Pith. sign in

Paper Citation Record · LEDGER

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions

As of 18 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 1 inbound Pith citation observation for arXiv:2505.19352.

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

pith.paper-citation-record.v1
2505.19352 v1

Coverage vector

measured 55 of 55 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:20:43.649274Z

measured 56 of 56 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-20T14:31:05.979325Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-20T14:33:21.485124Z

Reference resolution

55 of 55 outbound references displayed

  • verified exact0
  • verified fuzzy30
  • unresolved25
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 28cf88ce-ec49-4ac5-81cd-91191d62cc1a · outbound

This paper cites Introducing llama 3.1: Our most capable models to date.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Introducing llama 3.1: Our most capable models to date

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:49.574163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.175952Z digest=sha256:71192672a5cf3587a135a97443eee433d2ecc44baa40eea8d7bceb3e3b199417

Observation 22529c85-5712-4c65-978b-0546b247d086 · outbound

This paper cites Introducing claude 3.5 sonnet.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Introducing claude 3.5 sonnet

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:49.397206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.250588Z digest=sha256:ac4d6a5794bff02f3836eb44ce06295847315cc8498663ab5b4c646d3b01bba2

Observation 17d40d7d-fdc2-47d3-b2e3-8b015609b439 · outbound

This paper cites Qwen2.5-vl technical report, 2025.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Qwen2.5-vl technical report, 2025

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:40.425225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:40.425225Z digest=sha256:39c818d0d5395112acbf859d5613231d3b2ba27bca9b58e6f69c2aabd698be33

Observation fc8ecb79-6982-4cf1-b829-387a91b034bd · outbound

This paper cites iedit: Localised text-guided image editing with weak supervision.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions iedit: Localised text-guided image editing with weak supervision

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:49.076668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.482522Z digest=sha256:5336023fb4afae614c178ce2f77f90eeeb3913e106abcec0d292ae90e44e2f89

Observation 176d852e-3240-4248-9da5-eb6f0354f7a8 · outbound

This paper cites Ledits++: Limitless image editing using text-to-image models.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Ledits++: Limitless image editing using text-to-image models

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:48.927791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.561668Z digest=sha256:6b9d78e8e18905c326ae946e23d4efaa9e24d756070d778d45a04ed5a8dc006f

Observation c8e860dc-055f-4345-be8c-f48540db0461 · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 6

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:48.776219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.622773Z digest=sha256:85e770f6efb7c186c089bdb39141d0fb5e1db0b0953bfac9caee5f6856f2cfc0

Observation 8f785a53-9a58-4020-b075-c938ee96aa62 · outbound

This paper cites Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Masactrl: Tuning-free mutual self-attention control for consistent image synthesis and editing

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:48.638463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.695354Z digest=sha256:ef364f92c9d46d75bac145d52296983926174ca1a369c3044b9d56ed619942e3

Observation d14abc10-f18c-457c-8521-0acca6403203 · outbound

This paper cites Maskgit: Masked generative image transformer.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Maskgit: Masked generative image transformer

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:40.740531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:40.740531Z digest=sha256:230f5e2167ceac2a405affb57c9312d74f479f0aa6d327c277266404f6aa90f3

Observation 0d843fc7-d54c-46ef-9d2d-d2de55881a5d · outbound

This paper cites Scaling instruction-finetuned language models.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Scaling instruction-finetuned language models

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:48.413005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.801241Z digest=sha256:7e3521091d1841dfdf9085f6b6bb3205ebe2febd785594957581360998407502

Observation a878a92e-81ca-4acd-9ede-fa0b339d0af6 · outbound

This paper cites Diffedit: Diffusion-based semantic image editing with mask guidance, 2022.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Diffedit: Diffusion-based semantic image editing with mask guidance, 2022

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:48.269842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.893648Z digest=sha256:3b6ac3f5e3af85329d4e7fba7aa9ac44d5dc1e2a8fc0cad34fe874a5ea17ea1c

Observation 0028c1fa-8c0a-4a30-a871-851bc21507f7 · outbound

This paper cites Vqgan-clip: Open domain image generation and editing with natural language guidance.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Vqgan-clip: Open domain image generation and editing with natural language guidance

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:48.080093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.012908Z digest=sha256:e97d9db90411fbd157fb825eb856c5532dea2702313383a1dc7f50d69e98e8df

Observation 1614e1a3-3500-4594-a6e6-ef53ad82de7f · outbound

This paper cites GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:41.061314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:41.061314Z digest=sha256:b801a4594137c5fe9480ba8ac0e490d953501faa0619ce07d141ab84b255ffae

Observation 572e79f2-08c3-4dee-a111-59fb625a27ee · outbound

This paper cites Pair diffusion: A comprehensive multimodal object-level image editor.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Pair diffusion: A comprehensive multimodal object-level image editor

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:47.943097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.145761Z digest=sha256:63046dc99446c5d4339abfb07aa66bf81dc984e21859c2c3f43a4c8c0075f2a5

Observation 45bafe9e-04a3-43ce-89bb-2837d844e9f4 · outbound

This paper cites Gemini 2.5 pro announcement (placeholder).

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Gemini 2.5 pro announcement (placeholder)

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:47.810336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.247734Z digest=sha256:05d6881b809ae38805bbaac4c6449731f36f0b6f4bede915389e51e5c3296a6c

Observation 2bbcdb6f-d100-46dd-9cb9-92258d163687 · outbound

This paper cites Focus on your instruction: Fine-grained and multi-instruction image editing by attention modulation.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Focus on your instruction: Fine-grained and multi-instruction image editing by attention modulation

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:47.670716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.313404Z digest=sha256:24cd5b0ab48a2d130423414dc52fa19b11fd7d7b4759f4443540c626931e3fa8

Observation 91ab9073-34e2-464f-a497-f66ebec8770b · outbound

This paper cites Prompt-to- prompt image editing with cross attention control, 2022.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Prompt-to- prompt image editing with cross attention control, 2022

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:47.536543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.361731Z digest=sha256:c93035a36818e9b03b7e3edf35179520a65d2ed99806d4a73b6bf15fb11d5ea1

Observation 25fbfa75-87f7-470a-a6fa-6b7a2f70f6c9 · outbound

This paper cites Paralleledits: Efficient multi- aspect text-driven image editing with attention grouping.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Paralleledits: Efficient multi- aspect text-driven image editing with attention grouping

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:47.371578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.429643Z digest=sha256:ddaec40f584c1f3d2f7435f7f1ce42a99db3d0f2180b8263214b0fc2c6e6e049

Observation dc4bb4a2-1826-4a00-89a3-1b089bb1df2b · outbound

This paper cites HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:41.500059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:41.500059Z digest=sha256:80c338fd88ab937dde66fe1d0490b1d4c2d76398a2d15ff8df1bd4a06f895e3b

Observation 4106838b-72de-45af-8501-5a04160f210e · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:41.576015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:41.576015Z digest=sha256:39e7ba0f7c20376fe5db68f027516f8422d9da40c29588f735f29b9e5517d432

Observation 5b1f28bc-1587-4014-a25c-123e9695cb20 · outbound

This paper cites Zone: Zero-shot instruction-guided local editing.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Zone: Zero-shot instruction-guided local editing

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:47.156402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.633906Z digest=sha256:2552f29a6d846523b1350922e3dc283c43337f82531fc28651e6ad914d2c09c2

Observation f06f0ee7-f69c-43d2-838c-f5b7ddd773df · outbound

This paper cites Text-driven image editing via learnable regions.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Text-driven image editing via learnable regions

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:46.976710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.680620Z digest=sha256:6bbadd94eb757852313b2921c2e5b6d535531a6443d65ee5c4f44048a4f7162e

Observation 385e18ce-6995-4b26-9a67-111d90ef9349 · outbound

This paper cites DeepSeek-V3 Technical Report.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions DeepSeek-V3 Technical Report

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:41.740954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:41.740954Z digest=sha256:b1e67c759f7a0cc529ce5c7140adf9f251fac0028713649208f6c5a4da45be22

Observation 9c15cb5d-39bd-4f93-9881-ba212ac50884 · outbound

This paper cites Referring image editing: Object-level image editing via referring expressions.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Referring image editing: Object-level image editing via referring expressions

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:46.767369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.814439Z digest=sha256:aa0f3d4300a9061e077d39b51a5566e82b0dde3935b7485ae6d5afc877f62430

Observation 1ff3dbf7-3042-4aa6-a781-dd4d3e341109 · outbound

This paper cites Pd-gan: Probabilistic diverse gan for image inpainting.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Pd-gan: Probabilistic diverse gan for image inpainting

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:46.503879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:41.896641Z digest=sha256:d4640e5918f80d2d2050af98585a0a2494b422449ed3114f6fdd563088829a0b

Observation 6f78ffdc-3ff6-4645-9089-e2493832b196 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:41.965549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:41.965549Z digest=sha256:974890e1849ca508a979eb9c1f175027195476f89d613ae8f9d3a9ebe3a864ef

Observation 5143dd83-287d-4fc5-a141-c2ee464b31d2 · outbound

This paper cites Improved baselines with visual instruction tuning.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Improved baselines with visual instruction tuning

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.024877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.024877Z digest=sha256:a2742cad40dc59a4de9154baf31e62fb7b24a9916ed43a0bfd3c2d2075efba9d

Observation e15e3013-bd9a-42e4-b27d-12817a215ec0 · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 27

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:46.251952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.100720Z digest=sha256:4b6c17abd2f64f107007c9b0e3ea247089d498fcea487dc77e2cfb6a9f063220

Observation c2ff6c3a-8c49-4fdc-b5b1-cf14719eda89 · outbound

This paper cites Styleclip: Text-driven manipulation of stylegan imagery.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Styleclip: Text-driven manipulation of stylegan imagery

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:46.100092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.140181Z digest=sha256:27df9a75775382c010b5ddd4973949929ed9d1f63392ba503fdd1dcc4c71998d

Observation 7f6a44eb-ab8e-42fc-831b-d8ad4f8eee29 · outbound

This paper cites Scalable diffusion models with transformers, 2023.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Scalable diffusion models with transformers, 2023

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.186770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.186770Z digest=sha256:f5a6bf6183e332e9428b97d64f1fcf8c02924719cfc8f1748dfce730f8d42641

Observation af94e8f9-dbc4-4a23-ba5e-c97e9b09b2f1 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis, 2023.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Sdxl: Improving latent diffusion models for high-resolution image synthesis, 2023

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.246605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.246605Z digest=sha256:1fe6e1eeedd5e9ac079e0dbeb8e3b2c04e8d290e85c62bf7c4e2018ccaae3b28

Observation c62b1d82-5ae8-4159-9fef-1bc04ef6214a · outbound

This paper cites Learning transferable visual models from natural language supervision.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Learning transferable visual models from natural language supervision

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.272643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.272643Z digest=sha256:c3ce4db8495980f5da4dceb957bdc02ce13b928e9c38e97c8526c2eeb74fb105

Observation 659d46ea-396c-4c73-a974-02e7728363dd · outbound

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

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions High-resolution image synthesis with latent diffusion models

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.305248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.305248Z digest=sha256:0c66accd1c182c27f8533d20116cf1a1cdd01cbea2f30ff16356c73e0a069977

Observation f6109faf-26d0-48b0-a037-2881affbe116 · outbound

This paper cites LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.348361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.348361Z digest=sha256:f25ea956bb2329598e39b5b812f0d0c99771b61a3b94d3e885eebd22d37f0b88

Observation f15afbd8-63f3-4402-9e4b-48efa7203cd8 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Laion-5b: An open large-scale dataset for training next generation image-text models

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:45.885542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.381545Z digest=sha256:405234275a6628ad714985b35289c1faae440c0470b21543e9f7bbb2f37e906b

Observation f5da0bfc-3980-4d2b-b5aa-efa0ac15a98a · outbound

This paper cites Emu edit: Precise image editing via recognition and generation tasks.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Emu edit: Precise image editing via recognition and generation tasks

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:45.710131Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.450848Z digest=sha256:7d89b21971ba4a5a2ac7246c24d6700248d5017c23a135dadb09fb4dca937201

Observation b69f7415-16fb-42cd-8515-b40ff078421f · outbound

This paper cites Denoising Diffusion Implicit Models.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Denoising Diffusion Implicit Models

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.523009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.523009Z digest=sha256:2755fb2fe57f87678160c67a5bc89b579d807ee49f9e600efd9f091109e7b7f4

Observation b3e2f00d-2d65-4485-b492-a60ae15658fd · outbound

This paper cites Qwen2.5 technical report, 2024.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Qwen2.5 technical report, 2024

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.552366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.552366Z digest=sha256:3848f9b5a8ad92d896c9582bc30c20d0308ee09ce37b99bd5f8b825f139c28f9

Observation a3b85c4a-cead-4c10-becc-68cd243e2d88 · outbound

This paper cites Qwen2.5-vl technical report, 2025.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Qwen2.5-vl technical report, 2025

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.614886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.614886Z digest=sha256:78345735409c4f0d6c762634b6b67f4ad8d72d21c28044d3419b194e231b421a

Observation 46ddd841-9f76-42be-8cfb-d02a0e29b1dd · outbound

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

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Visual autoregressive modeling: Scalable image generation via next-scale prediction

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:45.536667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.692639Z digest=sha256:d17bc463a57aad865434cd3bc589ab08f0cbee78a2309cc131a70bd937df7e15

Observation 728f4ffd-84bd-40ea-a2b3-093beebb58d9 · outbound

This paper cites Plug-and-play diffusion features for text- driven image-to-image translation.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Plug-and-play diffusion features for text- driven image-to-image translation

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.755197Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.755197Z digest=sha256:f09768023a454a8455b7dd0b01ca97903805aa14c572942856f33352873a695a

Observation 9ac21f7a-0a32-41f1-9e1c-46b476e57cac · outbound

This paper cites Taming Rectified Flow for Inversion and Editing.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Taming Rectified Flow for Inversion and Editing

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-07T14:20:42.843642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-07T14:20:42.843642Z digest=sha256:8e6ece7d317fb29e01310be6d04d88f54a8a132c74cf86adac1617ece9af1517

Observation 1ecde599-697f-400a-ac45-2e1e1b4c0af0 · outbound

This paper cites Magicbrush: A manually annotated dataset for instruction-guided image editing.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Magicbrush: A manually annotated dataset for instruction-guided image editing

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:45.394596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.875026Z digest=sha256:0e86fad6369cddff449ef9e5d69e1d2114b376a56d844615d65449c05623e785

Observation c4de195c-a230-4c0d-82bd-7061957ba96d · outbound

This paper cites Ultraedit: Instruction-based fine-grained image editing at scale.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Ultraedit: Instruction-based fine-grained image editing at scale

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:45.203911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:42.907547Z digest=sha256:e0033dbd17b7272622776e6de50435d2adab4116e6e1166e58a64f4aa65c1613

Observation aae73bb8-5e57-4ca3-aee0-cf39deb1569a · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 45

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:45.089627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.004128Z digest=sha256:5d4003fad3aeb3473285aa8e9883114ea93c897d8f34a208b89f6c6852f91893

Observation 9b5a0c36-3406-4ae8-b2e1-33f0acc9d496 · outbound

This paper cites We define mtrain = 1 for regions to be inpainted and mtrain = 0 for regions to be preserved.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions We define mtrain = 1 for regions to be inpainted and mtrain = 0 for regions to be preserved

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:44.989574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.043717Z digest=sha256:3536a9710403c402ab4f0df1039b4414cf54ddabcdb1e2b6fbe8c1ad72ab9b00

Observation 325267a0-1465-4ad9-a161-f7a58f13c614 · outbound

This paper cites A common strategy for LDM inpainting [32] is to concatenate the noisy latent zt with the mask mtrain and the latent representation of the known (unmasked) regions (1 − mtrain) ⊙ z0.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions A common strategy for LDM inpainting [32] is to concatenate the noisy latent zt with the mask mtrain and the latent representation of the known (unmasked) regions (1 − mtrain) ⊙ z0

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:44.837437Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.088959Z digest=sha256:f029231d9dfe9620e4ce637d4008747707c41764e97134bcfbb277c8b8f56c81

Observation 69408f78-8f45-49dc-9639-5b11b5f2ed32 · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 48

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:44.730634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.216015Z digest=sha256:b546c2cd39f4e673dd0dac312d206295e56aa05d127661d9268e7f9341f03fcb

Observation bd82f6a3-e638-440c-8b18-0c6ef8c301b0 · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 49

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:44.572564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.299654Z digest=sha256:bbf6ebac280a4d024387cf98d68b42a447d1442ad05dcadd1ad422a9c0001cdb

Observation f2f174f1-06a0-4ae2-b7c9-ade042d5250d · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 50

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:44.500991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.318830Z digest=sha256:bde9c80dfb36b09e6fdaeb98875525c8151bf16eec203b64c0c8a421bafb9715

Observation 3e52bf75-358b-4675-bf02-930c47b11bbd · outbound

This paper cites an unresolved cited work.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Unresolved cited work

Reference 51

Resolution
unresolved
raw_fallback, observed 2026-08-07T14:20:44.378358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.366508Z digest=sha256:7ce5a8fd726fff1c8599e73444b8b3f7a18427a36d375d5cd31662ca4fa3424c

Observation f84f07f7-0125-4644-8cc0-c7365c2affc2 · outbound

This paper cites Here, m = 1 signifies the region to be inpainted/edited, and m = 0 signifies the region to be preserved.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Here, m = 1 signifies the region to be inpainted/edited, and m = 0 signifies the region to be preserved

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:44.291463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.446762Z digest=sha256:dd2716e06471fecdf7d8161d2275ba5fd9527fd392aae115242a03721bc4e324

Observation 039752da-d3d3-45e3-8bb7-99f986ef6ecf · outbound

This paper cites ,1: (a) Prepare U-Net Input: If the U-Net was trained for inpainting using channel concatenation (as in Eq.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions ,1: (a) Prepare U-Net Input: If the U-Net was trained for inpainting using channel concatenation (as in Eq

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:44.222655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.527926Z digest=sha256:8566ccbc083553112e2355e2940a3e43ac39c759efe7ec22fc05a040d3341965

Observation e2daab04-126a-4118-9285-97e14871682a · outbound

This paper cites For deterministic DDIM, σt = 0.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions For deterministic DDIM, σt = 0

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:44.039209Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.610644Z digest=sha256:731aa75897c43a6b024396cb3b8f434db9425a357d4815449df728cb1d936c51

Observation 87d9ecba-04a3-4b22-8fd3-25778950a280 · outbound

This paper cites Move the cat to the sofa,.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Move the cat to the sofa,

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:43.947935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:43.649274Z digest=sha256:756eb56f99eec191ae9ac20f6ddd2c377e01eca92676cd50acbbacd279d7e33d

Observation b8c91622-2188-4f07-a7e6-506f7c71af03 · outbound

This paper cites Note: Formal technical report might be available separately.

Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions Note: Formal technical report might be available separately

Reference 2024

Resolution
verified fuzzy
raw_fallback, observed 2026-08-07T14:20:49.256212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-08-07T14:20:40.346637Z digest=sha256:541e1d250fd9147d61d8f66d536e6f12ee12000ef5bf568d69338378b0a69487

Pith citing papers

Observation 77720712-e23a-4f8e-8bc1-d1f5ffb72f37 · inbound

Drift Flow Matching cites this paper.

Drift Flow Matching Beyond Editing Pairs: Fine-Grained Instructional Image Editing via Multi-Scale Learnable Regions

Reference 76

Resolution
malformed identifier
arxiv_id, observed 2026-05-20T14:33:21.486742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

source=pdf_text observed=2026-05-20T14:31:05.979325Z digest=sha256:122eaa09b1ac20874cc52b286aea4befebf722863913fd8c338fc31da048d178