GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis | Paper Citation Record

Observation bed3369b-650d-46a8-9234-aba256d75c34 · outbound

This paper cites A-star: Test-time attention segregation and retention for text-to-image synthesis, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis A-star: Test-time attention segregation and retention for text-to-image synthesis, 2023

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.300215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cda2b007-21ac-4b99-a754-572533473bc3 · outbound

This paper cites DeepFloyd IF: a novel state- of-the-art open-source text-to-image model with a high de- gree of photorealism and language understanding.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis DeepFloyd IF: a novel state- of-the-art open-source text-to-image model with a high de- gree of photorealism and language understanding

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.280303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b5bf230a-2a03-4e8c-9e0e-e773a6ce7919 · outbound

This paper cites Qwen-vl: A versatile vision-language model for un- derstanding, localization, text reading, and beyond, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Qwen-vl: A versatile vision-language model for un- derstanding, localization, text reading, and beyond, 2023

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.260506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b339c7e2-e714-4f03-b204-3d5721fa91dc · outbound

This paper cites Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.247234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90ae79cd-d2f3-4270-a9d8-c06a159c829f · outbound

This paper cites Improving image generation with better captions.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Improving image generation with better captions

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.228961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5bfdf924-71a9-4ae8-98db-80bbb96de9fc · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.490886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b638a2ad-8530-4496-a363-cdbf5012cf38 · outbound

This paper cites Language models are few-shot learners.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Language models are few-shot learners

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.191263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6086d326-f003-471e-aed3-4af2cd80ed40 · outbound

This paper cites Getting it right: Improving spatial consis- tency in text-to-image models, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Getting it right: Improving spatial consis- tency in text-to-image models, 2024

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.173419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 51d8c81c-b24a-436e-9c4f-765bf6bfd519 · outbound

This paper cites Attend-and-excite: Attention-based se- mantic guidance for text-to-image diffusion models, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Attend-and-excite: Attention-based se- mantic guidance for text-to-image diffusion models, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.503186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d57976e-fbca-430c-b40b-63dd5df28fba · outbound

This paper cites Pixart-α: Fast training of dif- fusion transformer for photorealistic text-to-image synthesis,.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Pixart-α: Fast training of dif- fusion transformer for photorealistic text-to-image synthesis,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.507931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1fea6b8-d836-4cda-a49e-e11900f76038 · outbound

This paper cites Pixart- σ: Weak-to-strong training of diffu- sion transformer for 4k text-to-image generation, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Pixart- σ: Weak-to-strong training of diffu- sion transformer for 4k text-to-image generation, 2024

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.107972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 02dfee4e-20f4-4853-b358-7155ee696c68 · outbound

This paper cites Region-aware text-to-image generation via hard binding and soft refinement, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Region-aware text-to-image generation via hard binding and soft refinement, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.091205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b166b6e3-0830-4c8f-aafd-92385457be22 · outbound

This paper cites Visual pro- gramming for text-to-image generation and evaluation.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Visual pro- gramming for text-to-image generation and evaluation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.075200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bf5da09b-78bc-43aa-a25c-157b42e6200c · outbound

This paper cites Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image gener- ation, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Davidsonian scene graph: Improving reliability in fine-grained evaluation for text-to-image gener- ation, 2024

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.051720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d0a41978-a67a-4a1f-af01-e85a61a2bcc7 · outbound

This paper cites Diffusion Models Beat GANs on Image Synthesis.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Diffusion Models Beat GANs on Image Synthesis

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.529153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0be05d1e-5683-4ba9-bb2e-da528f3f5469 · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:32.030718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cb20479a-72b5-4db0-97df-cddcee70e91f · outbound

This paper cites Training-free structured diffusion guidance for compositional text-to-image synthesis, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Training-free structured diffusion guidance for compositional text-to-image synthesis, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:32.005764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 74be5588-d15b-41c5-a165-51761f7a546b · outbound

This paper cites Training- free structured diffusion guidance for compositional text-to- image synthesis.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Training- free structured diffusion guidance for compositional text-to- image synthesis

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.984896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c77b16bb-bf01-4f26-83d5-c72ecf469408 · outbound

This paper cites Ranni: Taming text-to-image diffusion for accurate instruction following, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Ranni: Taming text-to-image diffusion for accurate instruction following, 2024

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.967627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 94161442-6227-474c-95c0-6d6fadb97322 · outbound

