8713-e96c0ee2560c · outbound

This paper cites Fast Timing-Conditioned Latent Audio Diffusion.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Fast Timing-Conditioned Latent Audio Diffusion

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.119379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec433e16-34cc-484b-90c8-52b54acf0be1 · outbound

This paper cites Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.123915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f1834e9-8542-4e38-a29d-e6bebdb4e362 · outbound

This paper cites Eva-02: A visual representation for neon genesis.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Eva-02: A visual representation for neon genesis

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.129163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9385977d-54a2-490e-88c2-97434ceac5b2 · outbound

This paper cites Restructuring Vector Quantization with the Rotation Trick.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Restructuring Vector Quantization with the Rotation Trick

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.133672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46df1f4d-cd50-47f2-b942-60f948d72f81 · outbound

This paper cites Make-a-scene: Scene- based text-to-image generation with human priors.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Make-a-scene: Scene- based text-to-image generation with human priors

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.138618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3417631d-9c10-4451-96b7-39d53518d731 · outbound

This paper cites MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.143121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 849e4bcd-c993-492a-a5f9-d12e86a61a47 · outbound

This paper cites Planting a seed of vision in large language model,.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Planting a seed of vision in large language model,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.148816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93142e31-20c6-43bc-96bf-f63d2547d81f · outbound

This paper cites Making LLaMA SEE and Draw with SEED Tokenizer.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Making LLaMA SEE and Draw with SEED Tokenizer

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.153399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec8f4e62-bd3b-44be-8aa1-8030aa58c767 · outbound

This paper cites DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.158166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc01d630-7fee-40f5-afc0-eca3d3d9dca3 · outbound

This paper cites Generative adversarial networks.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Generative adversarial networks

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.163379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3723f1-e282-4bf3-a68c-f17922b70194 · outbound

This paper cites Rethinking the objectives of vector-quantized tokenizers for image synthesis, 2023.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Rethinking the objectives of vector-quantized tokenizers for image synthesis, 2023

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.167952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3a41adb-549a-4f40-a258-121a18145560 · outbound

This paper cites Masked autoencoders are scal- able vision learners.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Masked autoencoders are scal- able vision learners

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.172497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb2da402-168d-41b0-a4db-1cea0a84597f · outbound

This paper cites Rotary position embedding for vision transformer.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Rotary position embedding for vision transformer

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.176985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c1aa017-323a-43c0-98be-f8fd56d0344c · outbound

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

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Gans trained by a two time-scale update rule converge to a local nash equilibrium

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.181358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82f625b5-b7b2-4b8a-bb97-eb70ddaab0e9 · outbound

This paper cites beta-vae: Learning basic visual concepts with a constrained variational framework.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer beta-vae: Learning basic visual concepts with a constrained variational framework

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.185786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a34eb81-8c31-42f5-9946-c8f87659117b · outbound

This paper cites Reducing the dimensionality of data with neural networks.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Reducing the dimensionality of data with neural networks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.190239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1f2f2ad-369f-4d26-a36d-f33821bf8966 · outbound

This paper cites Classifier-Free Diffusion Guidance.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Classifier-Free Diffusion Guidance

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.194625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc383858-ad5f-462c-8882-33612857c5a6 · outbound

This paper cites Denoising diffu- sion probabilistic models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Denoising diffu- sion probabilistic models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.200079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd048ef-a21c-4a74-82cf-2fc837062b69 · outbound

This paper cites Video dif- fusion models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Video dif- fusion models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.204507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee5901eb-78f3-4d9c-916c-2b51e1aeb6b3 · outbound

This paper cites Straightening out the straight-through estimator: Over- coming optimization challenges in vector quantized net- works.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Straightening out the straight-through estimator: Over- coming optimization challenges in vector quantized net- works

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.209089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfa48579-4528-464c-a78b-19aeee4d71cc · outbound

This paper cites an unresolved cited work.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Unresolved cited work

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.213515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b09be01b-fabb-4fe0-8c20-c94fb5ddfc55 · outbound

This paper cites Product quantization for nearest neighbor search.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Product quantization for nearest neighbor search

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.218002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 845aad99-60f4-4256-bd76-4797aa10a3ec · outbound

This paper cites Percep- tual losses for real-time style transfer and super-resolution.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Percep- tual losses for real-time style transfer and super-resolution

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.222387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d97107ca-26cf-45b4-8372-3ed4378eb4fd · outbound

This paper cites Composing graphical models with neural networks for structured representations and fast inference.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Composing graphical models with neural networks for structured representations and fast inference

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.226655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2314b4e-09e8-4e8b-a0ce-a9819092303a · outbound

This paper cites A style-based generator architecture for generative adversarial networks.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer A style-based generator architecture for generative adversarial networks

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.231037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bb7f5d9-0e47-4e80-a3e3-c0a1f4c37cc4 · outbound

This paper cites Analyzing and improv- ing the image quality of stylegan.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Analyzing and improv- ing the image quality of stylegan

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.235169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 507122e3-93e4-4b41-9699-0aa19b6c57d2 · outbound

