Paper Citation Record · LEDGER

1.58-bit FLUX

As of 18 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 10 inbound Pith citation observations for arXiv:2412.18653.

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

pith.paper-citation-record.v1
2412.18653 v1

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:39:36.782352Z

measured 73 of 73 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 10 of 10 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:42:59.643515Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T08:15:31.930344Z

Reference resolution

63 of 63 outbound references displayed

verified exact0
verified fuzzy25
unresolved38
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8592a99d-187b-4b12-969d-76cd8fd34043 · outbound

This paper cites https://news.adobe.com/news/news- details/2024/adobe-introduces-firefly-image-3-foundation- model-to-take-creative-exploration-and-ideation-to-new- heights.

1.58-bit FLUX https://news.adobe.com/news/news- details/2024/adobe-introduces-firefly-image-3-foundation- model-to-take-creative-exploration-and-ideation-to-new- heights

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.982191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f5010cf1-8ede-43b9-99aa-91f73c401e6f · outbound

This paper cites https://www.recraft.ai/blog/recraft-introduces- a-revolutionary-ai-model-that-thinks-in-design-language.

1.58-bit FLUX https://www.recraft.ai/blog/recraft-introduces- a-revolutionary-ai-model-that-thinks-in-design-language

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.966510Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 647b98c0-f330-4163-a44d-f6ae38e97ade · outbound

This paper cites Improving image generation with better captions.

1.58-bit FLUX Improving image generation with better captions

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.414506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 595c043f-a804-4c76-ac1e-bc4682571dc0 · outbound

This paper cites Zeroq: A novel zero shot quantization framework.

1.58-bit FLUX Zeroq: A novel zero shot quantization framework

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.940425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 07f37586-b5d1-43c7-8ca3-228c2fade14c · outbound

This paper cites Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models.

1.58-bit FLUX Low-Bitwidth Floating Point Quantization for Efficient High-Quality Diffusion Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.434306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33c414ae-e1b8-48f7-9506-2dddd3aa777f · outbound

This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.

1.58-bit FLUX PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.441245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b8d72a-bb88-4478-81ee-a126a62648a7 · outbound

This paper cites Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers.

1.58-bit FLUX Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.446559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf87b3c-a737-45a0-92df-431ea18ca8ca · outbound

This paper cites PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization.

1.58-bit FLUX PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.451619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187ab6a2-6840-48b0-9c1c-3bfbca806fa7 · outbound

This paper cites EfficientQAT: Efficient Quantization-Aware Training for Large Language Models.

1.58-bit FLUX EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.456617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bece48e-ed86-484d-90c5-74836d0f8d60 · outbound

This paper cites Low-bit quantization of neural networks for efficient infer- ence.

1.58-bit FLUX Low-bit quantization of neural networks for efficient infer- ence

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.924037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation cda3e752-a9c6-4a44-a951-e049186429a4 · outbound

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

1.58-bit FLUX VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.466927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46c534e0-3e77-4274-8e57-8bbb3025aa23 · outbound

This paper cites an unresolved cited work.

1.58-bit FLUX Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.472201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1652314b-7db8-41ad-b705-002595b4989c · outbound

This paper cites Hawq: Hessian aware quantization of neural networks with mixed-precision.

1.58-bit FLUX Hawq: Hessian aware quantization of neural networks with mixed-precision

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.896257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 89f211d9-5c2c-4527-9772-15e90d0fed29 · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

1.58-bit FLUX Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.486213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 610122ef-155f-4923-9af8-8ad862fd1f8c · outbound

This paper cites Learned Step Size Quantization.

1.58-bit FLUX Learned Step Size Quantization

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.491037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 871e3147-c6e6-4780-92f0-91a9a0f8867c · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

1.58-bit FLUX GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.496093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51ea60b3-5ee2-4096-ba63-acde92bb95d2 · outbound

This paper cites Geneval: An object-focused framework for evaluating text- to-image alignment.

1.58-bit FLUX Geneval: An object-focused framework for evaluating text- to-image alignment

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.870305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 846e1dfc-7814-4474-aa83-7aeaf50af73e · outbound

This paper cites Differ- entiable soft quantization: Bridging full-precision and low- bit neural networks.

