{"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/39","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":39,"pages_in_order":67,"rows_per_page":100,"rows":[3801,3900],"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/38","next":"/task/image-generation/papers/40","papers":[{"url":null,"slug":"comparing-noisy-neural-population-dynamics","title":"Comparing noisy neural population dynamics using optimal transport distances","date":"2024-12-19","arxiv_id":"2412.14421","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusiontrend-a-minimalist-approach-to","title":"DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On","date":"2024-12-19","arxiv_id":"2412.14465","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-diffusion-models-for-high-quality","title":"Enhancing Diffusion Models for High-Quality Image Generation","date":"2024-12-19","arxiv_id":"2412.14422","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowing-from-words-to-pixels-a-framework-for","title":"Flowing from Words to Pixels: A Framework for Cross-Modality Evolution","date":"2024-12-19","arxiv_id":"2412.15213","repositories_listed":0,"syntology":null},{"url":null,"slug":"lediff-latent-exposure-diffusion-for-hdr","title":"LEDiff: Latent Exposure Diffusion for HDR Generation","date":"2024-12-19","arxiv_id":"2412.14456","repositories_listed":0,"syntology":null},{"url":null,"slug":"llamafusion-adapting-pretrained-language","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","date":"2024-12-19","arxiv_id":"2412.15188","repositories_listed":0,"syntology":null},{"url":null,"slug":"qua-2-sedimo-quantifiable-quantization","title":"Qua$^2$SeDiMo: Quantifiable Quantization Sensitivity of Diffusion Models","date":"2024-12-19","arxiv_id":"2412.14628","repositories_listed":0,"syntology":null},{"url":null,"slug":"tiled-diffusion","title":"Tiled Diffusion","date":"2024-12-19","arxiv_id":"2412.15185","repositories_listed":0,"syntology":null},{"url":null,"slug":"e-car-efficient-continuous-autoregressive","title":"E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling","date":"2024-12-18","arxiv_id":"2412.14170","repositories_listed":0,"syntology":null},{"url":null,"slug":"fashioncomposer-compositional-fashion-image","title":"FashionComposer: Compositional Fashion Image Generation","date":"2024-12-18","arxiv_id":"2412.14168","repositories_listed":0,"syntology":null},{"url":null,"slug":"galot-generative-active-learning-via","title":"GALOT: Generative Active Learning via Optimizable Zero-shot Text-to-image Generation","date":"2024-12-18","arxiv_id":"2412.16227","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmo-ig-multi-class-and-multi-scale-object","title":"MMO-IG: Multi-Class and Multi-Scale Object Image Generation for Remote Sensing","date":"2024-12-18","arxiv_id":"2412.13684","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-control-a-better-conditional-mechanism","title":"Self-control: A Better Conditional Mechanism for Masked Autoregressive Model","date":"2024-12-18","arxiv_id":"2412.13635","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2relight-creative-portrait-relighting","title":"Text2Relight: Creative Portrait Relighting with Text Guidance","date":"2024-12-18","arxiv_id":"2412.13734","repositories_listed":0,"syntology":null},{"url":null,"slug":"videodpo-omni-preference-alignment-for-video","title":"VideoDPO: Omni-Preference Alignment for Video Diffusion Generation","date":"2024-12-18","arxiv_id":"2412.14167","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-meddiffusion-a-3d-medical-diffusion-model","title":"3D MedDiffusion: A 3D Medical Diffusion Model for Controllable and High-quality Medical Image Generation","date":"2024-12-17","arxiv_id":"2412.13059","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistent-diffusion-denoising-diffusion","title":"Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration","date":"2024-12-17","arxiv_id":"2412.12550","repositories_listed":0,"syntology":null},{"url":null,"slug":"f-bench-rethinking-human-preference","title":"F-Bench: Rethinking Human Preference Evaluation Metrics for Benchmarking Face Generation, Customization, and Restoration","date":"2024-12-17","arxiv_id":"2412.13155","repositories_listed":0,"syntology":null},{"url":null,"slug":"numerical-pruning-for-efficient","title":"Numerical Pruning for Efficient Autoregressive