Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-01T08:07:10.345273Z
Paper Citation Record · LEDGER
When Do Diffusion Models learn to Generate Multiple Objects?
As of 5 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2605.00273.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
42 of 42 outbound references displayed
- verified exact23
- verified fuzzy11
- unresolved2
- parse uncertain0
- malformed identifier0
- metadata mismatch6
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation acfb3be9-710d-49fd-8a1f-d53a41f97f9a · outbound
This paper cites & Mézard, M.Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in TrainingarXiv:2505.17638 [cs].
When Do Diffusion Models learn to Generate Multiple Objects? & Mézard, M.Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in TrainingarXiv:2505.17638 [cs]
Reference 1
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.923667Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 850f2cd5-b7de-41b7-8d85-f7fb0af70361 · outbound
This paper cites Countsteer: Steering attention for object counting in diffusion models.arXiv preprint arXiv:2511.11253,.
When Do Diffusion Models learn to Generate Multiple Objects? Countsteer: Steering attention for object counting in diffusion models.arXiv preprint arXiv:2511.11253,
Reference 2
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.919104Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e270e4fd-908f-4181-8700-121895dd69c4 · outbound
This paper cites Local mechanisms of compositional generalization in conditional diffusion.
When Do Diffusion Models learn to Generate Multiple Objects? Local mechanisms of compositional generalization in conditional diffusion
Reference 3
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.914001Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b8b22434-d16b-4090-9643-572d14c202c4 · outbound
This paper cites PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis.
When Do Diffusion Models learn to Generate Multiple Objects? PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.073008Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0cac837c-ce63-4b3a-a17c-a6887d1c5745 · outbound
This paper cites Identifiability Results for Multimodal Contrastive Learning.
When Do Diffusion Models learn to Generate Multiple Objects? Identifiability Results for Multimodal Contrastive Learning
Reference 5
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:32.077282Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ebbc73c0-dbe9-45d6-b3d7-ddd72cae66af · outbound
This paper cites A., and Zaharia, M.
When Do Diffusion Models learn to Generate Multiple Objects? A., and Zaharia, M
Reference 6
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:32.067435Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e9ad0629-5a2c-44e0-8775-6840e82abdd5 · outbound
This paper cites What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models.
When Do Diffusion Models learn to Generate Multiple Objects? What Drives Compositional Generalization? The Importance of Continuous Training Objectives in Visual Generative Models
Reference 7
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T08:15:32.041741Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b557a306-0d19-48cd-8212-2bb4953064f3 · outbound
This paper cites Early-stopping too late? traces of memorization be- fore overfitting in generative diffusion.
When Do Diffusion Models learn to Generate Multiple Objects? Early-stopping too late? traces of memorization be- fore overfitting in generative diffusion
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.148705Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b09db714-4c3a-4780-86b5-885e42dbacd3 · outbound
This paper cites LoRA: Low-Rank Adaptation of Large Language Models.
When Do Diffusion Models learn to Generate Multiple Objects? LoRA: Low-Rank Adaptation of Large Language Models
Reference 9
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T08:15:32.081490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d448f3cf-0a0c-4062-9664-74a23b754d86 · outbound
This paper cites Diffusion classifiers understand compositionality, but conditions apply.arXiv preprint arXiv:2505.17955, 2.
When Do Diffusion Models learn to Generate Multiple Objects? Diffusion classifiers understand compositionality, but conditions apply.arXiv preprint arXiv:2505.17955, 2
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.937551Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e8c71984-eb6f-44cb-a05f-c39d13411e80 · outbound
This paper cites An analytic theory of creativity in convolutional diffusion models.
When Do Diffusion Models learn to Generate Multiple Objects? An analytic theory of creativity in convolutional diffusion models
Reference 11
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:32.086639Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 84e90ae3-1ffc-4cf1-a269-c3c47ac644eb · outbound
This paper cites How Far is Video Generation from World Model: A Physical Law Perspective.
When Do Diffusion Models learn to Generate Multiple Objects? How Far is Video Generation from World Model: A Physical Law Perspective
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.091023Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 913c2c90-8bb3-4302-9963-933f3b884305 · outbound
This paper cites Rare text semantics were always there in your diffusion transformer.
When Do Diffusion Models learn to Generate Multiple Objects? Rare text semantics were always there in your diffusion transformer
Reference 13
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.996271Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 62d3eece-3623-4956-b62a-7d93620037e4 · outbound
This paper cites Auto-Encoding Variational Bayes.
When Do Diffusion Models learn to Generate Multiple Objects? Auto-Encoding Variational Bayes
Reference 14
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.037344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6bb9b5f4-139c-42d6-9c5b-ef066bd4aa2f · outbound
This paper cites Decoupled Weight Decay Regularization.
When Do Diffusion Models learn to Generate Multiple Objects? Decoupled Weight Decay Regularization
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.021693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b3a92b61-f631-4562-b38d-ef152a27f9a4 · outbound
This paper cites Representation Learning with Contrastive Predictive Coding.
When Do Diffusion Models learn to Generate Multiple Objects? Representation Learning with Contrastive Predictive Coding
Reference 16
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:31.981493Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 97dca175-feeb-44ca-88e3-6ad8d3f18e11 · outbound
This paper cites An Introduction to Convolutional Neural Networks.
When Do Diffusion Models learn to Generate Multiple Objects? An Introduction to Convolutional Neural Networks
Reference 17
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.000660Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 0a9f729a-3eca-44f0-b97d-1e75a389b2a6 · outbound
This paper cites Memorization to generalization: Emergence of diffusion models from associative memory.
When Do Diffusion Models learn to Generate Multiple Objects? Memorization to generalization: Emergence of diffusion models from associative memory
Reference 18
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T08:15:31.987242Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 2ef24aa6-5801-4580-842a-bbcc3f3218f9 · outbound
This paper cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis.
When Do Diffusion Models learn to Generate Multiple Objects? SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T08:15:32.012424Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d96b27bc-341a-4d7e-b0e7-cb86e1ba26ad · outbound
This paper cites Spatial Reasoners for Continuous Variables in Any Domain.
When Do Diffusion Models learn to Generate Multiple Objects? Spatial Reasoners for Continuous Variables in Any Domain
Reference 20
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:32.030894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 801ebdc8-e2a3-4fc2-a4fa-3fc5ca2f8c6f · outbound
This paper cites U-net: Con- volutional networks for biomedical image segmenta- tion.
When Do Diffusion Models learn to Generate Multiple Objects? U-net: Con- volutional networks for biomedical image segmenta- tion
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.146633Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 841e1b10-d082-40dd-a4d8-807f22d120c0 · outbound
This paper cites Score-Based Generative Modeling through Stochastic Differential Equations.
When Do Diffusion Models learn to Generate Multiple Objects? Score-Based Generative Modeling through Stochastic Differential Equations
Reference 22
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T08:15:31.960621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b9247553-0596-4f37-a64c-4f2baaa40b4d · outbound
This paper cites Qwen3 Technical Report.
When Do Diffusion Models learn to Generate Multiple Objects? Qwen3 Technical Report
Reference 23
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T08:15:31.991490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e2a43987-5922-4288-bdc8-f45caad6ffad · outbound
This paper cites Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines.
When Do Diffusion Models learn to Generate Multiple Objects? Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines
Reference 24
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:32.095589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 3678f4b4-059d-4ba0-91a3-cc29fb50c806 · outbound
This paper cites Does Data Scaling Lead to Visual Compositional Generalization?.
When Do Diffusion Models learn to Generate Multiple Objects? Does Data Scaling Lead to Visual Compositional Generalization?
Reference 25
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.950637Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 6a3550e8-58dd-45a9-8e05-392315479139 · outbound
This paper cites Spatial Reasoning with Denoising Models.
When Do Diffusion Models learn to Generate Multiple Objects? Spatial Reasoning with Denoising Models
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.955771Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation cd027f51-8c1e-4cef-988d-a3d0db6747ca · outbound
This paper cites Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks.
When Do Diffusion Models learn to Generate Multiple Objects? Pretraining Frequency Predicts Compositional Generalization of CLIP on Real-World Tasks
Reference 27
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.928425Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 11477df5-e65c-4e22-9cd9-86acdd606f1b · outbound
This paper cites OmniGen: Unified Image Generation.
When Do Diffusion Models learn to Generate Multiple Objects? OmniGen: Unified Image Generation
Reference 28
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.941960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 5e5983b5-3dbc-4479-9b3e-56b8e2a0365e · outbound
This paper cites 1.58-bit FLUX.
When Do Diffusion Models learn to Generate Multiple Objects? 1.58-bit FLUX
Reference 29
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:31.933006Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation c9abb6af-23de-4bc7-9c52-8f506d4a8604 · outbound
This paper cites Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities.
When Do Diffusion Models learn to Generate Multiple Objects? Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities
Reference 30
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-07-01T08:15:31.946430Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9efa2850-67bc-45ff-9c1c-c72c7f2c4866 · outbound
This paper cites 1” or “one.
When Do Diffusion Models learn to Generate Multiple Objects? 1” or “one
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.160544Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 9a691c44-6259-4290-95ae-67b025cd0426 · outbound
This paper cites Prompt:Find number words (one, two, three, four, five, six, seven, eight, nine, ten) that appear next to or very close to nouns describing countable physical things of any size.
When Do Diffusion Models learn to Generate Multiple Objects? Prompt:Find number words (one, two, three, four, five, six, seven, eight, nine, ten) that appear next to or very close to nouns describing countable physical things of any size
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.158689Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 182c46ce-a5c8-4ce5-b35a-8afd292e640d · outbound
This paper cites Following their object list, we uniformly generate 830 prompts for each target count.
When Do Diffusion Models learn to Generate Multiple Objects? Following their object list, we uniformly generate 830 prompts for each target count
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.142589Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation d8706b16-6f34-41b7-b5f5-b7827695918a · outbound
This paper cites in front of.
When Do Diffusion Models learn to Generate Multiple Objects? in front of
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.156141Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 137c67bb-adf5-426d-bea0-fb650981d81e · outbound
This paper cites For example, in a 100k dataset, theskeweddistribution allocates (22,550, 17,950, 14,350, 11,450, 9,150, 7,300, 5,850, 4,650, 3,750, 3,000) samples across the ten classes.
When Do Diffusion Models learn to Generate Multiple Objects? For example, in a 100k dataset, theskeweddistribution allocates (22,550, 17,950, 14,350, 11,450, 9,150, 7,300, 5,850, 4,650, 3,750, 3,000) samples across the ten classes
Reference 35
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.154298Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 700d328d-8a7c-4516-ac9d-61f5247317f5 · outbound
This paper cites an unresolved cited work.
When Do Diffusion Models learn to Generate Multiple Objects? Unresolved cited work
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-07-01T08:15:32.100066Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation bbd22f74-d2c5-410e-97ec-b9e66e709bd1 · outbound
This paper cites We adopt the DiT architecture from SD3 (Esser et al.,.
When Do Diffusion Models learn to Generate Multiple Objects? We adopt the DiT architecture from SD3 (Esser et al.,
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.163105Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation 8414e094-dd20-433f-a152-31f0aaeef6c2 · outbound
This paper cites To ensure comparable image quality across architectures, we fix the V AE to the one used in SD2, which is also used for all UNet-based experiments in this work.
When Do Diffusion Models learn to Generate Multiple Objects? To ensure comparable image quality across architectures, we fix the V AE to the one used in SD2, which is also used for all UNet-based experiments in this work
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.140744Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation ec8ab48c-3137-4e1b-986b-6f2db6076df9 · outbound
This paper cites an unresolved cited work.
When Do Diffusion Models learn to Generate Multiple Objects? Unresolved cited work
Reference 39
- Resolution
- unresolved
- raw_fallback, observed 2026-07-06T13:32:34.144204Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation e99f01ea-45f9-41d6-9439-3a74ced19d81 · outbound
This paper cites We also evaluate a frozen condition encoder (red) that is pretrained with cross-entropy loss and not jointly optimized with the diffusion model.
When Do Diffusion Models learn to Generate Multiple Objects? We also evaluate a frozen condition encoder (red) that is pretrained with cross-entropy loss and not jointly optimized with the diffusion model
Reference 40
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.150687Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation b4e47176-c889-4877-8fe8-7caddfec2b7c · outbound
This paper cites an unresolved cited work.
When Do Diffusion Models learn to Generate Multiple Objects? Unresolved cited work
Reference 41
- Resolution
- unresolved
- raw_fallback, observed 2026-07-06T13:32:34.152445Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Observation a875b08c-258b-465a-9c01-22c37e53e544 · outbound
This paper cites 26 When Do Diffusion Models learn to Generate Multiple Objects? A.3.2.
When Do Diffusion Models learn to Generate Multiple Objects? 26 When Do Diffusion Models learn to Generate Multiple Objects? A.3.2
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-07-06T13:32:34.138775Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.
Pith citing papers
No inbound Pith citation observations are available.