1.58-bit FLUX Differ- entiable soft quantization: Bridging full-precision and low- bit neural networks

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.854530Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 3fc80dba-69cf-47ec-905e-99de56623804 · outbound

This paper cites Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding.

1.58-bit FLUX Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.510956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dc638d4-cb4a-4a82-8133-c64320a3bd2e · outbound

This paper cites EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models.

1.58-bit FLUX EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.520801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96ad31bc-790b-4685-9b7b-45bf5f44d917 · outbound

This paper cites Bivit: Extremely com- pressed binary vision transformers.

1.58-bit FLUX Bivit: Extremely com- pressed binary vision transformers

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.838907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5ae1771d-6c94-46ad-a192-cd74bc67e6cf · outbound

This paper cites Ptqd: Accurate post-training quantization for diffusion models.

1.58-bit FLUX Ptqd: Accurate post-training quantization for diffusion models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.822262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d62d83da-c5c4-4a0d-9fcf-368fee71b7a5 · outbound

This paper cites T2i-compbench: A comprehensive bench- mark for open-world compositional text-to-image genera- tion.

1.58-bit FLUX T2i-compbench: A comprehensive bench- mark for open-world compositional text-to-image genera- tion

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.804801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 55dfd226-8692-4bf8-80f5-0bf4274620eb · outbound

This paper cites Tfmq-dm: Temporal feature maintenance quantization for diffusion models.

1.58-bit FLUX Tfmq-dm: Temporal feature maintenance quantization for diffusion models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.787764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7148d9d9-2ce0-455f-b472-6e9b3db66c3a · outbound

This paper cites Binarized neural networks.

1.58-bit FLUX Binarized neural networks

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.772843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation f1de931d-f494-4fda-a68b-6367846e4baf · outbound

This paper cites https://updates.midjourney.com/version-6-1/.

1.58-bit FLUX https://updates.midjourney.com/version-6-1/

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.756025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1302cbce-b2b2-411d-95e1-9b8dd77192b6 · outbound

This paper cites Quantization and training of neural networks for efficient integer-arithmetic-only inference.

1.58-bit FLUX Quantization and training of neural networks for efficient integer-arithmetic-only inference

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.740684Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2006d8ae-b07d-40b6-9803-43fa6828a3b0 · outbound

This paper cites SqueezeLLM: Dense-and-Sparse Quantization.

1.58-bit FLUX SqueezeLLM: Dense-and-Sparse Quantization

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.579296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5832f977-ce81-4a2f-acc9-7bf8e1128501 · outbound

This paper cites https://blackforestlabs.ai/announcements/.

1.58-bit FLUX https://blackforestlabs.ai/announcements/

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.584149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f54723fa-c0ae-4e7d-bf01-56cfc925e9e8 · outbound

This paper cites https://github.com/black-forest-labs/flux.

1.58-bit FLUX https://github.com/black-forest-labs/flux

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.714016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e7289807-6eed-49a3-96fc-d5362b354410 · outbound

This paper cites Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation.

1.58-bit FLUX Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.600834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50dd2571-8d99-45a6-b092-12b29787dd6b · outbound

This paper cites Svdquant: Absorbing outliers by low- rank components for 4-bit diffusion models.

1.58-bit FLUX Svdquant: Absorbing outliers by low- rank components for 4-bit diffusion models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.605408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d3b41c4-7064-4bc3-9e48-4c115be7d568 · outbound

This paper cites Q-diffusion: Quantizing diffusion models.

1.58-bit FLUX Q-diffusion: Quantizing diffusion models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.698705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7194ad15-f58f-4c1a-bb59-60b06c5ca154 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

1.58-bit FLUX Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.619684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 517bd047-c647-42d4-890f-c0d819396f49 · outbound

This paper cites QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving.

1.58-bit FLUX QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.624583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b7d4d9a-5f22-48e9-8f3c-87bf35b52059 · outbound

This paper cites Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models.

1.58-bit FLUX Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.630126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43cd28b1-221b-4339-abe2-9d58b81b955e · outbound

This paper cites HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization.

1.58-bit FLUX HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.635471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 481896e5-0976-4c7a-902e-6b5fe821096c · outbound

This paper cites EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models.

1.58-bit FLUX EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.641038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9733cd-a913-48a1-8749-859d50e49216 · outbound

This paper cites LLM-QAT: Data-Free Quantization Aware Training for Large Language Models.

1.58-bit FLUX LLM-QAT: Data-Free Quantization Aware Training for Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.646370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c3c529f-d120-49a8-82bc-a475ec652e09 · outbound

This paper cites The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits.

1.58-bit FLUX The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.651851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a7055dd-5e56-40ed-9381-3b348b3f7159 · outbound

This paper cites https://updates.midjourney.com/version-6-1/.

1.58-bit FLUX https://updates.midjourney.com/version-6-1/

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.672372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 719a1dad-edf4-4251-bc40-80662d15b55c · outbound

This paper cites Up or down? adap- tive rounding for post-training quantization.

1.58-bit FLUX Up or down? adap- tive rounding for post-training quantization

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.662470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b610852-d0e2-4d8d-a3e5-e68da08b25e3 · outbound

This paper cites A White Paper on Neural Network Quantization.

1.58-bit FLUX A White Paper on Neural Network Quantization

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.668815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7e71c00-2390-4dc1-a130-1365c749113e · outbound

This paper cites Overcoming oscillations in quantization-aware training.

1.58-bit FLUX Overcoming oscillations in quantization-aware training

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.645721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 4dc51f50-ceb8-4f02-8b5b-923fb1960d27 · outbound

This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.

1.58-bit FLUX SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.679674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0156acb-c6ae-4961-beb1-a9833493b2db · outbound

This paper cites Post-training quantization on diffusion models.

1.58-bit FLUX Post-training quantization on diffusion models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.625549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d62f4fac-01c8-4248-860e-8ba3c44f1feb · outbound

This paper cites OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models.

1.58-bit FLUX OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.690379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e7a8cb3-1789-409c-8828-a815010e5aef · outbound

This paper cites BitsFusion: 1.99 bits Weight Quantization of Diffusion Model.

1.58-bit FLUX BitsFusion: 1.99 bits Weight Quantization of Diffusion Model

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.695601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3313b9-5a6c-45be-b52f-495bcdbef99e · outbound

This paper cites Post-training quan- tization with progressive calibration and activation relaxing for text-to-image diffusion models.

1.58-bit FLUX Post-training quan- tization with progressive calibration and activation relaxing for text-to-image diffusion models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.607085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d2a9a58c-ab3c-45d4-b46d-07a5dd6c100b · outbound

This paper cites Towards accurate post-training quantization for diffusion models.

1.58-bit FLUX Towards accurate post-training quantization for diffusion models

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.589407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation af450a87-0dfe-4d07-b105-fa4e0b0ea00e · outbound

This paper cites BitNet: Scaling 1-bit Transformers for Large Language Models.

1.58-bit FLUX BitNet: Scaling 1-bit Transformers for Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.710683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c6e3e3-1bf0-4176-ab3d-c2012598070f · outbound

This paper cites 1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs.

1.58-bit FLUX 1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.716036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 693dbcb1-67e1-4669-ae52-be1f5c985e68 · outbound

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

1.58-bit FLUX Haq: Hardware-aware automated quantization with mixed precision

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.565698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d99da525-ee90-48cf-aa2e-4b479e4ae495 · outbound

This paper cites Outlier suppression: Pushing the limit of low-bit transformer language models.

1.58-bit FLUX Outlier suppression: Pushing the limit of low-bit transformer language models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.542223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a779e1dc-0b10-4b7c-8f51-d58bed7047e6 · outbound

This paper cites PTQ4DiT: Post-training Quantization for Diffusion Transformers.

1.58-bit FLUX PTQ4DiT: Post-training Quantization for Diffusion Transformers

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.730855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ad609c4-0c55-4b2c-b6aa-f3d6219e7f4d · outbound

This paper cites Smoothquant: Accurate and effi- cient post-training quantization for large language models.

