{"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/38","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":38,"pages_in_order":67,"rows_per_page":100,"rows":[3701,3800],"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/37","next":"/task/image-generation/papers/39","papers":[{"url":null,"slug":"zero-1-to-g-taming-pretrained-2d-diffusion","title":"Zero-1-to-G: Taming Pretrained 2D Diffusion Model for Direct 3D Generation","date":"2025-01-09","arxiv_id":"2501.05427","repositories_listed":0,"syntology":null},{"url":null,"slug":"circuit-complexity-bounds-for-visual","title":"Circuit Complexity Bounds for Visual Autoregressive Model","date":"2025-01-08","arxiv_id":"2501.04299","repositories_listed":0,"syntology":null},{"url":null,"slug":"color-correction-meets-cross-spectral","title":"Color Correction Meets Cross-Spectral Refinement: A Distribution-Aware Diffusion for Underwater Image Restoration","date":"2025-01-08","arxiv_id":"2501.04740","repositories_listed":0,"syntology":null},{"url":null,"slug":"editar-unified-conditional-generation-with","title":"EditAR: Unified Conditional Generation with Autoregressive Models","date":"2025-01-08","arxiv_id":"2501.04699","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-computational-limits-and-provably","title":"On Computational Limits and Provably Efficient Criteria of Visual Autoregressive Models: A Fine-Grained Complexity Analysis","date":"2025-01-08","arxiv_id":"2501.04377","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-image-caption-via-cycle-consistent","title":"Evaluating Image Caption via Cycle-consistent Text-to-Image Generation","date":"2025-01-07","arxiv_id":"2501.03567","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptguard-soft-prompt-guided-unsafe-content","title":"PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models","date":"2025-01-07","arxiv_id":"2501.03544","repositories_listed":0,"syntology":null},{"url":null,"slug":"scenebooth-diffusion-based-framework-for","title":"SceneBooth: Diffusion-based Framework for Subject-preserved Text-to-Image Generation","date":"2025-01-07","arxiv_id":"2501.03490","repositories_listed":0,"syntology":null},{"url":null,"slug":"ace-instruction-based-image-creation-and","title":"ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling","date":"2025-01-05","arxiv_id":"2501.02487","repositories_listed":0,"syntology":null},{"url":null,"slug":"medsegdiffnca-diffusion-models-with-neural","title":"MedSegDiffNCA: Diffusion Models With Neural Cellular Automata for Skin Lesion Segmentation","date":"2025-01-05","arxiv_id":"2501.02447","repositories_listed":0,"syntology":null},{"url":null,"slug":"vision-driven-prompt-optimization-for-large","title":"Vision-Driven Prompt Optimization for Large Language Models in Multimodal Generative Tasks","date":"2025-01-05","arxiv_id":"2501.02527","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-multimodal-images-with-gan","title":"Generating Multimodal Images with GAN: Integrating Text, Image, and Style","date":"2025-01-04","arxiv_id":"2501.02167","repositories_listed":0,"syntology":null},{"url":null,"slug":"plasma-cyclegan-plasma-biomarker-guided-mri","title":"Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN","date":"2025-01-04","arxiv_id":"2501.02146","repositories_listed":0,"syntology":null},{"url":null,"slug":"layeringdiff-layered-image-synthesis-via","title":"LayeringDiff: Layered Image Synthesis via Generation, then Disassembly with Generative Knowledge","date":"2025-01-02","arxiv_id":"2501.01197","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-level-visual-prompts-for-compositional","title":"Object-level Visual Prompts for Compositional Image Generation","date":"2025-01-02","arxiv_id":"2501.01424","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-controllable-image-generation-by","title":"Test-time Controllable Image Generation by Explicit Spatial Constraint Enforcement","date":"2025-01-02","arxiv_id":"2501.01368","repositories_listed":0,"syntology":null},{"url":null,"slug":"a4a-adapter-for-adapter-transfer-via-all-for","title":"A4A: Adapter for Adapter Transfer via All-for-All Mapping for Cross-Architecture Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adapting-text-to-image-generation-with","title":"Adapting Text-to-Image Generation with Feature Difference Instruction for Generic Image Restoration","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-non-uniform-timestep-sampling-for-1","title":"Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-domain-prompt-tuning-and","title":"Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-generation-a-diffusion-based-low-level","title":"Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-text-implementing-multimodal-large","title":"Beyond Text: Implementing Multimodal Large Language Model-Powered Multi-Agent Systems Using a No-Code Platform","date":"2025-01-01","arxiv_id":"2501.00750","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-hole-driven-identity-absorbing-in","title":"Black Hole-Driven Identity Absorbing in Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"cachequant-comprehensively-accelerated","title":"CacheQuant: Comprehensively Accelerated Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"composing-parts-for-expressive-object","title":"Composing Parts for Expressive Object Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"consistency-posterior-sampling-for-diverse","title":"Consistency Posterior Sampling for Diverse Image Synthesis","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"d-2it-dynamic-diffusion-transformer-for","title":"D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"decouple-then-merge-finetune-diffusion-models","title":"Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"detect-and-guide-self-regulation-of-diffusion","title":"Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"devil-is-in-the-detail-towards-injecting-fine","title":"Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-prism-enhancing-diversity-and","title":"Diffusion Prism: Enhancing Diversity and Morphology Consistency in Mask-to-Image Diffusion","date":"2025-01-01","arxiv_id":"2501.00944","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamrelation-bridging-customization-and","title":"DreamRelation: Bridging Customization and Relation Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-interrelated-diffusion-model-for-few","title":"Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"eidt-v-exploiting-intersections-in-diffusion","title":"EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-early-diabetic-retinopathy","title":"Enhancing Early Diabetic Retinopathy Detection through Synthetic DR1 Image Generation: A StyleGAN3 Approach","date":"2025-01-01","arxiv_id":"2501.00954","repositories_listed":0,"syntology":null},{"url":null,"slug":"flowing-from-words-to-pixels-a-noise-free","title":"Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fluxspace-disentangled-semantic-editing-in-1","title":"FluxSpace: Disentangled Semantic Editing in Rectified Flow Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizable-object-keypoint-localization","title":"Generalizable Object Keypoint Localization from Generative Priors","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-zero-shot-composed-image-retrieval","title":"Generative Zero-Shot Composed Image Retrieval","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"glass-guided-latent-slot-diffusion-for-object","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-global-local-collaborative","title":"Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-vision-language-alignment-for","title":"Hierarchical Vision-Language Alignment for Text-to-Image Generation via Diffusion Models","date":"2025-01-01","arxiv_id":"2501.00917","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-biased-general-annotated-dataset","title":"Low-Biased General Annotated Dataset Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mc-2-multi-concept-guidance-for-customized-1","title":"MC^2: Multi-concept Guidance for Customized Multi-concept Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-group-proportional-representations-for","title":"Multi-Group Proportional Representations for Text-to-Image Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-party-collaborative-attention-control","title":"Multi-party Collaborative Attention Control for Image Customization","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"noisectrl-a-sampling-algorithm-agnostic","title":"NoiseCtrl: A Sampling-Algorithm-Agnostic Conditional Generation Method for Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"oasis-uncovers-high-quality-t2i-models-same","title":"OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes","date":"2025-01-01","arxiv_id":"2501.00962","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-way-ticket-time-independent-unified","title":"One-Way Ticket: Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"patch-matters-training-free-fine-grained","title":"Patch Matters: Training-free Fine-grained Image Caption Enhancement via Local Perception","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"regression-guided-strategy-to-automated","title":"Regression Guided Strategy to Automated Facial Beauty Optimization through Image Synthesis","date":"2025-01-01","arxiv_id":"2501.00811","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-inference-time-compute-for-diffusion","title":"Scaling Inference Time Compute for Diffusion Models","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simpler-diffusion-1-5-fid-on-imagenet512-with","title":"Simpler Diffusion: 1.5 FID on ImageNet512 with Pixel-space Diffusion","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ske-layout-spatial-knowledge-enhanced-layout","title":"SKE-Layout: Spatial Knowledge Enhanced Layout Generation with