Models","date":"2024-12-17","arxiv_id":"2412.12441","repositories_listed":0,"syntology":null},{"url":"/paper/posterior-mean-matching-generative-modeling","slug":"posterior-mean-matching-generative-modeling","title":"Posterior Mean Matching: Generative Modeling through Online Bayesian Inference","date":"2024-12-17","arxiv_id":"2412.13286","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-augmentation-for-self-supervised-text-1","title":"Prompt Augmentation for Self-supervised Text-guided Image Manipulation","date":"2024-12-17","arxiv_id":"2412.13081","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-diffusion-is-a-natural-cross-modal","title":"Stable Diffusion is a Natural Cross-Modal Decoder for Layered AI-generated Image Compression","date":"2024-12-17","arxiv_id":"2412.12982","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-region-based-image-editing-of","title":"Unsupervised Region-Based Image Editing of Denoising Diffusion Models","date":"2024-12-17","arxiv_id":"2412.12912","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-lora-is-worth-a-thousand-pictures","title":"A LoRA is Worth a Thousand Pictures","date":"2024-12-16","arxiv_id":"2412.12048","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-scaling-of-diffusion-transformers","title":"Efficient Scaling of Diffusion Transformers for Text-to-Image Generation","date":"2024-12-16","arxiv_id":"2412.12391","repositories_listed":0,"syntology":null},{"url":null,"slug":"lineart-a-knowledge-guided-training-free-high","title":"LineArt: A Knowledge-guided Training-free High-quality Appearance Transfer for Design Drawing with Diffusion Model","date":"2024-12-16","arxiv_id":"2412.11519","repositories_listed":0,"syntology":null},{"url":null,"slug":"nearly-zero-cost-protection-against-mimicry","title":"Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models","date":"2024-12-16","arxiv_id":"2412.11423","repositories_listed":0,"syntology":null},{"url":null,"slug":"omniprism-learning-disentangled-visual","title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","date":"2024-12-16","arxiv_id":"2412.12242","repositories_listed":0,"syntology":null},{"url":null,"slug":"you-only-submit-one-image-to-find-the-most","title":"You Only Submit One Image to Find the Most Suitable Generative Model","date":"2024-12-16","arxiv_id":"2412.12232","repositories_listed":0,"syntology":null},{"url":null,"slug":"genlit-reformulating-single-image-relighting","title":"GenLit: Reformulating Single-Image Relighting as Video Generation","date":"2024-12-15","arxiv_id":"2412.11224","repositories_listed":0,"syntology":null},{"url":null,"slug":"grassmannian-geometry-meets-dynamic-mode","title":"Grassmannian Geometry Meets Dynamic Mode Decomposition in DMD-GEN: A New Metric for Mode Collapse in Time Series Generative Models","date":"2024-12-15","arxiv_id":"2412.11292","repositories_listed":0,"syntology":null},{"url":null,"slug":"provably-secure-robust-image-steganography","title":"Provably Secure Robust Image Steganography via Cross-Modal Error Correction","date":"2024-12-15","arxiv_id":"2412.12206","repositories_listed":0,"syntology":null},{"url":null,"slug":"progressive-compression-with-universally","title":"Progressive Compression with Universally Quantized Diffusion Models","date":"2024-12-14","arxiv_id":"2412.10935","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-general-annotated-dataset-generation","title":"Unbiased General Annotated Dataset Generation","date":"2024-12-14","arxiv_id":"2412.10831","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-generative-modeling-with-residual","title":"Efficient Generative Modeling with Residual Vector Quantization-Based Tokens","date":"2024-12-13","arxiv_id":"2412.10208","repositories_listed":0,"syntology":null},{"url":null,"slug":"op-lora-the-blessing-of-dimensionality","title":"OP-LoRA: The Blessing of Dimensionality","date":"2024-12-13","arxiv_id":"2412.10362","repositories_listed":0,"syntology":null},{"url":null,"slug":"safetydpo-scalable-safety-alignment-for-text","title":"SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation","date":"2024-12-13","arxiv_id":"2412.10493","repositories_listed":0,"syntology":null},{"url":null,"slug":"snapgen-v-generating-a-five-second-video","title":"SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device","date":"2024-12-13","arxiv_id":"2412.10494","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-conditional-latent-diffusion-models","title":"Are Conditional Latent Diffusion Models Effective for Image Restoration?","date":"2024-12-12","arxiv_id":"2412.09324","repositories_listed":0,"syntology":null},{"url":null,"slug":"easyref-omni-generalized-group-image","title":"EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM","date":"2024-12-12","arxiv_id":"2412.