Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion | Paper Citation Record

Observation 91f153a5-8045-4133-b3aa-ee83675e5305 · outbound

This paper cites Blended diffusion for text-driven editing of natural images.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Blended diffusion for text-driven editing of natural images

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:15:00.832237Z

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 cfaec9be-ac44-4d80-b2ff-1bec1a79e8d8 · outbound

This paper cites eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:45.731108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d295b597-6b91-4490-8afa-1e9c8dc1f0ea · outbound

This paper cites Multimodal garment designer: Human-centric latent diffusion models for fashion image editing.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Multimodal garment designer: Human-centric latent diffusion models for fashion image editing

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:15:00.686806Z

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 6289ad92-d421-4a6a-b98f-a6c758cb26fc · outbound

This paper cites Text2live: Text-driven layered image and video editing.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Text2live: Text-driven layered image and video editing

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:15:00.452555Z

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 a3f358c2-b535-4d28-b8b0-6b5eea127ce5 · outbound

This paper cites In- structpix2pix: Learning to follow image editing instructions.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion In- structpix2pix: Learning to follow image editing instructions

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:46.034524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6896941-d1f3-4312-a371-d24c8911b994 · outbound

This paper cites A Survey on Mixture of Experts in Large Language Models.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion A Survey on Mixture of Experts in Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:46.169244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2568ddde-47cc-48ee-b1f2-06cb6513e3a8 · outbound

This paper cites Decoupled textual embeddings for cus- tomized image generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Decoupled textual embeddings for cus- tomized image generation

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:15:00.256175Z

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 6760e80c-ec47-4da6-bf95-6dc42728e98b · outbound

This paper cites Disenbooth: Identity- preserving disentangled tuning for subject-driven text-to- image generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Disenbooth: Identity- preserving disentangled tuning for subject-driven text-to- image generation

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:15:00.086135Z

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 a486bef7-b04b-4cf4-b483-7c65298f1a12 · outbound

This paper cites Towards aligned layout generation via diffusion model with aesthetic constraints.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Towards aligned layout generation via diffusion model with aesthetic constraints

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:59.932175Z

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 d8c9d8b7-7bcc-41cb-9851-e5ce35be6257 · outbound

This paper cites Anydoor: Zero-shot object-level im- age customization.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Anydoor: Zero-shot object-level im- age customization

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:59.756195Z

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 0b57095c-eba2-4f69-93e5-f6b831194511 · outbound

This paper cites Diffu- sion models beat gans on image synthesis.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Diffu- sion models beat gans on image synthesis

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:59.588725Z

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 d61d9400-97ae-4b27-aa54-fae79a5fcf75 · outbound

This paper cites Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fe- dus, Maarten P.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Dai, Simon Tong, Dmitry Lepikhin, Yuanzhong Xu, Maxim Krikun, Yanqi Zhou, Adams Wei Yu, Orhan Firat, Barret Zoph, Liam Fe- dus, Maarten P

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:59.434058Z

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 fc8939df-58a5-4bce-81ae-25eb1c3edb83 · outbound

This paper cites Learning factored representations in a deep mixture of ex- perts.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Learning factored representations in a deep mixture of ex- perts

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:59.278240Z

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 81a3ff12-6790-469e-b853-9d85b4b38903 · outbound

This paper cites Scaling recti- fied flow transformers for high-resolution image synthesis.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Scaling recti- fied flow transformers for high-resolution image synthesis

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:47.076520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a6de1e-2908-4ae9-99fd-c2717485da75 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with sim- ple and efficient sparsity.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Switch transformers: Scaling to trillion parameter models with sim- ple and efficient sparsity

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:59.083709Z

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 3378e527-43c9-4f0e-8e60-eb56c58b947c · outbound

This paper cites An image is worth one word: Personalizing text-to-image generation using textual inversion.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion An image is worth one word: Personalizing text-to-image generation using textual inversion

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:58.838260Z

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 23d1482e-8114-4d85-a2e4-8ad3b9a64c97 · outbound

This paper cites Generative adversarial networks.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Generative adversarial networks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:47.359836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ee30907-a957-4a41-856a-01f6c73c026a · outbound

This paper cites Svdiff: Compact param- eter space for diffusion fine-tuning.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Svdiff: Compact param- eter space for diffusion fine-tuning

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:58.607425Z

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 27cdb942-70aa-41bd-b7fa-2cfdb0bcbc15 · outbound

This paper cites Fastermoe: modeling and optimizing training of large-scale dynamic pre-trained mod- els.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Fastermoe: modeling and optimizing training of large-scale dynamic pre-trained mod- els

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:58.398674Z

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 6d3c1e6e-b379-4370-8240-7b33af9e986d · outbound

This paper cites AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:47.572921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2040f434-9a46-44e6-8ff4-fc22deb57afe · outbound

This paper cites Denoising dif- fusion probabilistic models.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Denoising dif- fusion probabilistic models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:47.639845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b4679e4-11b2-42de-b810-7a294fbb74b2 · outbound

This paper cites Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:58.178344Z

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 15485768-7d66-4dc6-bdc5-576bd4787f7d · outbound

This paper cites DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion DiffuMatting: Synthesizing Arbitrary Objects with Matting-level Annotation

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:14:53.453172Z

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 f412bfe7-a6d3-4d2f-9b41-a2465d543ebe · outbound

This paper cites ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:47.905023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 856ba131-bf8f-4a55-9ef1-0d19c9e446b4 · outbound

This paper cites Adaptive mixtures of local experts.Neu- ral computation, 3(1):79–87, 1991.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Adaptive mixtures of local experts.Neu- ral computation, 3(1):79–87, 1991

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:47.988552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33e8dc0f-fd59-4efe-92fd-76846f63f79b · outbound

This paper cites Stableviton: Learning semantic correspon- dence with latent diffusion model for virtual try-on.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Stableviton: Learning semantic correspon- dence with latent diffusion model for virtual try-on

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:48.059792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25d4a27c-6c70-4739-bafa-77e5eb022a65 · outbound

This paper cites Stylemc: Multi-channel based fast text-guided im- age generation and manipulation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Stylemc: Multi-channel based fast text-guided im- age generation and manipulation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:57.987237Z

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 c5a40d3c-e0dd-471b-8296-cb4962d30ff5 · outbound

This paper cites CustAny: Customizing Anything from A Single Example.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion CustAny: Customizing Anything from A Single Example

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:48.317554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42907d6f-9077-42ca-b06a-48fa9649c10a · outbound

This paper cites Omg: Occlusion-friendly personalized multi-concept generation in diffusion models.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Omg: Occlusion-friendly personalized multi-concept generation in diffusion models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:57.814046Z

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 aa0ad955-d3f0-4407-9cea-9de3f6f298c6 · outbound

This paper cites Multi-concept customiza- tion of text-to-image diffusion.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Multi-concept customiza- tion of text-to-image diffusion

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:57.514572Z

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 5ea52d0e-f476-4da6-bd43-1c1498d0d9da · outbound

This paper cites Generating multi-image synthetic data for text-to-image customization.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Generating multi-image synthetic data for text-to-image customization

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:48.534763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89136eb0-9974-43b8-a507-a0a4289ed19c · outbound

This paper cites Gshard: Scaling giant models with conditional computation and automatic sharding.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Gshard: Scaling giant models with conditional computation and automatic sharding

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:57.259459Z

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 5eefbc42-99fd-4700-afe1-1aabdf690ba2 · outbound

This paper cites Blip-diffusion: Pre- trained subject representation for controllable text-to-image generation and editing.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Blip-diffusion: Pre- trained subject representation for controllable text-to-image generation and editing

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:48.666099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 522e9416-de3b-4318-b745-2774a2314b36 · outbound

This paper cites Subject- diffusion: Open domain personalized text-to-image genera- tion without test-time fine-tuning.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Subject- diffusion: Open domain personalized text-to-image genera- tion without test-time fine-tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:48.732672Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb41754-12d7-4aef-8ba5-c711cffc7dc8 · outbound

This paper cites Ladi-vton: Latent diffusion textual-inversion enhanced virtual try-on.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Ladi-vton: Latent diffusion textual-inversion enhanced virtual try-on

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:57.014951Z

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 d4250a06-efb1-48c5-a1ce-3fd4e0fae72b · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:48.914829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 301595a6-a236-47c3-b730-7d2c28c72f1e · outbound

This paper cites an unresolved cited work.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-07T13:14:56.810240Z

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 bb325955-1f02-43a1-8b64-82f3b4941485 · outbound

This paper cites Attndreambooth: To- wards text-aligned personalized text-to-image generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Attndreambooth: To- wards text-aligned personalized text-to-image generation

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:56.556845Z

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 48a4a79c-75a2-471a-b343-a5467a518b84 · outbound

This paper cites TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion TextBoost: Boosting Text Encoder for Personalized Text-to-Image Generation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:49.189713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f68c1134-8934-406f-9587-711919b491ed · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Styleclip: Text-driven manipulation of stylegan imagery

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:49.285012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fc49497-ac4d-4668-b69e-14f29d276d0f · outbound

This paper cites Scalable diffusion models with transformers.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Scalable diffusion models with transformers

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:49.361226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14b2a9c-8fcc-46c2-83a4-b69f4e98c481 · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:49.472916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 496d7f47-bba0-44be-a6d1-3c2d834748a3 · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Learning transferable visual models from natural language supervision

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:49.582131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e6be9b4-a0db-4d88-8467-4e073360681d · outbound

This paper cites Dreamblend: Advancing person- 10 alized fine-tuning of text-to-image diffusion models.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Dreamblend: Advancing person- 10 alized fine-tuning of text-to-image diffusion models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:56.275935Z

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 ccaa6263-ed81-4a7b-89a3-90ed4eeda8d3 · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Hierarchical Text-Conditional Image Generation with CLIP Latents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:49.810378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f536b44d-8477-4030-b0b4-accedbdf82fe · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion High-resolution image syn- thesis with latent diffusion models

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:56.049974Z

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 2493ce32-ebb7-4262-ba98-5bfca5e8f35d · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:50.231088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b825b96-e864-416f-9738-b0f770be4b24 · outbound

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

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Photorealistic text-to-image diffusion models with deep language understanding

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:50.301139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff0c62ba-2a03-4b7e-b81d-1070661ec529 · outbound

This paper cites Visual layout composer: Image-vector dual diffusion model for de- sign layout generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Visual layout composer: Image-vector dual diffusion model for de- sign layout generation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:55.819288Z

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 b00c52de-f573-484e-ac97-7dd0ca65d64a · outbound

This paper cites Ziplora: Any subject in any style by effectively merging loras.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Ziplora: Any subject in any style by effectively merging loras

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:55.623200Z

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 c6005e95-d8e6-42b2-a47f-39ad402decf3 · outbound

This paper cites Le, Geoffrey E.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Le, Geoffrey E

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:55.491682Z

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 9175290a-c651-4c57-9009-325622cf9e1d · outbound

This paper cites Scaling vision-language models with sparse mixture of experts.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Scaling vision-language models with sparse mixture of experts

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:55.209712Z

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 3046fb00-df50-404f-ae31-8802db3d5df9 · outbound

This paper cites Zhao, Hongkun Yu, Kurt Keutzer, Trevor Darrell, and Denny Zhou.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Zhao, Hongkun Yu, Kurt Keutzer, Trevor Darrell, and Denny Zhou

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:54.956851Z

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 c8278f25-3567-443b-a47b-26c76904f3ed · outbound

This paper cites In- stantbooth: Personalized text-to-image generation without test-time finetuning.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion In- stantbooth: Personalized text-to-image generation without test-time finetuning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:50.973970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dee78fcd-56ae-4ef3-8076-e7516770b811 · outbound

This paper cites DreamRelation: Bridging Customization and Relation Generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion DreamRelation: Bridging Customization and Relation Generation

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:51.087857Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c043180-7b38-4167-bc84-088069cf6ba1 · outbound

This paper cites Moma: Multimodal llm adapter for fast personalized image generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Moma: Multimodal llm adapter for fast personalized image generation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:54.742823Z

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 e080e8f9-0206-4919-9388-9fa4c7ba9e4e · outbound

This paper cites Resolution-robust large mask inpainting with fourier convolutions.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Resolution-robust large mask inpainting with fourier convolutions

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:51.413086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71e755bb-cf1e-4ebc-94ee-3e54b1d5fae9 · outbound

This paper cites InstantID: Zero-shot Identity-Preserving Generation in Seconds.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion InstantID: Zero-shot Identity-Preserving Generation in Seconds

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:51.539668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 450ed4af-5e58-40fc-8b51-702408054b51 · outbound

This paper cites MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:51.605547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 401e7903-bfb7-4b17-8621-b140dc64ab2c · outbound

This paper cites Dolfin: Diffusion layout transformers without autoencoder.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Dolfin: Diffusion layout transformers without autoencoder

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:54.498330Z

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 ec456f7c-0d71-41a5-b0c9-79103be2e37d · outbound

This paper cites GroundingBooth: Grounding Text-to-Image Customization.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion GroundingBooth: Grounding Text-to-Image Customization

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:51.859590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56931266-a238-4597-afa2-c37ee332064f · outbound

This paper cites Predict, prevent, and evaluate: Disentangled text-driven im- age manipulation empowered by pre-trained vision-language model.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Predict, prevent, and evaluate: Disentangled text-driven im- age manipulation empowered by pre-trained vision-language model

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:54.316082Z

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 ac8e711b-6d80-4a30-ad05-d5ca9c78687b · outbound

This paper cites Dreammix: Decoupling object attributes for enhanced ed- itability in customized image inpainting.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Dreammix: Decoupling object attributes for enhanced ed- itability in customized image inpainting

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:52.023601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d9edf0c-8042-454f-b031-cd2c2c579d7d · outbound

This paper cites IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:52.135812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bf683d3-39ef-42c1-b306-20f03ac1fd9a · outbound

This paper cites Inpaint Anything: Segment Anything Meets Image Inpainting.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Inpaint Anything: Segment Anything Meets Image Inpainting

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:52.264580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4de2f01a-4c0d-44a9-be6f-095465dff920 · outbound

This paper cites Cat-dm: Controllable acceler- ated virtual try-on with diffusion model.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Cat-dm: Controllable acceler- ated virtual try-on with diffusion model

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:54.066232Z

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 c871684d-cfe4-4b77-a4ff-5a12c285483c · outbound

This paper cites Ssr-encoder: Encoding selective subject representation for subject-driven generation.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Ssr-encoder: Encoding selective subject representation for subject-driven generation

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:53.906203Z

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 8123a8b4-4763-4429-8454-e25a6fc166b3 · outbound

This paper cites Efficientvit-sam: Accelerated segment anything model without performance loss.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion Efficientvit-sam: Accelerated segment anything model without performance loss

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T13:14:53.719288Z

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 1dd107db-fb9d-4a60-b1f8-a8bf233e242e · outbound

This paper cites MultiBooth: Towards Generating All Your Concepts in an Image from Text.

Identity-Preserving Text-to-Image Generation via Dual-Level Feature Decoupling and Expert-Guided Fusion MultiBooth: Towards Generating All Your Concepts in an Image from Text

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T13:14:52.788211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers