{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-generation/papers/44","list_of":"/task/image-generation","task":"Image Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":44,"pages_in_order":67,"rows_per_page":100,"rows":[4301,4400],"of":6689,"counts":{"archive_papers_tagged":6689,"with_a_code_link":3102,"where_syntology_ran_a_sample":1223,"not_listed_spam_title":0,"listed":6689,"listed_where_code_ran":1223,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1063,"every_run_a_failure_of_syntologys_instrument":160,"listed_with_a_run_with_no_instrument_failure":1063,"listed_every_run_a_failure_of_syntologys_instrument":160,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-generation","prev":"/task/image-generation/papers/43","next":"/task/image-generation/papers/45","papers":[{"url":null,"slug":"from-principles-to-practices-lessons-learned","title":"From Principles to Practices: Lessons Learned from Applying Partnership on AI's (PAI) Synthetic Media Framework to 11 Use Cases","date":"2024-07-17","arxiv_id":"2407.13025","repositories_listed":0,"syntology":null},{"url":null,"slug":"i2am-interpreting-image-to-image-latent","title":"I2AM: Interpreting Image-to-Image Latent Diffusion Models via Attribution Maps","date":"2024-07-17","arxiv_id":"2407.12331","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-fabrication-of-reality-and-fantasy-scene","title":"The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation","date":"2024-07-17","arxiv_id":"2407.12579","repositories_listed":0,"syntology":null},{"url":null,"slug":"voltage-controlled-magnetoelectric-devices","title":"Voltage-Controlled Magnetoelectric Devices for Neuromorphic Diffusion Process","date":"2024-07-17","arxiv_id":"2407.12261","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-text-guided-infinite-image","title":"Zero-shot Text-guided Infinite Image Synthesis with LLM guidance","date":"2024-07-17","arxiv_id":"2407.12642","repositories_listed":0,"syntology":null},{"url":null,"slug":"beta-sampling-is-all-you-need-efficient-image","title":"Beta Sampling is All You Need: Efficient Image Generation Strategy for Diffusion Models using Stepwise Spectral Analysis","date":"2024-07-16","arxiv_id":"2407.12173","repositories_listed":0,"syntology":null},{"url":null,"slug":"dino-diffusion-scaling-medical-diffusion-via","title":"DiNO-Diffusion. Scaling Medical Diffusion via Self-Supervised Pre-Training","date":"2024-07-16","arxiv_id":"2407.11594","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-training-with-denoised-neural","title":"Efficient Training with Denoised Neural Weights","date":"2024-07-16","arxiv_id":"2407.11966","repositories_listed":0,"syntology":null},{"url":null,"slug":"flatfish-disease-detection-based-on-part","title":"Flatfish Disease Detection Based on Part Segmentation Approach and Disease Image Generation","date":"2024-07-16","arxiv_id":"2407.11348","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-guided-cross-image-attention-for-zero","title":"Mask-guided cross-image attention for zero-shot in-silico histopathologic image generation with a diffusion model","date":"2024-07-16","arxiv_id":"2407.11664","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-adaptation-for-approximate","title":"Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems","date":"2024-07-16","arxiv_id":"2407.11288","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-defenses-against-ai-generated","title":"A Survey of Defenses against AI-generated Visual Media: Detection, Disruption, and Authentication","date":"2024-07-15","arxiv_id":"2407.10575","repositories_listed":0,"syntology":null},{"url":null,"slug":"addressing-image-hallucination-in-text-to","title":"Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval","date":"2024-07-15","arxiv_id":"2407.10683","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-generalization-for-6d-pose-estimation","title":"Domain Generalization for 6D Pose Estimation Through NeRF-based Image Synthesis","date":"2024-07-15","arxiv_id":"2407.10762","repositories_listed":0,"syntology":null},{"url":null,"slug":"opa-ma-text-guided-mamba-for-360-degree-image","title":"OPa-Ma: Text Guided Mamba for 360-degree Image Out-painting","date":"2024-07-15","arxiv_id":"2407.10923","repositories_listed":0,"syntology":null},{"url":null,"slug":"optical-diffusion-models-for-image-generation","title":"Optical Diffusion Models for Image Generation","date":"2024-07-15","arxiv_id":"2407.10897","repositories_listed":0,"syntology":null},{"url":null,"slug":"physics-inspired-generative-models-in-medical","title":"Physics-Inspired Generative Models in Medical Imaging: A