Paper Citation Record · LEDGER

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

As of 5 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 2 inbound Pith citation observations for arXiv:2605.09430.

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

pith.paper-citation-record.v1
2605.09430 v2

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T05:54:24.248910Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T15:30:23.485228Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact23
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 58df8b08-5569-4e19-b870-2de04b899fb2 · outbound

This paper cites Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T10:59:41.530185Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 01e36f9c-31a2-4afd-aa22-b482b9038559 · outbound

This paper cites Qwen Technical Report.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Qwen Technical Report

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.723037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0c7faca6-810c-47fd-a7bb-81d967daa41a · outbound

This paper cites ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.630811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4895c73c-42b5-4497-af09-ef72cc4f9346 · outbound

This paper cites Opengpt-4o-image: A compre- hensive dataset for advanced image generation and editing.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Opengpt-4o-image: A compre- hensive dataset for advanced image generation and editing

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.688588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 24c30f45-c64c-4dc8-86c7-adf4a7e67b5a · outbound

This paper cites Uniform discrete diffusion with metric path for video generation.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Uniform discrete diffusion with metric path for video generation

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.652337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0a7e3915-f12f-4216-9621-199304ffeb80 · outbound

This paper cites Flex Attention: A Programming Model for Generating Optimized Attention Kernels.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Flex Attention: A Programming Model for Generating Optimized Attention Kernels

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-17T21:27:16.810492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6fbafad0-7943-4e3c-a57c-805ae01e18ad · outbound

This paper cites X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.706601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 77989242-f5db-4178-b5aa-5fbe956d59ce · outbound

This paper cites Classifier-Free Diffusion Guidance.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Classifier-Free Diffusion Guidance

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.719981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3bc7113d-5ac9-496b-bf3f-364882fc2d2d · outbound

This paper cites LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.677292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bcaf70f0-2236-4510-8b1c-90e55658aaf2 · outbound

This paper cites Autoregressive image generation with randomized parallel decoding.arXiv preprint arXiv:2503.10568.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Autoregressive image generation with randomized parallel decoding.arXiv preprint arXiv:2503.10568

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.695333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 23a5030c-42ef-4c75-8a0a-fd9a0293c645 · outbound

This paper cites Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.659868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fe295582-0207-4928-8f43-03047967a51c · outbound

This paper cites Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.663453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 216d043b-7da5-4d20-9463-6e1dae92f61c · outbound

This paper cites Layer by Layer: Uncovering Hidden Representations in Language Models.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Layer by Layer: Uncovering Hidden Representations in Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-15T16:30:37.615120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8969a9c6-bf9a-4a1f-8966-acfd79a99ebb · outbound

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

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.713752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fa2313cd-6497-4c9e-b290-a757d6e2f27f · outbound

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

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation HART: Efficient Visual Generation with Hybrid Autoregressive Transformer

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.674076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4e9329a1-62bc-44bf-89c2-14961553bc73 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Gemini: A Family of Highly Capable Multimodal Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.698720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 36307d51-2891-4ee9-a280-0fe07ea3e4e9 · outbound

This paper cites NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.624188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f7c93f33-e7ce-4cb3-9aa4-65e1fc0b4d70 · outbound

This paper cites Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.710551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0c4869ac-8db9-4b36-9e3d-97bcb9f6fc7c · outbound

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

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation LLaMA: Open and Efficient Foundation Language Models

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.716776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7e4053d4-2612-4068-b274-78a090f03660 · outbound

This paper cites SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.667247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 286ac545-9494-45ae-8642-fff3ef966c8a · outbound

This paper cites Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.702712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6f56ecbc-cf62-415c-9272-9e26aecc2636 · outbound

This paper cites Qwen3 Technical Report.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Qwen3 Technical Report

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.684977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9ff55bda-251c-4cfb-8aba-df5b878a3218 · outbound

This paper cites Scaling Autoregressive Models for Content-Rich Text-to-Image Generation.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:02:23.670463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 93467342-a379-476c-b658-492ecec8926c · outbound

This paper cites Locality-aware parallel decoding for efficient autoregressive image generation.arXiv preprint arXiv:2507.01957.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Locality-aware parallel decoding for efficient autoregressive image generation.arXiv preprint arXiv:2507.01957

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.691848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation d1ca4ecb-7b30-4800-9a5d-c9bf0f4190f4 · inbound

Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation cites this paper.

Spectral Origins of the Self-Correction Blind Spot in Autoregressive Generation FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-14T15:30:23.485228Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0414151a-9e34-412c-a634-0586e1233a1f · inbound

Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model cites this paper.

Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-14T04:10:14.360463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.