Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models | Paper Citation Record

Observation 1b45c9dc-5db5-4982-9ef1-e50edfe83359 · outbound

This paper cites write newline.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:50.808315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f71b3e6-8ec6-463b-bbec-afd2add3b53b · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models A-star: Test-time attention segregation and retention for text-to-image synthesis

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:50.867916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07799072-ad50-41b4-b658-3d6ceaf1db9d · outbound

This paper cites Kandinsky 3.0 Technical Report.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Kandinsky 3.0 Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:50.976891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2a69bfd-0dca-4dd9-8e21-23820b2719b6 · outbound

This paper cites Finite-time analysis of the multiarmed bandit problem.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Finite-time analysis of the multiarmed bandit problem

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.033654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a8c774a-95af-48c2-849f-65c0d9e7309f · outbound

This paper cites Spatext: Spatio-textual representation for controllable image generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Spatext: Spatio-textual representation for controllable image generation

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.080754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b624120-e17e-4a45-9d74-32299bfb1238 · outbound

This paper cites Cc3d: Layout-conditioned generation of compositional 3d scenes.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Cc3d: Layout-conditioned generation of compositional 3d scenes

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.127391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e40a2e8-8777-44e5-873e-7d0bd3629d80 · outbound

This paper cites Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models, 2023.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Hrs-bench: Holistic, reliable and scalable benchmark for text-to-image models, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.167595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3b64dc5-5646-4eef-900f-5df72f601870 · outbound

This paper cites MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.252650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41a8f068-b396-4a9b-b4e4-133192444c86 · outbound

This paper cites Improving image generation with better captions.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Improving image generation with better captions

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.298620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd1b3e2-497d-4ced-ae61-9af9773af035 · outbound

This paper cites Make It Count: Text-to-Image Generation with an Accurate Number of Objects.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Make It Count: Text-to-Image Generation with an Accurate Number of Objects

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.348576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26a059a3-eb12-4ace-b2ed-612a9e13c0e9 · outbound

This paper cites Conceptual 12M : Pushing web-scale image-text pre-training to recognize long-tail visual concepts.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Conceptual 12M : Pushing web-scale image-text pre-training to recognize long-tail visual concepts

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:03.878208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b3a0d950-88b9-4ea0-9329-aa5f0ab4ffb8 · outbound

This paper cites Getting it Right: Improving Spatial Consistency in Text-to-Image Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Getting it Right: Improving Spatial Consistency in Text-to-Image Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.518955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bfb679c-f849-4704-bf91-e714a875ec45 · outbound

This paper cites Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:03.719627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e1d998d1-f294-4f63-905f-d4b06ff9f1f6 · outbound

This paper cites SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.657856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aaae8dd0-4517-47b7-bf31-a63a6426e88d · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.736340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 307c10fb-40cd-45ef-8cf9-05c055f67e7e · outbound

This paper cites Training-free layout control with cross-attention guidance.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Training-free layout control with cross-attention guidance

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:03.564234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f60b0b08-79b3-4092-81a7-67085a3a6130 · outbound

This paper cites LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.832817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a510a3f-4052-400d-b187-98e87f161fd8 · outbound

This paper cites Dall·e mini, 7 2021.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Dall·e mini, 7 2021

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:03.406246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9765d374-7cba-47c7-84b2-6d72e643d53c · outbound

This paper cites CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:51.971405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7458bd6-c8d0-4088-bc99-df1b62ad21c2 · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Training-free structured diffusion guidance for compositional text-to-image synthesis

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:03.187547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6e88afe7-aa0c-466e-b77f-134e9213febc · outbound

This paper cites Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.182184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b3f176-fa36-40c8-99f9-e08ba899c89e · outbound

This paper cites GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.298002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54e5f73d-cf88-4460-bc27-fa90af3275fe · outbound

This paper cites Benchmarking Spatial Relationships in Text-to-Image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Benchmarking Spatial Relationships in Text-to-Image Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.391265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a97cb007-cd59-49c9-8682-85279d24b011 · outbound

This paper cites Gradient Guidance for Diffusion Models: An Optimization Perspective.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Gradient Guidance for Diffusion Models: An Optimization Perspective

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.464757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56e3b960-01db-4269-88bc-a7be5e2209ab · outbound

This paper cites CLIPScore: A Reference-free Evaluation Metric for Image Captioning.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.605567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5d12599-6650-44dc-a625-5dbe2c18cc58 · outbound

This paper cites GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.737177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b727f7-47fc-4c9b-83c7-40f10f905237 · outbound

This paper cites Probability inequalities for sums of bounded random variables.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Probability inequalities for sums of bounded random variables

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.842219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6111a05-8052-4a32-8d30-9ecd28e2c8e2 · outbound

This paper cites Probability inequalities for sums of bounded random variables.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Probability inequalities for sums of bounded random variables

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:52.928167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f00c05be-3b62-4de4-a843-a95554a680d8 · outbound

This paper cites Token merging for training-free semantic binding in text-to-image synthesis.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Token merging for training-free semantic binding in text-to-image synthesis

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:03.036753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 79b60aa4-8021-40ee-a135-487356241c7b · outbound

This paper cites A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:48:58.751381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 68e853c2-b619-4f9d-95ab-a9eda965bb51 · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:02.829715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8206daf3-8e7a-48dc-9aa8-fead9a8a5ba7 · outbound

This paper cites An information-theoretic evaluation of generative models in learning multi-modal distributions.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models An information-theoretic evaluation of generative models in learning multi-modal distributions

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:02.654824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 07d48034-0798-4fe7-9a7d-d13cc77c49dc · outbound

This paper cites Rethinking FID: Towards a Better Evaluation Metric for Image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Rethinking FID: Towards a Better Evaluation Metric for Image Generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:53.316391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b20c63-ef67-4c6f-8e17-fdad4f6363f6 · outbound

This paper cites What's ``up'' with vision-language models? investigating their struggle with spatial reasoning.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models What's ``up'' with vision-language models? investigating their struggle with spatial reasoning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:02.501071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 568f43b0-6aeb-4c70-a4c0-43df7e04bb1f · outbound

This paper cites If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:53.437835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71edc826-1f08-423d-bc26-8dfe123c5cfb · outbound

This paper cites BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:48:58.598720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 65b24792-db47-47ac-a5cb-977279bd3622 · outbound

This paper cites Dense text-to-image generation with attention modulation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Dense text-to-image generation with attention modulation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:02.338882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 60788508-c8c4-4c60-b0e9-270c434757eb · outbound

This paper cites Segment Anything.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Segment Anything

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:53.722447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 632e5ff8-76bb-4f4e-89de-f5cc318033e6 · outbound

This paper cites Improved Precision and Recall Metric for Assessing Generative Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Improved Precision and Recall Metric for Assessing Generative Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:53.852853Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 938ff7f5-8e90-47a5-b9f5-08632237ec65 · outbound

This paper cites Laion-coco 600m.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Laion-coco 600m

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:02.158280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cc4b0226-9d4c-407a-8619-11b898df9d86 · outbound

This paper cites GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T21:48:58.472999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 83dd898d-37de-4d8f-b1b2-ea746ca26f09 · outbound

This paper cites GLIGEN: Open-Set Grounded Text-to-Image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models GLIGEN: Open-Set Grounded Text-to-Image Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:54.226577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0981c3cf-42c0-4f5a-ad88-a0fa44bdb9bb · outbound

This paper cites Divide & bind your attention for improved generative semantic nursing.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Divide & bind your attention for improved generative semantic nursing

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:01.947376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 163ad252-7a8e-46fe-966d-63458b240b4e · outbound

This paper cites LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:54.541171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b6393a3-ac2e-4b9f-b839-c7024428db99 · outbound

This paper cites Microsoft COCO: Common Objects in Context.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Microsoft COCO: Common Objects in Context

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:54.670059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation babd993d-63a6-4fb9-89a9-c3b2f7b3f4cd · outbound

This paper cites Evaluating Text-to-Visual Generation with Image-to-Text Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Evaluating Text-to-Visual Generation with Image-to-Text Generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:54.778142Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c9d4880-0781-4eaa-a364-e680ac9a6c13 · outbound

This paper cites Compositional Visual Generation with Composable Diffusion Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Compositional Visual Generation with Composable Diffusion Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:54.880447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced64cf3-11ee-4234-afc1-7abfb9ed26c6 · outbound

This paper cites Grounding dino: Marrying dino with grounded pre-training for open-set object detection.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Grounding dino: Marrying dino with grounded pre-training for open-set object detection

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:01.783156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9fd69e75-d069-47bf-9d8d-e0c8a10bb6cf · outbound

This paper cites Correcting diffusion generation through resampling.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Correcting diffusion generation through resampling

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:01.584642Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9090d239-61cb-4e85-98b5-3771c792f67e · outbound

This paper cites Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.131271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a67cb10-e9b4-462b-8869-d8d9ce9ea2b3 · outbound

This paper cites Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:48:58.305767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b8d16741-9771-454f-b974-e8b3bc0b739c · outbound

This paper cites Scaling open-vocabulary object detection.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Scaling open-vocabulary object detection

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:01.393772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9970ec12-3997-4701-9dba-82053fae0d7e · outbound

This paper cites Simple Open-Vocabulary Object Detection with Vision Transformers.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Simple Open-Vocabulary Object Detection with Vision Transformers

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.316835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a378cbee-6979-48cf-a0c9-9d1ed0c2c8aa · outbound

This paper cites GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.441530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35e4c707-9e52-4348-b0d1-5155491146cf · outbound

This paper cites GPT-4 Technical Report.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models GPT-4 Technical Report

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.619085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84c356ae-bf5c-4a8f-b989-9ee6242478a9 · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models DINOv2: Learning Robust Visual Features without Supervision

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.723845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 676cee09-5884-4021-9fad-a5e72b17e219 · outbound

This paper cites Grounded Text-to-Image Synthesis with Attention Refocusing.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Grounded Text-to-Image Synthesis with Attention Refocusing

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.795064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 721246fa-07dd-4586-a22c-97860a7034c4 · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:55.869024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a181d03-2143-46e2-898a-5e4a2f6f696a · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Learning transferable visual models from natural language supervision

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:01.192900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e6aace94-dd9d-4064-93eb-a33d6b4d5ae1 · outbound

This paper cites Zero-shot text-to-image generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Zero-shot text-to-image generation

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:00.928478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 26b51eb6-89dd-43c0-83c6-b8ba3c63a021 · outbound

This paper cites Hierarchical Text-Conditional Image Generation with CLIP Latents.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.058839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2edd81a-8cec-4252-a975-0b63c4d33ac0 · outbound

This paper cites Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Linguistic binding in diffusion models: Enhancing attribute correspondence through attention map alignment

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:00.717211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 367c2b0b-cd2b-4eb0-9ee8-07b77b7c9b72 · outbound

This paper cites Arkhipkin, Igor Pavlov, Ilya Ryabov, Angelina Kuts, Alexander Panchenko, Andrey Kuznetsov, and Denis Dimitrov.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Arkhipkin, Igor Pavlov, Ilya Ryabov, Angelina Kuts, Alexander Panchenko, Andrey Kuznetsov, and Denis Dimitrov

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:00.511252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 112b0fc5-524c-4449-a5eb-e9e146ef55fd · outbound

This paper cites Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.243827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf64bec-9478-44dd-9edb-b24615ee4229 · outbound

This paper cites Be more diverse than the most diverse: Optimal mixtures of generative models via mixture- UCB bandit algorithms.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Be more diverse than the most diverse: Optimal mixtures of generative models via mixture- UCB bandit algorithms

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:00.335950Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dc1a2e9c-df3d-4cad-9d28-43c19116b4c3 · outbound

This paper cites Some aspects of the sequential design of experiments.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Some aspects of the sequential design of experiments

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.381683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dce2eed6-d5f8-4927-b29d-0b19ead8005f · outbound

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

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models High-resolution image synthesis with latent diffusion models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.449019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e97464c5-dbec-4752-bd3f-816cbb486125 · outbound

This paper cites Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:49:00.178187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1878b31b-1707-4e95-b649-8c5be5da182b · outbound

This paper cites Predicated diffusion: Predicate logic-based attention guidance for text-to-image diffusion models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Predicated diffusion: Predicate logic-based attention guidance for text-to-image diffusion models

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:48:59.979688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e6c76451-9de6-4185-a098-92aa33429390 · outbound

This paper cites InstanceDiffusion: Instance-level Control for Image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models InstanceDiffusion: Instance-level Control for Image Generation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.611116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6eea2c92-3000-4d91-a3bb-cca1487973e0 · outbound

This paper cites Wolfe and Robert V.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Wolfe and Robert V

Reference 71

Resolution: verified exact; raw_fallback, observed 2026-08-06T21:48:58.107706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aa2d77d7-1af9-455d-87fa-796a078c9105 · outbound

This paper cites R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.745122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d63d2f5-54b2-4226-bed7-c60f7208a5cd · outbound

This paper cites BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

Reference 73

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:48:57.931564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8ba51f86-cc4a-4f76-a2b8-a0ccd79790fb · outbound

This paper cites Imagereward: Learning and evaluating human preferences for text-to-image generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Imagereward: Learning and evaluating human preferences for text-to-image generation

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:48:59.834159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ff379478-dc49-45a9-9c2d-0c34e5ca44a1 · outbound

This paper cites Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:56.923723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855cada1-bf5a-43e5-8e87-dbdad5b0b6fc · outbound

This paper cites Reco: Region-controlled text-to-image generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Reco: Region-controlled text-to-image generation

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:48:59.681822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3c0c1880-0a35-4d0d-a0ed-89c56d17e0ef · outbound

This paper cites Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:57.035500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ecde0f2-5b63-4da1-a25c-e919df18b343 · outbound

This paper cites Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:57.092979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c6e4dad-b9be-4ec0-9c4e-a2e4a8147b8d · outbound

This paper cites Multi-grained vision language pre-training: Aligning texts with visual concepts.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Multi-grained vision language pre-training: Aligning texts with visual concepts

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:48:59.553613Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation dbe8a91e-ea7b-491b-89ed-248bec555a13 · outbound

This paper cites Adding Conditional Control to Text-to-Image Diffusion Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Adding Conditional Control to Text-to-Image Diffusion Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:57.313620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2075568a-7757-4427-bc8b-f412c48e1914 · outbound

This paper cites Realcompo: Balancing realism and compositionality improves text-to-image diffusion models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Realcompo: Balancing realism and compositionality improves text-to-image diffusion models

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:48:59.423169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 640cee54-8bbc-4849-9c19-455d032b15ab · outbound

This paper cites Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:57.426716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac7f8dd9-14e8-4c32-a600-b96082be45b4 · outbound

This paper cites LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:48:57.770163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7924c320-10cd-4992-9f9a-459d6d3807d2 · outbound

This paper cites a henb \.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models a henb \

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:48:59.258838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 092761a5-b219-4d41-b024-75209b95bd11 · outbound

This paper cites write newline.

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models write newline

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-06T21:48:57.591417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers