SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation | Paper Citation Record

Observation cea0948c-e204-4389-98f3-0ab474309b98 · outbound

This paper cites A general theoretical paradigm to un- derstand learning from human preferences.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation A general theoretical paradigm to un- derstand learning from human preferences

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.425670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87972546-4366-430f-99ce-a603d9a9cab7 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.432116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2308b4-26cd-4692-a7b1-0ab937bf4918 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Constitutional AI: Harmlessness from AI Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.438022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c51e86d-9037-43a5-b399-b44baeeca17f · outbound

This paper cites Improving image generation with better captions.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Improving image generation with better captions

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.444537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9df390e6-4d00-4133-b67d-81db4ee16d9b · outbound

This paper cites Training diffusion models with reinforce- ment learning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Training diffusion models with reinforce- ment learning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.450209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e42c48-eed0-4469-9c66-9a18b80a00d9 · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Attend-and-excite: Attention-based se- mantic guidance for text-to-image diffusion models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.456093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83a1fc6-8c7b-4ed9-bc02-a5b7bcb64cef · outbound

This paper cites Spatialvlm: Endow- ing vision-language models with spatial reasoning capabili- ties.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Spatialvlm: Endow- ing vision-language models with spatial reasoning capabili- ties

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.461932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8d922ed-9047-4648-8215-7797aa739e7b · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.467979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b939c50c-136c-4707-bb3e-2aceab3c850a · outbound

This paper cites Multimodal dialog systems with dual knowledge-enhanced generative pretrained language model.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Multimodal dialog systems with dual knowledge-enhanced generative pretrained language model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.474582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c756234-837b-4fc9-ae05-f335eea6c755 · outbound

This paper cites Ultrafeedback: Boosting language mod- els with scaled ai feedback.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Ultrafeedback: Boosting language mod- els with scaled ai feedback

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.479995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2b9dcb9-7d2e-47b7-aea4-1fbbb6f6809e · outbound

This paper cites How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Composition

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.485181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 570ae0a7-16f7-49e8-a123-ccc5b30618cc · outbound

This paper cites A Survey on In-context Learning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation A Survey on In-context Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.490817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86bce015-8c03-4ab8-bc54-ea9998cb64d2 · outbound

This paper cites Dreamllm: Synergistic multimodal com- prehension and creation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Dreamllm: Synergistic multimodal com- prehension and creation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.320857Z

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 0e54758c-4964-4bd5-a531-493f70c7c7a9 · outbound

This paper cites The Llama 3 Herd of Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.501287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6f0ada-8bab-4cb2-a5b4-672a6c967600 · outbound

This paper cites Re- inforcement learning for fine-tuning text-to-image diffusion models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Re- inforcement learning for fine-tuning text-to-image diffusion models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.301343Z

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 8ac07f17-bf7b-44c3-b003-1f728254dd55 · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Training- free structured diffusion guidance for compositional text-to- image synthesis

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.281347Z

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 32ed574c-a15e-4127-b44e-fb49d7ed90a8 · outbound

This paper cites LayoutGPT: Compositional Visual Planning and Generation with Large Language Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.516822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1380e6d-aa3c-4550-8c78-1ec7694fda77 · outbound

This paper cites Dropout as a bayesian approximation: Representing model uncertainty in deep learning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Dropout as a bayesian approximation: Representing model uncertainty in deep learning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.262716Z

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 76b2b88d-6473-4fb6-9d22-063fcbf954f3 · outbound

This paper cites Making llama see and draw with seed tokenizer.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Making llama see and draw with seed tokenizer

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.242557Z

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 43f55e14-52cb-43d9-87de-c429d821c81b · outbound

This paper cites SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.534962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02dd1084-32f7-4518-8fcb-7253bb27af22 · outbound

This paper cites Pela: Learning parameter-efficient models with low-rank ap- proximation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Pela: Learning parameter-efficient models with low-rank ap- proximation

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.222788Z

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 37d22593-872a-4da7-a0e7-fa0b0031ee45 · outbound

This paper cites Hearst, Susan T Dumais, Edgar Osuna, John Platt, and Bernhard Scholkopf.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Hearst, Susan T Dumais, Edgar Osuna, John Platt, and Bernhard Scholkopf

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.202807Z

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 b6104bc7-3929-4b4f-b642-bbec0342d082 · outbound

This paper cites Clipscore: A reference-free evaluation met- ric for image captioning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Clipscore: A reference-free evaluation met- ric for image captioning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.552087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef7b8ac8-23ab-45b7-8521-232b896f4edf · outbound

This paper cites spaCy: Industrial-strength Natural Lan- guage Processing in Python.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation spaCy: Industrial-strength Natural Lan- guage Processing in Python

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.162098Z

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 ca859cb2-f157-4de5-a242-4b22b7b76119 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation LoRA: Low-Rank Adaptation of Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.563093Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ad3bfda-995a-42fd-8007-f4b48db7f005 · outbound

This paper cites ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.569982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c13b01b-5833-48ac-aca2-b64f90424c1c · outbound

This paper cites Tifa: Accu- rate and interpretable text-to-image faithfulness evaluation with question answering.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Tifa: Accu- rate and interpretable text-to-image faithfulness evaluation with question answering

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.140222Z

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 ba8b844a-14c1-4197-9215-addeb8761065 · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation T2i-compbench: A comprehensive bench- mark for open-world compositional text-to-image genera- tion

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.109749Z

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 89755587-7531-4663-8ead-3d3171a34ae1 · outbound

This paper cites Sequence tutor: Conservative fine-tuning of sequence generation models with kl-control.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Sequence tutor: Conservative fine-tuning of sequence generation models with kl-control

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.085843Z

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 be89228f-fb0b-45fc-b0d1-a2e725cbf520 · outbound

This paper cites Human-centric Dialog Training via Offline Reinforcement Learning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Human-centric Dialog Training via Offline Reinforcement Learning

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.589831Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8dac8bf-9d68-40f7-9015-351ea247033e · outbound

This paper cites Pick-a-pic: An open dataset of user preferences for text-to-image generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Pick-a-pic: An open dataset of user preferences for text-to-image generation

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.059195Z

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 408d493a-9ba9-43af-bed1-d49fb29ef99a · outbound

This paper cites Rlaif vs.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Rlaif vs

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.039698Z

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 2bfce24b-305f-4c3b-914c-5e927ee7b661 · outbound

This paper cites Aligning Text-to-Image Models using Human Feedback.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Aligning Text-to-Image Models using Human Feedback

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.606432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35d94c09-4032-4761-942c-a42bd99ed973 · outbound

This paper cites Invariant grounding for video question answering.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Invariant grounding for video question answering

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:17.017086Z

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 5228c811-4ab1-4013-a631-82f86b8ad6aa · outbound

This paper cites Transformer-empowered invariant grounding for video question answering.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Transformer-empowered invariant grounding for video question answering

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.997434Z

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 70999c1c-a7c6-4b16-b553-49a1a8147b13 · outbound

This paper cites Attribute-driven disentangled representation learning for multimodal recommendation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Attribute-driven disentangled representation learning for multimodal recommendation

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.975428Z

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 e06eca76-f3a3-42bc-ad0c-6911f2a7fef2 · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.780369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 320e6226-04a0-46c8-b2f5-c38b42ce22c9 · outbound

This paper cites Llm-grounded video diffusion models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Llm-grounded video diffusion models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.952412Z

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 0e70dd17-b9c3-4039-93f3-576100664f06 · outbound

This paper cites Visual Instruction Tuning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Visual Instruction Tuning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.791940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd9190e3-a68e-4306-8cb9-74b5bb6d8b48 · outbound

This paper cites Ipo: Interior-point policy optimization under constraints.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Ipo: Interior-point policy optimization under constraints

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.931447Z

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 ae637458-13c3-4aad-809b-7d8353dda7f6 · outbound

This paper cites Cheap and quick: Efficient vision- language instruction tuning for large language models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Cheap and quick: Efficient vision- language instruction tuning for large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.906814Z

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 de3e33b1-a0d0-4d4b-a91b-a0e450e21476 · outbound

This paper cites Compositional chain-of-thought prompting for large multimodal models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Compositional chain-of-thought prompting for large multimodal models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.880847Z

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 7c854fc5-b474-4022-902e-04a7e97c823c · outbound

This paper cites Training language models to follow instructions with human feedback.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Training language models to follow instructions with human feedback

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.857710Z

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 c90f62e0-ffb5-49f2-ad00-1f67506be9ac · outbound

This paper cites Lan- guage model self-improvement by reinforcement learning contemplation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Lan- guage model self-improvement by reinforcement learning contemplation

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.830206Z

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 a10cdbb2-3f62-43ad-b1a6-358bb7a8d34e · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.828251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b8f96f5-f778-4f94-a4aa-efc8f256dfda · outbound

This paper cites Diffusiongpt: Llm-driven text-to-image generation system.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Diffusiongpt: Llm-driven text-to-image generation system

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.835904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c91c364-838c-42e7-9248-30a6077d8814 · outbound

This paper cites 3d-immc: Incomplete multi-modal 3d shape clustering via cross mapping and dual adaptive fu- sion.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation 3d-immc: Incomplete multi-modal 3d shape clustering via cross mapping and dual adaptive fu- sion

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.801841Z

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 cc049737-d86c-4483-beab-17e02817bdc0 · outbound

This paper cites Dynamic modality interaction modeling for image-text retrieval.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Dynamic modality interaction modeling for image-text retrieval

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.780318Z

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 d33920c6-87e8-4169-a282-5973f0c44eae · outbound

This paper cites Layoutllm-t2i: Eliciting layout guidance from llm for text-to-image generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Layoutllm-t2i: Eliciting layout guidance from llm for text-to-image generation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.755881Z

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 887a7e9c-0f78-47e2-85d2-337131800f72 · outbound

This paper cites TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.862417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84421468-b731-4c91-a58d-75318e869631 · outbound

This paper cites Discriminative probing and tuning for text-to-image generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Discriminative probing and tuning for text-to-image generation

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.716643Z

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 9eecad53-b581-4051-a8a3-f31dffde9fcd · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Learning transferable visual models from natural language supervi- sion

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.876127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c18a1184-669e-414b-a192-a2b12e67b21d · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Direct preference optimization: Your language model is secretly a reward model

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.676752Z

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 35a3e8a0-81de-42ef-8dbe-c9c8a2588edd · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Exploring the limits of transfer learning with a unified text-to-text transformer

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.888536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f48b242-ce8c-4d77-b59a-fc39a8394717 · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.895419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9bda355-e586-4b4a-81a4-b96b7f080455 · outbound

This paper cites Can generative multimodal models count to ten? In Proceedings of the Annual Meeting of the Cognitive Science Society, 2024.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Can generative multimodal models count to ten? In Proceedings of the Annual Meeting of the Cognitive Science Society, 2024

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.641581Z

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 539b5c37-2b5b-44a7-ae54-0c49d9ba829e · outbound

This paper cites Photorealistic text-to-image diffusion models with deep language understanding.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Photorealistic text-to-image diffusion models with deep language understanding

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.908071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7c48f5c-b5ff-4968-b58b-94b54d96ec4b · outbound

This paper cites Proximal Policy Optimization Algorithms.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Proximal Policy Optimization Algorithms

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.916590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4fc7d2c-1932-49f0-a8fc-d4745571505c · outbound

This paper cites Llava-prumerge: Adaptive token reduction for efficient large multimodal models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Llava-prumerge: Adaptive token reduction for efficient large multimodal models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.925715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e42345c-659a-491c-86d0-5f8356bd7620 · outbound

This paper cites Kernel methods for pattern analysis.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Kernel methods for pattern analysis

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.602990Z

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 fb1c32aa-617f-4a1b-bdb7-e33bea58efda · outbound

This paper cites Learning to summarize with human feed- back.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Learning to summarize with human feed- back

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.574025Z

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 6db52ec4-4bc8-4b8d-9d1b-80ca89fab095 · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.948321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a2f98ab-2a47-461a-af6e-df5fc9dad34f · outbound

This paper cites Emu: Generative pretraining in multimodality.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Emu: Generative pretraining in multimodality

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.550116Z

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 4a06d198-7078-4c46-90fa-f3e6db573399 · outbound

This paper cites Generative multimodal mod- els are in-context learners.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Generative multimodal mod- els are in-context learners

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.525803Z

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 da1636db-9755-48d1-b737-1fc8490a3eba · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation LLaMA: Open and Efficient Foundation Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.965603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27cde872-daf7-4a47-8a95-a8ecee165677 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.972615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e784b1d0-b4e5-4819-a765-59301aadd65e · outbound

This paper cites Diffusion model align- ment using direct preference optimization.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Diffusion model align- ment using direct preference optimization

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.476027Z

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 7f86175a-2f06-488b-af03-f0d5a78f6480 · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Emu3: Next-Token Prediction is All You Need

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.984003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 386c3901-3ef0-45c6-8a8e-f23fb05974a4 · outbound

This paper cites RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation RL-VLM-F: Reinforcement Learning from Vision Language Foundation Model Feedback

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.989517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23e8be3f-bce4-4c19-8a68-135c0d0f84dd · outbound

This paper cites Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:14.995830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4379731-fbbd-4494-8e0f-4dcbafa00c41 · outbound

This paper cites Comprehensive linguistic-visual composition network for image retrieval.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Comprehensive linguistic-visual composition network for image retrieval

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.454831Z

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 8156953c-c6eb-45bc-a587-202660fd0e40 · outbound

This paper cites Next-gpt: Any-to-any multimodal llm.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Next-gpt: Any-to-any multimodal llm

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.430022Z

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 b6b00d45-594d-4e44-aca3-e58920d56492 · outbound

This paper cites Human Preference Score: Better Aligning Text-to-Image Models with Human Preference.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Human Preference Score: Better Aligning Text-to-Image Models with Human Preference

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.012326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 899eeccf-28a4-4e52-9f08-01e9cb958c8c · outbound

This paper cites Show-o: One Single Transformer to Unify Multimodal Understanding and Generation.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.018504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18dcb2bf-e914-4e33-a6a3-57e8434978b2 · outbound

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

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Mastering text-to-image dif- fusion: Recaptioning, planning, and generating with multi- modal llms

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.408048Z

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 187bde08-e143-4317-ac54-438a1d50ef05 · outbound

This paper cites Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.031298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81c91a9c-c72f-4739-b8da-d163f2aba32e · outbound

This paper cites Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Rlaif-v: Aligning mllms through open-source ai feedback for super gpt-4v trustworthiness

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.036973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01a12e6a-dc3f-46e9-aa50-b0f1a6c0d1ca · outbound

This paper cites Self-Rewarding Language Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Self-Rewarding Language Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.043167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce8d0df0-8e3a-43b9-ace0-8fc071093344 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.050001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32ef74f3-9fd0-437e-b0d4-9ec92225f51a · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Fine-Tuning Language Models from Human Preferences

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-11T20:25:15.058528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ffb9301-f40b-4731-beeb-4e9a3fc017c8 · outbound

This paper cites Attributes such as color, shape, texture, and 2D/3D spatial relations are also incorpo- rated.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Attributes such as color, shape, texture, and 2D/3D spatial relations are also incorpo- rated

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.374352Z

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 be913525-b847-4757-8445-144e73a0bfb1 · outbound

This paper cites These atomic concepts are then transformed into simple yes-or-no questions.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation These atomic concepts are then transformed into simple yes-or-no questions

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.347768Z

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 b76f1ddb-96aa-4c1f-9a24-66df37816450 · outbound

This paper cites log σ − ¯σβ 2 LX i=1 ∥hw i − µi∥2 2 − βC + β 2¯σ LX i=1 ∥hw i − µref i ∥2 2 + βC − β 2¯σ LX i=1 ∥hl i − µi∥2 2 − βC + β 2¯σ LX i=1 ∥hl i − µref i ∥2 2 + βC ! # = −E(x,zw ,zl)∼D.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation log σ − ¯σβ 2 LX i=1 ∥hw i − µi∥2 2 − βC + β 2¯σ LX i=1 ∥hw i − µref i ∥2 2 + βC − β 2¯σ LX i=1 ∥hl i − µi∥2 2 − βC + β 2¯σ LX i=1 ∥hl i − µref i ∥2 2 + βC ! # = −E(x,zw ,zl)∼D

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.323140Z

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 ef46e847-313a-4933-8d7b-ac3157509c1f · outbound

This paper cites For SEED-LLaMA, the LLM backbone of DreamLLM is optimized for 1k steps, with a learning rate of 5 × 10−5, 100 warm-up steps, and a cosine learning rate scheduler.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation For SEED-LLaMA, the LLM backbone of DreamLLM is optimized for 1k steps, with a learning rate of 5 × 10−5, 100 warm-up steps, and a cosine learning rate scheduler

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.294856Z

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 b059f2be-e759-4159-b1db-cc5fd264105a · outbound

This paper cites an unresolved cited work.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation Unresolved cited work

Reference 85

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:25:16.274373Z

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 a0e4efb8-59b7-445c-b30c-c3f8d2abb4f5 · outbound

This paper cites First Half.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation First Half

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.254438Z

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 625205fb-3c24-4363-8277-4bc54bb41e6f · outbound

This paper cites 14 - 24” means the rejected data points are sampled from rank-14 to rank-24 which is a hard range, while “20 - 30.

SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation 14 - 24” means the rejected data points are sampled from rank-14 to rank-24 which is a hard range, while “20 - 30

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:25:16.235360Z

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