This paper cites Understanding diffusion objectives as the elbo with simple data augmentation.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Understanding diffusion objectives as the elbo with simple data augmentation

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.239231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c85a29ca-c109-4c16-b6b1-ec339b0a5055 · outbound

This paper cites Auto-Encoding Variational Bayes.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Auto-Encoding Variational Bayes

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.243492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 141ab1c4-e1e4-4c9e-afee-a89683e0367c · outbound

This paper cites Improved precision and recall metric for assessing generative models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Improved precision and recall metric for assessing generative models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.247514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e731ce-1456-454f-8a95-2f8a98d62b88 · outbound

This paper cites Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.251602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b309de-3202-4693-897e-11534830e673 · outbound

This paper cites Autoencoding beyond pixels using a learned similarity metric.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Autoencoding beyond pixels using a learned similarity metric

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.256119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67582688-9b0c-44a4-96ea-43f913b4205b · outbound

This paper cites Autoregressive image generation using residual quantization.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Autoregressive image generation using residual quantization

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.260104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5aa7035-2763-4a43-a457-12e32037db62 · outbound

This paper cites Autoregressive image generation using residual quantization, 2022.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Autoregressive image generation using residual quantization, 2022

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.264143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57a51a0b-a6b9-4a9d-af6a-b9a6ccb24796 · outbound

This paper cites Scalable autoregressive image generation with mamba.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Scalable autoregressive image generation with mamba

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.268840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1169c724-5ac9-4147-9ce9-33e65e74ed67 · outbound

This paper cites Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Blip- 2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.273161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c1cd7f6-e3f3-4deb-b36f-e5951e305a30 · outbound

This paper cites Mage: Masked generative encoder to unify representation learning and im- age synthesis, 2023.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Mage: Masked generative encoder to unify representation learning and im- age synthesis, 2023

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.277694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4f4048-1066-4e46-8d0e-4c2e74dc33c2 · outbound

This paper cites Autoregressive image generation without vec- tor quantization, 2024.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Autoregressive image generation without vec- tor quantization, 2024

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.282109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e7046c-d4fb-4a3a-b6fb-0d8f77c9a4cd · outbound

This paper cites TokenPacker: Efficient Visual Projector for Multimodal LLM.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer TokenPacker: Efficient Visual Projector for Multimodal LLM

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.286584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 499d77d8-1899-444e-8516-fa819ab0cbaa · outbound

This paper cites ImageFolder: Autoregressive Image Generation with Folded Tokens.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer ImageFolder: Autoregressive Image Generation with Folded Tokens

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.291256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00011b92-6bd8-485b-96d9-c215a7ae257d · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.295905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44889bf7-01ad-45ee-b1e8-db53fd2be9c9 · outbound

This paper cites SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.300508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c931c434-6338-4352-860f-0570feba0c8e · outbound

This paper cites Flow Matching for Generative Modeling.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Flow Matching for Generative Modeling

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.306174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9150376d-81ad-4bcb-b174-0056d66e846b · outbound

This paper cites Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.310907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726a3626-e1c0-4473-ab06-e2d8146533af · outbound

This paper cites Least squares quantization in pcm.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Least squares quantization in pcm

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.315525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57702906-ab4c-431e-8e14-17d2c4ae0551 · outbound

This paper cites Decoupled Weight Decay Regularization.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Decoupled Weight Decay Regularization

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.319871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be5aefdb-81c7-48f6-b79b-131cbb6392c3 · outbound

This paper cites Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.324722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f856e7e-0bec-498b-b64d-3a77b3e1661e · outbound

This paper cites Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.329381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1865715b-0ec9-436d-8a7a-29ba1fe52158 · outbound

This paper cites Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.333762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed533d42-d389-4536-944a-4e5090081365 · outbound

This paper cites SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.338668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f497f54d-87d1-45a0-995b-47a998da0486 · outbound

This paper cites Finite scalar quantization: Vq-vae made simple, 2023.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Finite scalar quantization: Vq-vae made simple, 2023

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.453492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d681227-7bc2-4410-9fb1-bc818af2ff6e · outbound

This paper cites Midjourney.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Midjourney

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.458279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea32e042-1385-44a6-a156-62569add43f0 · outbound

This paper cites Improved denoising diffusion probabilistic models, 2021.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Improved denoising diffusion probabilistic models, 2021

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.462613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ecda30f-f230-4b73-beb4-abf7a71399ca · outbound

This paper cites GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.467389Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea5e38d4-aba4-47b9-a558-11df9c14e31c · outbound

This paper cites Certain topics in telegraph transmission theory.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Certain topics in telegraph transmission theory

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.472143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb9fa985-7de4-4a16-a860-bfbd59e658a5 · outbound

This paper cites Video generation models as world simulators.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Video generation models as world simulators

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.476838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eb381dc-708f-46c7-a2af-28e66d491ef1 · outbound

This paper cites an unresolved cited work.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-11T15:33:15.134776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5c2bc65b-628b-4be3-9b02-f78e63f0a83e · outbound

This paper cites Scalable diffusion models with transformers, 2023.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Scalable diffusion models with transformers, 2023

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.119464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 406bf857-fd21-48c1-8a34-16cfdd0b2451 · outbound

This paper cites Grad-tts: A diffusion probabilistic model for text-to-speech.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Grad-tts: A diffusion probabilistic model for text-to-speech

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.102846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9ca122af-6f1e-4e04-ba1a-e6ed126a86fc · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Learn- ing transferable visual models from natural language super- vision

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.086872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 14dcbe19-d435-4635-8304-b855b87e3322 · outbound

This paper cites Zero-shot text-to-image generation.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Zero-shot text-to-image generation

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.070087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 209686a3-ba66-49aa-8795-6f4dfe2535e3 · outbound

This paper cites Gener- ating diverse high-fidelity images with vq-vae-2.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Gener- ating diverse high-fidelity images with vq-vae-2

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.055563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1b382d1e-4e6f-49c2-8076-cd5685bc64eb · outbound

This paper cites Gen- erating diverse high-fidelity images with vq-vae-2, 2019.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Gen- erating diverse high-fidelity images with vq-vae-2, 2019

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.041377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ad4194d3-5e82-4d50-b94e-c23654fba4d7 · outbound

This paper cites Gaussian mixture models.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Gaussian mixture models

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.026710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cdf455bc-8065-4e0f-84bf-a3e438ee94a1 · outbound

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

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer High-resolution image synthesis with latent diffusion models

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.516862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb16e1f-b221-43e2-8d38-2e5acfa65ad5 · outbound

This paper cites High-resolution image synthesis with latent diffusion models, 2022.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer High-resolution image synthesis with latent diffusion models, 2022

Reference 88

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:15.001592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8fd12bbb-487a-49cb-a534-dd23aa97b56e · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Photorealistic text-to-image diffusion models with deep language understanding

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.986771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 71269577-80cd-4ff2-8e74-cde7b10ceab7 · outbound

This paper cites Improved techniques for training gans.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Improved techniques for training gans

Reference 90

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.970885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c0b1c941-672d-44d1-8dff-4a78af647f98 · outbound

This paper cites Communication in the presence of noise.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Communication in the presence of noise

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.954290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2dd07c0d-d410-4cc2-b45c-97cb116b6729 · outbound

This paper cites Deep unsupervised learning using nonequilibrium thermodynamics.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Deep unsupervised learning using nonequilibrium thermodynamics

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.939417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation cc611138-2587-411f-90ae-1614607b7534 · outbound

This paper cites Weiss, Niru Mah- eswaranathan, and Surya Ganguli.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Weiss, Niru Mah- eswaranathan, and Surya Ganguli

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.924652Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation acb165d3-b674-471a-90d0-a9a7c78b8304 · outbound

This paper cites Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Less is More: A Simple yet Effective Token Reduction Method for Efficient Multi-modal LLMs

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.548179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f35823c9-883e-47cd-88b6-c1529839663d · outbound

This paper cites Denois- ing diffusion implicit models, 2022.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Denois- ing diffusion implicit models, 2022

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.909303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f8e0c1bc-1ad4-4908-9c88-155f982f70f9 · outbound

This paper cites Sd vae ft ema, 2023.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Sd vae ft ema, 2023

Reference 96

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.893960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 758e142c-3232-4297-ba59-fd7f983a3cc6 · outbound

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

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Roformer: Enhanced transformer with rotary position embedding

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.562297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 437128a1-8d6e-43fd-9d4c-098366ed7514 · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-11T15:33:13.566667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea6607b3-075d-441d-b325-9991145e8573 · outbound

This paper cites Visual autoregressive modeling: Scalable image generation via next-scale prediction, 2024.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Visual autoregressive modeling: Scalable image generation via next-scale prediction, 2024

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.869486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation dfefb3a5-a806-49a5-82cd-c9263dd43973 · outbound

This paper cites Givt: Generative infinite-vocabulary transformers.

SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer Givt: Generative infinite-vocabulary transformers

Reference 100

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T15:33:14.854543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation be54b425-21eb-4843-b885-592c25502b3c · inbound

Masked Autoencoders Are Effective Tokenizers for Diffusion Models cites this paper.

Masked Autoencoders Are Effective Tokenizers for Diffusion Models SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T04:47:30.290200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3913c8b6-1a18-49b6-8969-9b05bb6e4b43 · inbound

Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation cites this paper.

Instella-T2I: Pushing the Limits of 1D Discrete Latent Space Image Generation SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-06T22:43:02.699039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00cb8b07-238c-497a-97e4-1ca54dcd4c11 · inbound

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis cites this paper.

Rethinking Discrete Tokens: Treating Them as Conditions for Continuous Autoregressive Image Synthesis SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T20:49:40.554531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62f40565-28e3-4d95-bbfe-fa5f79d53533 · inbound

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer cites this paper.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.624757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7508108d-4de6-4935-9311-117ed61ec7a3 · inbound

Structure over Pixels: Learning Variable-Length Visual Programs cites this paper.

Structure over Pixels: Learning Variable-Length Visual Programs SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-06-29T18:13:49.030820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.