Paper Citation Record · LEDGER

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

As of 19 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2412.10208.

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

pith.paper-citation-record.v1
2412.10208 v3

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T16:22:19.353801Z

measured 19 of 19 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-15T03:42:44.523919Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-15T03:42:44.862362Z

Reference resolution

18 of 18 outbound references displayed

verified exact0
verified fuzzy6
unresolved11
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 70f86796-6fe4-4c9a-90c6-80769eeaa1c9 · outbound

This paper cites GPT-4 Technical Report.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.282603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a09971e-204a-4e1a-9ab8-911b34659fe2 · outbound

This paper cites To increase the depth of RVQ, we warm-start from the 4-depth RQ-V AE checkpoint (Lee et al., 2022), excluding the attention layers, and reduce the latent dimension from 256 to.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens To increase the depth of RVQ, we warm-start from the 4-depth RQ-V AE checkpoint (Lee et al., 2022), excluding the attention layers, and reduce the latent dimension from 256 to

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:22:19.614219Z

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 2ad91bf4-1493-4cc2-800d-4958da7a87d2 · outbound

This paper cites Scaling Laws for Neural Language Models.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Scaling Laws for Neural Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.295909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf5e36cd-eb8d-405f-89ff-a26a48a63e6c · outbound

This paper cites doi: 10.1162/tacl a 00618.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens doi: 10.1162/tacl a 00618

Reference 5

Resolution: malformed identifier; no resolver link, observed 2026-08-11T16:22:19.300960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92f5168a-840d-48fc-87a7-7c491045ad0e · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.305041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c84f958e-01fa-40a2-8c16-527801f835d2 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens LLaMA: Open and Efficient Foundation Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.319925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a01a7b-d78e-4416-8759-23df7f4d945b · outbound

This paper cites Training details A.1.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Training details A.1

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:22:19.626621Z

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 5520c7f9-6cff-40dc-b47a-e5a78d0b45e0 · outbound

This paper cites an unresolved cited work.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-11T16:22:19.552738Z

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 cfc73804-e658-45e8-8b79-5e539af37a44 · outbound

This paper cites These log probabilities are derived from the squared distance between token embeddings and the sampled latent zi at each position i.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens These log probabilities are derived from the squared distance between token embeddings and the sampled latent zi at each position i

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:22:19.539088Z

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 e76da39a-a5e0-4ee6-94f0-e2e0b17ac84a · outbound

This paper cites As shown in Table 8, these models achieve FID scores of 1.78 and 1.62, respectively.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens As shown in Table 8, these models achieve FID scores of 1.78 and 1.62, respectively

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:22:19.521598Z

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 efc7fad1-fb0a-441f-9029-7edf55ff2d0a · outbound

This paper cites an unresolved cited work.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-11T16:22:19.569031Z

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 b6ed3826-78eb-4d76-81a2-7a413f604922 · outbound

This paper cites For the RVQ quantizer, we employ the probabilistic RVQ method from Kim et al.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens For the RVQ quantizer, we employ the probabilistic RVQ method from Kim et al

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:22:19.600226Z

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 de7a578e-1c2b-476d-bf84-a288ce7bb4ae · outbound

This paper cites an unresolved cited work.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Unresolved cited work

Reference 1024

Resolution: unresolved; raw_fallback, observed 2026-08-11T16:22:19.584959Z

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 25f967cd-5129-48b4-a473-a4ccb5f0444c · outbound

This paper cites Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.324852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2caaccb8-4118-4a35-bd30-0a114dcc0fe9 · outbound

This paper cites Lu- miere: A space-time diffusion model for video generation.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens Lu- miere: A space-time diffusion model for video generation

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T16:22:19.638005Z

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 ce179dba-bdd7-4a19-9a1b-0344bc44bc63 · outbound

This paper cites AudioPaLM: A Large Language Model That Can Speak and Listen.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens AudioPaLM: A Large Language Model That Can Speak and Listen

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.309832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 880d71cc-4d7b-434e-b7a4-e0656cb484ad · outbound

This paper cites SoundStorm: Efficient Parallel Audio Generation.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens SoundStorm: Efficient Parallel Audio Generation

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.291624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5210d4f4-2327-4cf5-bff4-e21166770e0c · outbound

This paper cites HART: Efficient Visual Generation with Hybrid Autoregressive Transformer.

Efficient Generative Modeling with Residual Vector Quantization-Based Tokens HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T16:22:19.315127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 52bf4706-4245-46fb-8b51-c552affd56be · inbound

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models cites this paper.

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models Efficient Generative Modeling with Residual Vector Quantization-Based Tokens

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-05-15T03:42:44.866209Z

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.