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"fluxspace-disentangled-semantic-editing-in","title":"FluxSpace: Disentangled Semantic Editing in Rectified Flow Transformers","date":"2024-12-12","arxiv_id":"2412.09611","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-noise-to-nuance-advances-in-deep","title":"From Noise to Nuance: Advances in Deep Generative Image Models","date":"2024-12-12","arxiv_id":"2412.09656","repositories_listed":0,"syntology":null},{"url":null,"slug":"loraclr-contrastive-adaptation-for","title":"LoRACLR: Contrastive Adaptation for Customization of Diffusion Models","date":"2024-12-12","arxiv_id":"2412.09622","repositories_listed":0,"syntology":null},{"url":null,"slug":"rad-region-aware-diffusion-models-for-image","title":"RAD: Region-Aware Diffusion Models for Image Inpainting","date":"2024-12-12","arxiv_id":"2412.09191","repositories_listed":0,"syntology":null},{"url":null,"slug":"spectral-image-tokenizer","title":"Spectral Image Tokenizer","date":"2024-12-12","arxiv_id":"2412.09607","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-language-models-represent-darker","title":"Vision-Language Models Represent Darker-Skinned Black Individuals as More Homogeneous than Lighter-Skinned Black Individuals","date":"2024-12-12","arxiv_id":"2412.09668","repositories_listed":0,"syntology":null},{"url":null,"slug":"viunit-visual-unit-tests-for-more-robust","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","date":"2024-12-12","arxiv_id":"2412.08859","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-and-improving-model-collapse-in","title":"Analyzing and Improving Model Collapse in Rectified Flow Models","date":"2024-12-11","arxiv_id":"2412.08175","repositories_listed":0,"syntology":null},{"url":null,"slug":"asyncdsb-schedule-asynchronous-diffusion","title":"AsyncDSB: Schedule-Asynchronous Diffusion Schrödinger Bridge for Image Inpainting","date":"2024-12-11","arxiv_id":"2412.08149","repositories_listed":0,"syntology":null},{"url":null,"slug":"cc-diff-enhancing-contextual-coherence-in","title":"CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesis","date":"2024-12-11","arxiv_id":"2412.08464","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-zoo","title":"Generative Zoo","date":"2024-12-11","arxiv_id":"2412.08101","repositories_listed":0,"syntology":null},{"url":null,"slug":"gptdrawer-enhancing-visual-synthesis-through","title":"GPTDrawer: Enhancing Visual Synthesis through ChatGPT","date":"2024-12-11","arxiv_id":"2412.10429","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-approaches-to-fair-image","title":"Multimodal Approaches to Fair Image Classification: An Ethical Perspective","date":"2024-12-11","arxiv_id":"2412.12165","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-syntax-uncovering-syntactic-learning","title":"Seeing Syntax: Uncovering Syntactic Learning Limitations in Vision-Language Models","date":"2024-12-11","arxiv_id":"2412.08111","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-visual-secrets-inverting-features","title":"Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstruction","date":"2024-12-11","arxiv_id":"2412.10448","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-victim-model-for-segmentation","title":"A Generative Victim Model for Segmentation","date":"2024-12-10","arxiv_id":"2412.07274","repositories_listed":0,"syntology":null},{"url":null,"slug":"buster-incorporating-backdoor-attacks-into","title":"Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation","date":"2024-12-10","arxiv_id":"2412.07249","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffsensei-bridging-multi-modal-llms-and","title":"DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation","date":"2024-12-10","arxiv_id":"2412.07589","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-text-to-image-synthesis","title":"Fine-grained Text to Image Synthesis","date":"2024-12-10","arxiv_id":"2412.07196","repositories_listed":0,"syntology":null},{"url":null,"slug":"fiva-fine-grained-visual-attribute-dataset","title":"FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models","date":"2024-12-10","arxiv_id":"2412.07674","repositories_listed":0,"syntology":null},{"url":null,"slug":"fusion-embedding-for-pose-guided-person-image","title":"Fusion Embedding for Pose-Guided Person Image Synthesis with Diffusion Model","date":"2024-12-10","arxiv_id":"2412.07333","repositories_listed":0,"syntology":null},{"url":null,"slug":"moderating-the-generalization-of-score-based","title":"Moderating the Generalization of Score-based Generative Model","date":"2024-12-10","arxiv_id":"2412.07229","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-and-sequential-text-to-image","title":"Preference Adaptive and Sequential Text-to-Image Generation","date":"2024-12-10","arxiv_id":"2412.10419","repositories_listed":0,"syntology":null},{"url":null,"slug":"unireal-universal-image-generation-and","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","date":"2024-12-10","arxiv_id":"2412.07774","repositories_listed":0,"syntology":null},{"url":null,"slug":"asgdiffusion-parallel-high-resolution","title":"ASGDiffusion: Parallel High-Resolution Generation with Asynchronous Structure Guidance","date":"2024-12-09","arxiv_id":"2412.06163","repositories_listed":0,"syntology":null},{"url":null,"slug":"contrail-a-framework-for-realistic-railway","title":"ContRail: A Framework for Realistic Railway Image Synthesis using ControlNet","date":"2024-12-09","arxiv_id":"2412.06742","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficiency-meets-fidelity-a-novel","title":"Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion","date":"2024-12-09","arxiv_id":"2412.06661","repositories_listed":0,"syntology":null},{"url":"/paper/illume-illuminating-your-llms-to-see-draw-and","slug":"illume-illuminating-your-llms-to-see-draw-and","title":"ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance","date":"2024-12-09","arxiv_id":"2412.06673","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-lexicon-rich-image-features-in","title":"Visual Lexicon: Rich Image Features in Language Space","date":"2024-12-09","arxiv_id":"2412.06774","repositories_listed":0,"syntology":null},{"url":null,"slug":"budgetfusion-perceptually-guided-adaptive","title":"BudgetFusion: Perceptually-Guided Adaptive Diffusion Models","date":"2024-12-08","arxiv_id":"2412.05780","repositories_listed":0,"syntology":null},{"url":null,"slug":"csg-a-context-semantic-guided-diffusion","title":"CSG: A Context-Semantic Guided Diffusion Approach in De Novo Musculoskeletal Ultrasound Image Generation","date":"2024-12-08","arxiv_id":"2412.05833","repositories_listed":0,"syntology":null},{"url":null,"slug":"grape-a-generate-plan-edit-framework-for","title":"GraPE: A Generate-Plan-Edit Framework for Compositional T2I Synthesis","date":"2024-12-08","arxiv_id":"2412.06089","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-image-tokenization-for","title":"Language-Guided Image Tokenization for Generation","date":"2024-12-08","arxiv_id":"2412.05796","repositories_listed":0,"syntology":null},{"url":null,"slug":"nested-diffusion-models-using-hierarchical","title":"Nested Diffusion Models Using Hierarchical Latent Priors","date":"2024-12-08","arxiv_id":"2412.05984","repositories_listed":0,"syntology":null},{"url":null,"slug":"open-source-acceleration-of-stable-diffusion","title":"Open-Source Acceleration of Stable-Diffusion.cpp Deployable on All Devices","date":"2024-12-08","arxiv_id":"2412.05781","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-guidance-boosting-flow-and-diffusion","title":"Self-Guidance: Boosting Flow and Diffusion Generation on Their Own","date":"2024-12-08","arxiv_id":"2412.05827","repositories_listed":0,"syntology":null},{"url":null,"slug":"silmm-self-improving-large-multimodal-models","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","date":"2024-12-08","arxiv_id":"2412.05818","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tiered-gan-approach-for-monet-style-image","title":"A Tiered GAN Approach for Monet-Style Image Generation","date":"2024-12-07","arxiv_id":"2412.05724","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncovering-vision-modality-threats-in-image","title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","date":"2024-12-07","arxiv_id":"2412.05538","repositories_listed":0,"syntology":null},{"url":null,"slug":"continuous-video-process-modeling-videos-as","title":"Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction","date":"2024-12-06","arxiv_id":"2412.04929","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-matters-diffusion-model-based-urban","title":"Noise Matters: Diffusion Model-based Urban Mobility Generation with Collaborative Noise Priors","date":"2024-12-06","arxiv_id":"2412.05000","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-silent-prompt-initial-noise-as-implicit","title":"The Silent Prompt: Initial Noise as Implicit Guidance for Goal-Driven Image Generation","date":"2024-12-06","arxiv_id":"2412.05101","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-image-synthesis-using","title":"A Framework For Image Synthesis Using Supervised Contrastive Learning","date":"2024-12-05","arxiv_id":"2412.03957","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-noise-is-worth-diffusion-guidance","title":"A Noise is Worth Diffusion Guidance","date":"2024-12-05","arxiv_id":"2412.03895","repositories_listed":0,"syntology":null},{"url":null,"slug":"anydressing-customizable-multi-garment","title":"AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models","date":"2024-12-05","arxiv_id":"2412.04146","repositories_listed":0,"syntology":null},{"url":null,"slug":"bodymetric-evaluating-the-realism-of","title":"BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation","date":"2024-12-05","arxiv_id":"2412.04086","repositories_listed":0,"syntology":null},{"url":null,"slug":"creatilayout-siamese-multimodal-diffusion","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","date":"2024-12-05","arxiv_id":"2412.03859","repositories_listed":0,"syntology":null},{"url":null,"slug":"layerfusion-harmonized-multi-layer-text-to","title":"LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors","date":"2024-12-05","arxiv_id":"2412.04460","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-curvature-smoothing-with-stein-s","title":"Local Curvature Smoothing with Stein's Identity for Efficient Score Matching","date":"2024-12-05","arxiv_id":"2412.03962","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-subject-image-synthesis-as-a-generative","title":"Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction","date":"2024-12-05","arxiv_id":"2412.04324","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-communication-round-is-all-it-needs-for","title":"One Communication Round is All It Needs for Federated Fine-Tuning Foundation Models","date":"2024-12-05","arxiv_id":"2412.04650","repositories_listed":0,"syntology":null},{"url":null,"slug":"t2i-factualbench-benchmarking-the-factuality","title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","date":"2024-12-05","arxiv_id":"2412.04300","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-hyperfitting-phenomenon-sharpening-and","title":"The Hyperfitting Phenomenon: Sharpening and Stabilizing LLMs for Open-Ended Text Generation","date":"2024-12-05","arxiv_id":"2412.04318","repositories_listed":0,"syntology":null},{"url":null,"slug":"appearance-matching-adapter-for-exemplar","title":"Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis","date":"2024-12-04","arxiv_id":"2412.03150","repositories_listed":0,"syntology":null},{"url":null,"slug":"dive-taming-dino-for-subject-driven-video","title":"DIVE: Taming DINO for Subject-Driven Video Editing","date":"2024-12-04","arxiv_id":"2412.03347","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamiccontrol-adaptive-condition-selection","title":"DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation","date":"2024-12-04","arxiv_id":"2412.03255","repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-matching-with-general-discrete-paths-a","title":"Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective","date":"2024-12-04","arxiv_id":"2412.03487","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-diffusion-model-with-adjusted","title":"Generalized Diffusion Model with Adjusted Offset Noise","date":"2024-12-04","arxiv_id":"2412.03134","repositories_listed":0,"syntology":null},{"url":null,"slug":"geometry-guided-cross-view-diffusion-for-one","title":"Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis","date":"2024-12-04","arxiv_id":"2412.03315","repositories_listed":0,"syntology":null},{"url":null,"slug":"implicit-priors-editing-in-stable-diffusion","title":"Implicit Priors Editing in Stable Diffusion via Targeted Token Adjustment","date":"2024-12-04","arxiv_id":"2412.03400","repositories_listed":0,"syntology":null}],"record_sha256":"8dac0258b8ac024cf326f7db3604f0d598f5e39f866b21e4c7e598e38ae7be10","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}