This paper cites Lumina-t2x: Trans- forming text into any modality, resolution, and duration via flow-based large diffusion transformers, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Lumina-t2x: Trans- forming text into any modality, resolution, and duration via flow-based large diffusion transformers, 2024

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.946643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9bc66789-4e7d-4efc-a703-c1712d0cd2d2 · outbound

This paper cites Seed-data-edit technical report: A hybrid dataset for instruc- tional image editing, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Seed-data-edit technical report: A hybrid dataset for instruc- tional image editing, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.921767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f4b8586-bfbc-4a7f-8956-d0e82f3fa6d9 · outbound

This paper cites Benchmarking spatial relationships in text-to-image generation, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Benchmarking spatial relationships in text-to-image generation, 2023

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.900395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e18515ee-4e55-4fa5-904f-7a8d3b48e650 · outbound

This paper cites Prompt-to-Prompt Image Editing with Cross Attention Control.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Prompt-to-Prompt Image Editing with Cross Attention Control

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.561625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dded3e00-4697-4846-b141-59dbf9eb4832 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium, 2018.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Gans trained by a two time-scale update rule converge to a local nash equilib- rium, 2018

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.566028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f606f45-365b-4313-8f32-450e2e0454bc · outbound

This paper cites Ella: Equip diffusion models with llm for en- hanced semantic alignment, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Ella: Equip diffusion models with llm for en- hanced semantic alignment, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.872525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3e2bb6fd-8749-46a5-a0d6-fea4fcc57ef2 · outbound

This paper cites Tifa: Accurate and interpretable text-to-image faithfulness evaluation with question answering, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Tifa: Accurate and interpretable text-to-image faithfulness evaluation with question answering, 2023

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.858551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98f72a65-7a4e-46a1-aaea-54c54a17e0c0 · outbound

This paper cites T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation, 2023

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.840121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c9b3de4b-e734-4834-b6ee-28b02d02a96d · outbound

This paper cites Comat: Aligning text-to-image diffusion model with image- to-text concept matching, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Comat: Aligning text-to-image diffusion model with image- to-text concept matching, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.826308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3af56afe-6a0a-4abb-affb-fa86450f6d9f · outbound

This paper cites Text encoders bottleneck compositionality in contrastive vision- language models, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Text encoders bottleneck compositionality in contrastive vision- language models, 2023

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.805599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cda29111-aeb8-4beb-9f30-f6b84ccfac76 · outbound

This paper cites Learning action and reasoning-centric image editing from videos and simulations, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Learning action and reasoning-centric image editing from videos and simulations, 2024

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.785230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cdcbd46e-ab37-4f70-b60f-99903e531ada · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:31.770392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 49ed22d1-d73c-47f8-b29f-1bf897de3a44 · outbound

This paper cites Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image genera- tion, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Playground v2.5: Three insights towards enhancing aesthetic quality in text-to-image genera- tion, 2024

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.752002Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f20a9e5d-e240-4f25-91c2-e38994916b3e · outbound

This paper cites Llm- grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models,.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Llm- grounded diffusion: Enhancing prompt understanding of text-to-image diffusion models with large language models,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.732899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 21670d09-c97f-4be5-99da-d205ac76e14c · outbound

This paper cites Playground v3: Improving text-to- image alignment with deep-fusion large language models,.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Playground v3: Improving text-to- image alignment with deep-fusion large language models,

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.716202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 99421c2f-a9dd-401a-96b6-525f25f84133 · outbound

This paper cites Visual instruction tuning, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Visual instruction tuning, 2023

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.616321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e39eaedf-1627-4daf-8ca9-3af8a57bc7c0 · outbound

This paper cites LLMScore: Unveiling the power of large language models in text-to-image synthesis evaluation.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis LLMScore: Unveiling the power of large language models in text-to-image synthesis evaluation

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.681682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 66938b13-bc4d-41eb-ab2d-84792ada1d62 · outbound

This paper cites Improved Denoising Diffusion Probabilistic Models.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Improved Denoising Diffusion Probabilistic Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.625314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12cbd62a-810f-44f6-b663-979f9c563dd5 · outbound

This paper cites Compositional text-to-image gen- eration with dense blob representations.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Compositional text-to-image gen- eration with dense blob representations

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.665627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5d1d8955-eba2-4ed4-94c6-8ced69af0631 · outbound