1.58-bit FLUX Smoothquant: Accurate and effi- cient post-training quantization for large language models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.737437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32b15292-ec6c-4508-8311-6ed4e6f7b8b2 · outbound

This paper cites Efficient Quantization Strategies for Latent Diffusion Models.

1.58-bit FLUX Efficient Quantization Strategies for Latent Diffusion Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.742987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a62a6782-c4ca-45d6-8a42-6a9a0c3603cc · outbound

This paper cites Timestep-Aware Correction for Quantized Diffusion Models.

1.58-bit FLUX Timestep-Aware Correction for Quantized Diffusion Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.748329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d2fbb5d-c982-4d4f-bf5d-a1c276cecbf2 · outbound

This paper cites Zeroquant: Ef- ficient and affordable post-training quantization for large- scale transformers.

1.58-bit FLUX Zeroquant: Ef- ficient and affordable post-training quantization for large- scale transformers

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.511222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 06afcad5-ae64-4a94-af83-a593239ac90c · outbound

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

1.58-bit FLUX Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.759706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b51d65e1-d231-4621-8537-a5ce48b93d92 · outbound

This paper cites ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation.

1.58-bit FLUX ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.765459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be355e0f-dbd9-43ba-b537-1d5b90172431 · outbound

This paper cites MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization.

1.58-bit FLUX MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T04:39:36.771152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbef7a13-aeef-4d99-9759-28e97d07ed56 · outbound

This paper cites Atom: Low-bit quantization for efficient and accurate llm serving.

1.58-bit FLUX Atom: Low-bit quantization for efficient and accurate llm serving

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:39:37.493174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Pith citing papers

Observation 01a696b0-1b70-4bf4-b15e-294cdc495165 · inbound

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens cites this paper.

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens 1.58-bit FLUX

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-10T20:42:59.643515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20031a9d-1774-46c2-9f24-63e9b5f8b4bd · inbound

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers cites this paper.

Grouping First, Attending Smartly: Training-Free Acceleration for Diffusion Transformers 1.58-bit FLUX

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.353042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19791cd6-72dd-400f-83eb-ced73d7df9ea · inbound

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models cites this paper.

Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models 1.58-bit FLUX

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:57:07.883088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4902f6f-b6df-4ac1-9973-8e6d29559582 · inbound

DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing cites this paper.

DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing 1.58-bit FLUX

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T22:42:45.239323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 341967ce-a624-4e3d-bfd7-dce5f476e6b3 · inbound

Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Data cites this paper.

Investigation of Accuracy and Bias in Face Recognition Trained with Synthetic Data 1.58-bit FLUX

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T13:19:35.659081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaa632b9-92ab-4adf-b16b-e20b8a6d1fe8 · inbound

ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset cites this paper.

ID-Card Synthetic Generation: Toward a Simulated Bona fide Dataset 1.58-bit FLUX

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T19:15:33.544769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a2b0492-a1cc-475d-aa5a-89f3791261df · inbound

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens cites this paper.

A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens 1.58-bit FLUX

Reference 79

Resolution: verified exact; arxiv_id, observed 2026-05-10T23:10:50.235148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 059fb680-461a-4d25-a427-96f117d6d4fc · inbound

Frequency-Aware Flow Matching for High-Quality Image Generation cites this paper.

Frequency-Aware Flow Matching for High-Quality Image Generation 1.58-bit FLUX

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-10T11:00:04.073008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5e5983b5-3dbc-4479-9b3e-56b8e2a0365e · inbound

When Do Diffusion Models learn to Generate Multiple Objects? cites this paper.

When Do Diffusion Models learn to Generate Multiple Objects? 1.58-bit FLUX

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:15:31.933006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 08b3fc18-4f03-41c5-94b8-04b8d30d8539 · inbound

RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models cites this paper.

RT-Lynx: Putting GEMM Sparsity in the Right Place for Diffusion Models 1.58-bit FLUX

Reference 68

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.719370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.