Review","date":"2024-07-15","arxiv_id":"2407.10856","repositories_listed":0,"syntology":null},{"url":null,"slug":"layout-and-retouch-a-dual-stage-framework-for","title":"Layout-and-Retouch: A Dual-stage Framework for Improving Diversity in Personalized Image Generation","date":"2024-07-13","arxiv_id":"2407.09779","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairylandai-personalized-fairy-tales","title":"FairyLandAI: Personalized Fairy Tales utilizing ChatGPT and DALLE-3","date":"2024-07-12","arxiv_id":"2407.09467","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-apophenia-the-kaleidoscopic","title":"Machine Apophenia: The Kaleidoscopic Generation of Architectural Images","date":"2024-07-12","arxiv_id":"2407.09172","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgical-text-to-image-generation","title":"Surgical Text-to-Image Generation","date":"2024-07-12","arxiv_id":"2407.09230","repositories_listed":0,"syntology":null},{"url":null,"slug":"e2vidiff-perceptual-events-to-video","title":"E2VIDiff: Perceptual Events-to-Video Reconstruction using Diffusion Priors","date":"2024-07-11","arxiv_id":"2407.08231","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-medical-image-synthesis-via","title":"Boosting Medical Image Synthesis via Registration-guided Consistency and Disentanglement Learning","date":"2024-07-10","arxiv_id":"2407.07660","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-mobile-edge-generation-meg-by","title":"Accelerating Mobile Edge Generation (MEG) by Constrained Learning","date":"2024-07-09","arxiv_id":"2407.07245","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-image-generation-by-conditional","title":"Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion","date":"2024-07-09","arxiv_id":"2407.07249","repositories_listed":0,"syntology":null},{"url":null,"slug":"sketch-guided-scene-image-generation","title":"Sketch-Guided Scene Image Generation","date":"2024-07-09","arxiv_id":"2407.06469","repositories_listed":0,"syntology":null},{"url":null,"slug":"genartist-multimodal-llm-as-an-agent-for","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","date":"2024-07-08","arxiv_id":"2407.05600","repositories_listed":0,"syntology":null},{"url":null,"slug":"jedi-joint-image-diffusion-models-for-1","title":"JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation","date":"2024-07-08","arxiv_id":"2407.06187","repositories_listed":0,"syntology":null},{"url":null,"slug":"layered-diffusion-model-for-one-shot-high","title":"Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis","date":"2024-07-08","arxiv_id":"2407.06079","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmis-multimodal-dataset-for-interior-scene","title":"MMIS: Multimodal Dataset for Interior Scene Visual Generation and Recognition","date":"2024-07-08","arxiv_id":"2407.05980","repositories_listed":0,"syntology":null},{"url":null,"slug":"mobileportrait-real-time-one-shot-neural-head","title":"MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices","date":"2024-07-08","arxiv_id":"2407.05712","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-image-skip-connections-in","title":"Rethinking Image Skip Connections in StyleGAN2","date":"2024-07-08","arxiv_id":"2407.05527","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-method-for-personalizing","title":"An Improved Method for Personalizing Diffusion Models","date":"2024-07-07","arxiv_id":"2407.05312","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-label-efficient-medical-image","title":"Enhancing Label-efficient Medical Image Segmentation with Text-guided Diffusion Models","date":"2024-07-07","arxiv_id":"2407.05323","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-conditional-generative-modeling","title":"Multi-scale Conditional Generative Modeling for Microscopic Image Restoration","date":"2024-07-07","arxiv_id":"2407.05259","repositories_listed":0,"syntology":null},{"url":null,"slug":"dicti-diffusion-based-clothing-designer-via","title":"DiCTI: Diffusion-based Clothing Designer via Text-guided Input","date":"2024-07-04","arxiv_id":"2407.03901","repositories_listed":0,"syntology":null},{"url":null,"slug":"lateralization-lora-interleaved-instruction","title":"Lateralization LoRA: Interleaved Instruction Tuning with Modality-Specialized Adaptations","date":"2024-07-04","arxiv_id":"2407.03604","repositories_listed":0,"syntology":null},{"url":null,"slug":"redifine-reusable-diffusion-finetuning-for","title":"Model Collapse in the Self-Consuming Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling","date":"2024-07-04","arxiv_id":"2407.17493","repositories_listed":0,"syntology":null},{"url":null,"slug":"bacon-supercharge-your-vlm-with-bag-of","title":"BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs","date":"2024-07-03","arxiv_id":"2407.03314","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-learning-with-cgan-for-casual","title":"Representation learning with CGAN for casual inference","date":"2024-07-03","arxiv_id":"2407.02825","repositories_listed":0,"syntology":null},{"url":null,"slug":"swiftdiffusion-efficient-diffusion-model","title":"SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules","date":"2024-07-02","arxiv_id":"2407.02031","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultrapixel-advancing-ultra-high-resolution","title":"UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peaks","date":"2024-07-02","arxiv_id":"2407.02158","repositories_listed":0,"syntology":null},{"url":null,"slug":"label-free-neural-semantic-image-synthesis","title":"Label-free Neural Semantic Image Synthesis","date":"2024-07-01","arxiv_id":"2407.01790","repositories_listed":0,"syntology":null},{"url":null,"slug":"badm-batch-admm-for-deep-learning","title":"BADM: Batch ADMM for Deep Learning","date":"2024-06-30","arxiv_id":"2407.01640","repositories_listed":0,"syntology":null},{"url":null,"slug":"chest-diffusion-a-light-weight-text-to-image","title":"Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation","date":"2024-06-30","arxiv_id":"2407.00752","repositories_listed":0,"syntology":null},{"url":null,"slug":"toward-a-diffusion-based-generalist-for-dense","title":"Toward a Diffusion-Based Generalist for Dense Vision Tasks","date":"2024-06-29","arxiv_id":"2407.00503","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-quality-bias-and-performance-in","title":"Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models","date":"2024-06-28","arxiv_id":"2407.00138","repositories_listed":0,"syntology":null},{"url":null,"slug":"wavelets-are-all-you-need-for-autoregressive","title":"Wavelets Are All You Need for Autoregressive Image Generation","date":"2024-06-28","arxiv_id":"2406.19997","repositories_listed":0,"syntology":null},{"url":null,"slug":"diminishing-stereotype-bias-in-image","title":"Diminishing Stereotype Bias in Image Generation Model using Reinforcemenlent Learning Feedback","date":"2024-06-27","arxiv_id":"2407.09551","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-stable-is-stable-diffusion-under","title":"How Stable is Stable Diffusion under Recursive InPainting (RIP)?","date":"2024-06-27","arxiv_id":"2407.09549","repositories_listed":0,"syntology":null},{"url":null,"slug":"multidiff-consistent-novel-view-synthesis-1","title":"MultiDiff: Consistent Novel View Synthesis from a Single Image","date":"2024-06-26","arxiv_id":"2406.18524","repositories_listed":0,"syntology":null},{"url":null,"slug":"mumu-bootstrapping-multimodal-image","title":"MUMU: Bootstrapping Multimodal Image Generation from Text-to-Image Data","date":"2024-06-26","arxiv_id":"2406.18790","repositories_listed":0,"syntology":null},{"url":null,"slug":"vdg-vision-only-dynamic-gaussian-for-driving","title":"VDG: Vision-Only Dynamic Gaussian for Driving Simulation","date":"2024-06-26","arxiv_id":"2406.18198","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-generative-extractor-for-synergistic","title":"Masked Generative Extractor for Synergistic Representation and 3D Generation of Point Clouds","date":"2024-06-25","arxiv_id":"2406.17342","repositories_listed":0,"syntology":null},{"url":null,"slug":"syncnoise-geometrically-consistent-noise","title":"SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing","date":"2024-06-25","arxiv_id":"2406.17396","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-tree-of-diffusion-life-evolutionary","title":"EvolvED: Evolutionary Embeddings to Understand the Generation Process of Diffusion Models","date":"2024-06-25","arxiv_id":"2406.17462","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsynd-targeted-synthetic-data-generation-for","title":"TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification","date":"2024-06-25","arxiv_id":"2406.17473","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-thumbs-up-down-untangling-challenges","title":"Beyond Thumbs Up/Down: Untangling Challenges of Fine-Grained Feedback for Text-to-Image Generation","date":"2024-06-24","arxiv_id":"2406.16807","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-consistency-image-generation-pcig-a","title":"Prompt-Consistency Image Generation (PCIG): A Unified Framework Integrating LLMs, Knowledge Graphs, and Controllable Diffusion Models","date":"2024-06-24","arxiv_id":"2406.16333","repositories_listed":0,"syntology":null},{"url":null,"slug":"resmaster-mastering-high-resolution-image","title":"ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance","date":"2024-06-24","arxiv_id":"2406.16476","repositories_listed":0,"syntology":null},{"url":null,"slug":"emoattack-emotion-to-image-diffusion-models","title":"EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation","date":"2024-06-22","arxiv_id":"2406.15863","repositories_listed":0,"syntology":null},{"url":null,"slug":"disability-representations-finding-biases-in","title":"Disability Representations: Finding Biases in Automatic Image Generation","date":"2024-06-21","arxiv_id":"2406.14993","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-diffusion-models-for-parameterization","title":"Latent diffusion models for parameterization and data assimilation of facies-based geomodels","date":"2024-06-21","arxiv_id":"2406.14815","repositories_listed":0,"syntology":null},{"url":null,"slug":"holistic-evaluation-for-interleaved-text-and","title":"Holistic Evaluation for Interleaved Text-and-Image Generation","date":"2024-06-20","arxiv_id":"2406.14643","repositories_listed":0,"syntology":null},{"url":null,"slug":"invertible-consistency-distillation-for-text","title":"Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps","date":"2024-06-20","arxiv_id":"2406.14539","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-generation-with-learned-action-prior","title":"Video Generation with Learned Action Prior","date":"2024-06-20","arxiv_id":"2406.14436","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-s-next-exploring-utilization-challenges","title":"What's Next? Exploring Utilization, Challenges, and Future Directions of AI-Generated Image Tools in Graphic Design","date":"2024-06-19","arxiv_id":"2406.13436","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-diffusion-models-with-federated","title":"Training Diffusion Models with Federated Learning","date":"2024-06-18","arxiv_id":"2406.12575","repositories_listed":0,"syntology":null},{"url":null,"slug":"artist-improving-the-generation-of-text-rich","title":"ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models","date":"2024-06-17","arxiv_id":"2406.12044","repositories_listed":0,"syntology":null},{"url":null,"slug":"decomposed-evaluations-of-geographic","title":"Decomposed evaluations of geographic disparities in text-to-image models","date":"2024-06-17","arxiv_id":"2406.11988","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-hamiltonian-variational","title":"Discriminative Hamiltonian Variational Autoencoder for Accurate Tumor Segmentation in Data-Scarce Regimes","date":"2024-06-17","arxiv_id":"2406.11659","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-the-role-of-large-language-models","title":"Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models","date":"2024-06-17","arxiv_id":"2406.11831","repositories_listed":0,"syntology":null},{"url":"/paper/phybench-a-physical-commonsense-benchmark-for","slug":"phybench-a-physical-commonsense-benchmark-for","title":"PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models","date":"2024-06-17","arxiv_id":"2406.11802","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-analysis-on-quantizing-diffusion","title":"An Analysis on Quantizing Diffusion Transformers","date":"2024-06-16","arxiv_id":"2406.11100","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-generative-ai-replace-immunofluorescent","title":"Can Generative AI Replace Immunofluorescent Staining Processes? A Comparison Study of Synthetically Generated CellPainting Images from Brightfield","date":"2024-06-15","arxiv_id":"2407.09507","repositories_listed":0,"syntology":null},{"url":null,"slug":"poetry2image-an-iterative-correction","title":"Poetry2Image: An Iterative Correction Framework for Images Generated from Chinese Classical Poetry","date":"2024-06-15","arxiv_id":"2407.06196","repositories_listed":0,"syntology":null},{"url":null,"slug":"crafting-parts-for-expressive-object","title":"Crafting Parts for Expressive Object Composition","date":"2024-06-14","arxiv_id":"2406.10197","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-image-is-worth-more-than-16x16-patches","title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels","date":"2024-06-13","arxiv_id":"2406.09415","repositories_listed":0,"syntology":null},{"url":null,"slug":"stablematerials-enhancing-diversity-in","title":"StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning","date":"2024-06-13","arxiv_id":"2406.09293","repositories_listed":0,"syntology":null},{"url":null,"slug":"toffee-efficient-million-scale-dataset","title":"Toffee: Efficient Million-Scale Dataset Construction for Subject-Driven Text-to-Image Generation","date":"2024-06-13","arxiv_id":"2406.09305","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-soup-model-merging-for-text-to","title":"Diffusion Soup: Model Merging for Text-to-Image Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08431","repositories_listed":0,"syntology":null},{"url":null,"slug":"ditfastattn-attention-compression-for","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","date":"2024-06-12","arxiv_id":"2406.08552","repositories_listed":0,"syntology":null},{"url":null,"slug":"fontstudio-shape-adaptive-diffusion-model-for","title":"FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation","date":"2024-06-12","arxiv_id":"2406.08392","repositories_listed":0,"syntology":null},{"url":"/paper/what-if-we-recaption-billions-of-web-images","slug":"what-if-we-recaption-billions-of-web-images","title":"What If We Recaption Billions of Web Images with LLaMA-3?","date":"2024-06-12","arxiv_id":"2406.08478","repositories_listed":0,"syntology":null},{"url":null,"slug":"wmadapter-adding-watermark-control-to-latent","title":"WMAdapter: Adding WaterMark Control to Latent Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08337","repositories_listed":0,"syntology":null},{"url":null,"slug":"words-worth-a-thousand-pictures-measuring-and","title":"Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation","date":"2024-06-12","arxiv_id":"2406.08482","repositories_listed":0,"syntology":null},{"url":null,"slug":"beware-of-aliases-signal-preservation-is","title":"Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration","date":"2024-06-11","arxiv_id":"2406.07435","repositories_listed":0,"syntology":null},{"url":null,"slug":"commonsense-t2i-challenge-can-text-to-image","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","date":"2024-06-11","arxiv_id":"2406.07546","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-x-controlling-structure-and-appearance","title":"Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance","date":"2024-06-11","arxiv_id":"2406.07540","repositories_listed":0,"syntology":null},{"url":null,"slug":"eye-for-an-eye-appearance-transfer-with","title":"Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models","date":"2024-06-11","arxiv_id":"2406.07008","repositories_listed":0,"syntology":null},{"url":null,"slug":"instant-3d-human-avatar-generation-using","title":"Instant 3D Human Avatar Generation using Image Diffusion Models","date":"2024-06-11","arxiv_id":"2406.07516","repositories_listed":0,"syntology":null},{"url":null,"slug":"progress-towards-decoding-visual-imagery-via","title":"Progress Towards Decoding Visual Imagery via fNIRS","date":"2024-06-11","arxiv_id":"2406.07662","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effect-of-training-dataset-size-on","title":"The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems","date":"2024-06-10","arxiv_id":"2406.06160","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-prompt-modifiers-control-bias-a","title":"Can Prompt Modifiers Control Bias? A Comparative Analysis of Text-to-Image Generative Models","date":"2024-06-09","arxiv_id":"2406.05602","repositories_listed":0,"syntology":null},{"url":null,"slug":"omnicontrolnet-dual-stage-integration-for","title":"OmniControlNet: Dual-stage Integration for Conditional Image Generation","date":"2024-06-09","arxiv_id":"2406.05871","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-text-to-image-generation-and","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","date":"2024-06-09","arxiv_id":"2406.05814","repositories_listed":0,"syntology":null},{"url":null,"slug":"rapid-review-of-generative-ai-in-smart","title":"Rapid Review of Generative AI in Smart Medical Applications","date":"2024-06-08","arxiv_id":"2406.06627","repositories_listed":0,"syntology":null},{"url":null,"slug":"attndreambooth-towards-text-aligned","title":"AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation","date":"2024-06-07","arxiv_id":"2406.05000","repositories_listed":0,"syntology":null},{"url":null,"slug":"coherent-zero-shot-visual-instruction","title":"Coherent Zero-Shot Visual Instruction Generation","date":"2024-06-06","arxiv_id":"2406.04337","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-large-vision-language-models","title":"DiffuSyn Bench: Evaluating Vision-Language Models on Real-World Complexities with Diffusion-Generated Synthetic Benchmarks","date":"2024-06-06","arxiv_id":"2406.04470","repositories_listed":0,"syntology":null}],"record_sha256":"cc8e0a76074bc19f53f47888e155ed3724309ae506c93e323126ee21bd1f07a0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}