This paper cites Plummer, Liwei Wang, Chris M.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Plummer, Liwei Wang, Chris M

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.647693Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9755f409-36c3-4099-a91c-507ffdfaeb5c · outbound

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

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Sdxl: Improving latent diffusion models for high-resolution image synthesis, 2023

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.632633Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1644ac52-90ff-4843-8c0d-c545cc70919a · outbound

This paper cites Learning transferable visual models from natural language supervision, 2021.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Learning transferable visual models from natural language supervision, 2021

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.617470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 14670d5c-3894-4a0f-8b4c-e11f6b7ecf87 · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:31.602380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e14f0581-2da5-4d64-a571-7c97840f6f00 · outbound

This paper cites Hierarchical text-conditional image gener- ation with clip latents, 2022.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Hierarchical text-conditional image gener- ation with clip latents, 2022

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.650842Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35c68b8a-11a2-4ed9-b342-00e1509b0003 · outbound

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

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis High-resolution image synthesis with latent diffusion models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.574643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 27132a6a-43e1-49c0-ae3d-d47e8641a6fe · outbound

This paper cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.658247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 257296de-fc2f-43f3-b8f4-e026024ef113 · outbound

This paper cites Image ma- nipulation via multi-hop instructions - a new dataset and weakly-supervised neuro-symbolic approach.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Image ma- nipulation via multi-hop instructions - a new dataset and weakly-supervised neuro-symbolic approach

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.559849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1b4b7c84-ad86-4540-8d0f-859bed7223a7 · outbound

This paper cites Weiss, Niru Mah- eswaranathan, and Surya Ganguli.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Weiss, Niru Mah- eswaranathan, and Surya Ganguli

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.666169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b282ce-f535-493e-9bdb-ddc69fb0d79f · outbound

This paper cites Stable diffusion 3.5.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Stable diffusion 3.5

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.537546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c9a82887-f876-49c8-9e8b-fb47ee37e061 · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:31.518877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fcaa1468-af26-43c5-acdb-c88f8fd7becc · outbound

This paper cites Winoground: Probing vision and language models for visio- linguistic compositionality.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Winoground: Probing vision and language models for visio- linguistic compositionality

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.501698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 348e1eb1-bfc3-471b-91d4-c89d745ff740 · outbound

This paper cites Llama 2: Open foundation and fine- tuned chat models, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Llama 2: Open foundation and fine- tuned chat models, 2023

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.682908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f305d66-94d9-4a5e-ae82-369b7cdc71ce · outbound

This paper cites GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.687083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5720fe84-870b-4b23-97e9-417e29eb24ba · outbound

This paper cites Tokencompose: Text-to-image diffusion with token-level supervision, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Tokencompose: Text-to-image diffusion with token-level supervision, 2024

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.469464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f9e0b8e0-e33c-4f8e-adfb-4eee1ad3d8bd · outbound

This paper cites Omniedit: Building image editing generalist models through specialist supervision, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Omniedit: Building image editing generalist models through specialist supervision, 2024

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.455906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation edadb203-31e2-4a9d-a523-d7a5af957c6f · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Chain-of-thought prompting elicits reasoning in large language models, 2023

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.700401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d668723-8511-4b85-b5e0-72b230b8b9ee · outbound

This paper cites Revisiting text-to-image evaluation with gecko: On metrics, prompts, and human ratings, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Revisiting text-to-image evaluation with gecko: On metrics, prompts, and human ratings, 2024

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.425586Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98d6a5a6-3c38-4338-96d4-f9bd776d20fb · outbound

This paper cites Self-correcting LLM-controlled Diffusion Models.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Self-correcting LLM-controlled Diffusion Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.711227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba1aad6d-46f2-469e-a992-ce9ad1fad528 · outbound

This paper cites Paragraph-to-image generation with information-enriched diffusion model, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Paragraph-to-image generation with information-enriched diffusion model, 2023

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.410456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 294115a5-0286-43a0-a44a-1c049e630ea1 · outbound

This paper cites Conceptmix: A compositional image generation benchmark with controllable difficulty, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Conceptmix: A compositional image generation benchmark with controllable difficulty, 2024

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.396133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bd55eee2-c0c4-414e-adab-39192feae6f6 · outbound

This paper cites Sana: Efficient high-resolution im- age synthesis with linear diffusion transformer, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Sana: Efficient high-resolution im- age synthesis with linear diffusion transformer, 2024

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.381895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd65f77d-2bd4-4ab0-922e-d50f5bc8ba7a · outbound

This paper cites Mastering text-to-image diffu- sion: Recaptioning, planning, and generating with multi- modal llms.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Mastering text-to-image diffu- sion: Recaptioning, planning, and generating with multi- modal llms

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.362287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aa07a71b-bfec-4774-83fe-9e5d1b87c90a · outbound

This paper cites What you see is what you read? improving text- image alignment evaluation, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis What you see is what you read? improving text- image alignment evaluation, 2023

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.348073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b094fcda-f175-479b-9d18-88ffdfda1fe8 · outbound

This paper cites When and why vision- language models behave like bags-of-words, and what to do about it?, 2023.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis When and why vision- language models behave like bags-of-words, and what to do about it?, 2023

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.332473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cad9604b-9dbe-4bcc-9a57-87f815593b72 · outbound

This paper cites Magicbrush: A manually annotated dataset for instruction- guided image editing, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Magicbrush: A manually annotated dataset for instruction- guided image editing, 2024

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.317935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e92afcc7-c31a-4635-be7d-e864c85bddde · outbound

This paper cites HIVE: Harnessing Human Feedback for Instructional Visual Editing.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis HIVE: Harnessing Human Feedback for Instructional Visual Editing

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T20:06:30.750233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d78ac876-020a-47ac-83c3-544d832bdc9a · outbound

This paper cites Text as neural operator: Image manipulation by text instruction.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Text as neural operator: Image manipulation by text instruction

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.305073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dee9b134-643b-4a62-8803-5b3cd5ff9f1f · outbound

This paper cites Tie: Revolutionizing text-based image edit- ing for complex-prompt following and high-fidelity editing,.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Tie: Revolutionizing text-based image edit- ing for complex-prompt following and high-fidelity editing,

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.290596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7dbac9ee-fedb-40f1-bca2-7a576a932679 · outbound

This paper cites Lumina-next: Making lumina-t2x stronger and faster with next-dit, 2024.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Lumina-next: Making lumina-t2x stronger and faster with next-dit, 2024

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.277490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 95ad7bdf-d2b1-47fa-90b5-29f9f47ac959 · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:31.264591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a9b6d4d4-eaaa-49b5-867e-bb23db5bfc61 · outbound

This paper cites 8 for the GraPE naive pipeline used in sec- tion 4.3.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis 8 for the GraPE naive pipeline used in sec- tion 4.3

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.251327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ea2346f2-a9be-48f5-b7db-8c1b765ff574 · outbound

This paper cites Unlike GraPE, SLD operates in image layout- space which is either generated using either LLMs or open- vocabulary object detectors.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unlike GraPE, SLD operates in image layout- space which is either generated using either LLMs or open- vocabulary object detectors

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.236554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 944d8ac0-127a-4bd2-af3a-ee5bbb7b089f · outbound

This paper cites golden apple, next to bronze, next to silver grapes.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis golden apple, next to bronze, next to silver grapes

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.221772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a922c883-212a-4f36-a984-bc4a1d470120 · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:31.207157Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ae337b3c-36dc-45e6-b775-85a6ea27dc30 · outbound

This paper cites A woman wearing a white shirt and gray shorts using a shovel to dig in snow.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis A woman wearing a white shirt and gray shorts using a shovel to dig in snow

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.192504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cd0453f4-28b3-4e77-97dc-765c4cbcd0e6 · outbound

This paper cites Therefore we can use the following editing instructions to correct these.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Therefore we can use the following editing instructions to correct these

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.177474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f258f834-36e0-486d-aa30-ccf856f85b5e · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:06:31.165249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cf2e1a26-f3e8-468e-af0f-f92dbb66fa4c · outbound

This paper cites an unresolved cited work.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Unresolved cited work

Reference 77

Resolution: parse uncertain; raw_fallback, observed 2026-08-11T20:06:31.151215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a4046dbc-9326-47cd-af71-cfd4a9ec8989 · outbound

This paper cites Figure 8.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis Figure 8

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.129872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 88daf809-5308-4771-9c85-3dbcb14201e2 · outbound

This paper cites We look at the breakup of these 100 plans and how the planner and editing-model fare on them.

GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis We look at the breakup of these 100 plans and how the planner and editing-model fare on them

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:06:31.115370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers