Paper Citation Record · LEDGER

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders

As of 6 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 0 inbound Pith citation observations for arXiv:2604.07340.

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

pith.paper-citation-record.v1
2604.07340 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T17:44:14.636654Z

measured 16 of 16 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

16 of 16 outbound references displayed

verified exact14
verified fuzzy1
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c11e6fc8-b615-473c-9d05-939f85690523 · outbound

This paper cites A Note on the Inception Score.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders A Note on the Inception Score

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.120240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 22655daf-2916-408c-9536-4c09f39bfe88 · outbound

This paper cites Hieratok: Multi-scale visual tokenizer improves image reconstruction and generation.arXiv preprint arXiv:2509.23736, 2025a.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Hieratok: Multi-scale visual tokenizer improves image reconstruction and generation.arXiv preprint arXiv:2509.23736, 2025a

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.179300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ae4659c6-ec83-4e1e-9602-6835a6c2a7c9 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:57.132264Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2aa396cf-8da4-4bbc-b54a-8e497bd7139a · outbound

This paper cites Learnings from Scaling Visual Tokenizers for Reconstruction and Generation.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Learnings from Scaling Visual Tokenizers for Reconstruction and Generation

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.138473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 41d4bcd3-d7bc-48aa-8e5a-8dfea1887219 · outbound

This paper cites Dc-gen: Post-training diffusion acceleration with deeply compressed latent space.arXiv preprint arXiv:2509.25180.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Dc-gen: Post-training diffusion acceleration with deeply compressed latent space.arXiv preprint arXiv:2509.25180

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.170481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6ce7136a-c97e-4d75-b520-6cae1b3940bc · outbound

This paper cites Ming-univision: Joint image understanding and generation with a unified continuous tokenizer.arXiv preprint arXiv:2510.06590, 2025a.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Ming-univision: Joint image understanding and generation with a unified continuous tokenizer.arXiv preprint arXiv:2510.06590, 2025a

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.164310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 78716e60-5ce4-4f67-8dc0-e84e6d0265aa · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders DINOv2: Learning Robust Visual Features without Supervision

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-11T06:15:57.143915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3c4135f8-afe1-49e7-8d48-5bf83f7dfede · outbound

This paper cites Latent diffusion model without variational autoencoder.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Latent diffusion model without variational autoencoder

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.128784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f28efa9a-0e5e-46c3-815d-805942692de6 · outbound

This paper cites What matters for representation alignment: Global information or spatial structure?.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders What matters for representation alignment: Global information or spatial structure?

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.193189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ffd2316e-6aa9-41d5-8999-765548fa6fdf · outbound

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

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:09:17.130563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b492d801-0693-4f2a-b9d5-519d6eedd784 · outbound

This paper cites SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T06:15:57.159132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c0bd6338-1510-41ad-a48c-c63e857b3ca6 · outbound

This paper cites GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.185595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 617441f0-beb9-40a9-97b9-8c557c19722a · outbound

This paper cites Towards scalable pre-training of visual tokenizers for generation.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Towards scalable pre-training of visual tokenizers for generation

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:15:57.200617Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5d2a3d8c-2b9e-455f-9d27-3916bb9367e4 · outbound

This paper cites Diffusion Transformers with Representation Autoencoders.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders Diffusion Transformers with Representation Autoencoders

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:34:18.071377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f13400c4-50a1-4d64-9e7a-25c1da3a35c8 · outbound

This paper cites iBOT: Image BERT Pre-Training with Online Tokenizer.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders iBOT: Image BERT Pre-Training with Online Tokenizer

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-14T02:10:27.691909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e1e4c66f-a7cb-4608-b268-ae6d61f5628d · outbound

This paper cites To ensure stable joint optimization with the reconstruction objective, we reduce the learning rate.

TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders To ensure stable joint optimization with the reconstruction objective, we reduce the learning rate

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T09:14:22.544047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

No inbound Pith citation observations are available.