LLMs","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"smartspatial-enhancing-the-3d-spatial","title":"SmartSpatial: Enhancing the 3D Spatial Arrangement Capabilities of Stable Diffusion Models and Introducing a Novel 3D Spatial Evaluation Framework","date":"2025-01-01","arxiv_id":"2501.01998","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2earth-unlocking-text-driven-remote","title":"Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model","date":"2025-01-01","arxiv_id":"2501.00895","repositories_listed":0,"syntology":null},{"url":null,"slug":"tfcustom-customized-image-generation-with","title":"TFCustom: Customized Image Generation with Time-Aware Frequency Feature Guidance","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-universal-dataset-distillation-via","title":"Towards Universal Dataset Distillation via Task-Driven Diffusion","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unseen-visual-anomaly-generation","title":"Unseen Visual Anomaly Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"vodiff-controlling-object-visibility-order-in","title":"VODiff: Controlling Object Visibility Order in Text-to-Image Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"yo-chameleon-personalized-vision-and-language","title":"Yo'Chameleon: Personalized Vision and Language Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"z-magic-zero-shot-multiple-attributes-guided","title":"Z-Magic: Zero-shot Multiple Attributes Guided Image Creator","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mllm-as-a-judge-for-image-safety-without","title":"MLLM-as-a-Judge for Image Safety without Human Labeling","date":"2024-12-31","arxiv_id":"2501.00192","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-drifting-in-diffusion-models-for","title":"Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis","date":"2024-12-30","arxiv_id":"2412.20651","repositories_listed":0,"syntology":null},{"url":null,"slug":"pqd-post-training-quantization-for-efficient","title":"PQD: Post-training Quantization for Efficient Diffusion Models","date":"2024-12-30","arxiv_id":"2501.00124","repositories_listed":0,"syntology":null},{"url":null,"slug":"prometheus-3d-aware-latent-diffusion-models","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation","date":"2024-12-30","arxiv_id":"2412.21117","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-to-image-gan-with-pretrained","title":"Text-to-Image GAN with Pretrained Representations","date":"2024-12-30","arxiv_id":"2501.00116","repositories_listed":0,"syntology":null},{"url":null,"slug":"diff4mmlits-advanced-multimodal-liver-tumor","title":"Diff4MMLiTS: Advanced Multimodal Liver Tumor Segmentation via Diffusion-Based Image Synthesis and Alignment","date":"2024-12-29","arxiv_id":"2412.20418","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-ordinary-differential-equation-sampler","title":"An Ordinary Differential Equation Sampler with Stochastic Start for Diffusion Bridge Models","date":"2024-12-28","arxiv_id":"2412.19992","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-generalized-schrodinger-bridges-from","title":"Deep Generalized Schrödinger Bridges: From Image Generation to Solving Mean-Field Games","date":"2024-12-28","arxiv_id":"2412.20279","repositories_listed":0,"syntology":null},{"url":null,"slug":"infelm-in-depth-fairness-evaluation-of-large","title":"INFELM: In-depth Fairness Evaluation of Large Text-To-Image Models","date":"2024-12-28","arxiv_id":"2501.01973","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-free-group-wise-fully-quantized-winograd","title":"Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales","date":"2024-12-27","arxiv_id":"2412.19867","repositories_listed":0,"syntology":null},{"url":null,"slug":"focusing-image-generation-to-mitigate","title":"Focusing Image Generation to Mitigate Spurious Correlations","date":"2024-12-27","arxiv_id":"2412.19457","repositories_listed":0,"syntology":null},{"url":null,"slug":"p3s-diffusion-a-selective-subject-driven","title":"P3S-Diffusion:A Selective Subject-driven Generation Framework via Point Supervision","date":"2024-12-27","arxiv_id":"2412.19533","repositories_listed":0,"syntology":null},{"url":null,"slug":"conditional-balance-improving-multi","title":"Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation","date":"2024-12-25","arxiv_id":"2412.19853","repositories_listed":0,"syntology":null},{"url":null,"slug":"dific-your-diffusion-model-holds-the-secret","title":"DiFiC: Your Diffusion Model Holds the Secret to Fine-Grained Clustering","date":"2024-12-25","arxiv_id":"2412.18838","repositories_listed":0,"syntology":null},{"url":null,"slug":"drdm-a-disentangled-representations-diffusion","title":"DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images","date":"2024-12-25","arxiv_id":"2412.18797","repositories_listed":0,"syntology":null},{"url":null,"slug":"elucidating-flow-matching-ode-dynamics-with","title":"Elucidating Flow Matching ODE Dynamics with Respect to Data Geometries","date":"2024-12-25","arxiv_id":"2412.18730","repositories_listed":0,"syntology":null},{"url":null,"slug":"protective-perturbations-against-unauthorized","title":"Protective Perturbations against Unauthorized Data Usage in Diffusion-based Image Generation","date":"2024-12-25","arxiv_id":"2412.18791","repositories_listed":0,"syntology":null},{"url":null,"slug":"unic-adapter-unified-image-instruction","title":"UNIC-Adapter: Unified Image-instruction Adapter with Multi-modal Transformer for Image Generation","date":"2024-12-25","arxiv_id":"2412.18928","repositories_listed":0,"syntology":null},{"url":null,"slug":"1-58-bit-flux","title":"1.58-bit FLUX","date":"2024-12-24","arxiv_id":"2412.18653","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-face-personalized-face-generation-model","title":"Dense-Face: Personalized Face Generation Model via Dense Annotation Prediction","date":"2024-12-24","arxiv_id":"2412.18149","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensuring-consistency-for-in-image-translation","title":"Ensuring Consistency for In-Image Translation","date":"2024-12-24","arxiv_id":"2412.18139","repositories_listed":0,"syntology":null},{"url":null,"slug":"fashionability-enhancing-outfit-image-editing","title":"Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models","date":"2024-12-24","arxiv_id":"2412.18421","repositories_listed":0,"syntology":null},{"url":null,"slug":"rdpm-solve-diffusion-probabilistic-models-via","title":"RDPM: Solve Diffusion Probabilistic Models via Recurrent Token Prediction","date":"2024-12-24","arxiv_id":"2412.18390","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminative-image-generation-with","title":"Discriminative Image Generation with Diffusion Models for Zero-Shot Learning","date":"2024-12-23","arxiv_id":"2412.17219","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-large-vision-language-models","title":"Personalized Large Vision-Language Models","date":"2024-12-23","arxiv_id":"2412.17610","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-based-approaches-in-medical-image","title":"Diffusion-Based Approaches in Medical Image Generation and Analysis","date":"2024-12-22","arxiv_id":"2412.16860","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamomni-unified-image-generation-and","title":"DreamOmni: Unified Image Generation and Editing","date":"2024-12-22","arxiv_id":"2412.17098","repositories_listed":0,"syntology":null},{"url":null,"slug":"hypernet-fields-efficiently-training","title":"HyperNet Fields: Efficiently Training Hypernetworks without Ground Truth by Learning Weight Trajectories","date":"2024-12-22","arxiv_id":"2412.17040","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-and-timestep-adaptive-differentiable","title":"Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers","date":"2024-12-22","arxiv_id":"2412.16822","repositories_listed":0,"syntology":null},{"url":null,"slug":"modular-conversational-agents-for-surveys-and","title":"Modular Conversational Agents for Surveys and Interviews","date":"2024-12-22","arxiv_id":"2412.17049","repositories_listed":0,"syntology":null},{"url":null,"slug":"realisid-scale-robust-and-fine-controllable","title":"RealisID: Scale-Robust and Fine-Controllable Identity Customization via Local and Global Complementation","date":"2024-12-22","arxiv_id":"2412.16832","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-corrected-flow-distillation-for","title":"Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation","date":"2024-12-22","arxiv_id":"2412.16906","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attack-against-images","title":"Adversarial Attack Against Images Classification based on Generative Adversarial Networks","date":"2024-12-21","arxiv_id":"2412.16662","repositories_listed":0,"syntology":null},{"url":null,"slug":"safecfg-redirecting-harmful-classifier-free","title":"SafeCFG: Redirecting Harmful Classifier-Free Guidance for Safe Generation","date":"2024-12-20","arxiv_id":"2412.16039","repositories_listed":0,"syntology":null},{"url":null,"slug":"semdp-semantic-level-differential-privacy","title":"SemDP: Semantic-level Differential Privacy Protection for Face Datasets","date":"2024-12-20","arxiv_id":"2412.15590","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-adaptation-of-diffusion","title":"Semi-Supervised Adaptation of Diffusion Models for Handwritten Text Generation","date":"2024-12-20","arxiv_id":"2412.15853","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylish-and-functional-guided-interpolation","title":"Stylish and Functional: Guided Interpolation Subject to Physical Constraints","date":"2024-12-20","arxiv_id":"2412.15507","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-worse-is-better-navigating-the","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","date":"2024-12-20","arxiv_id":"2412.16326","repositories_listed":0,"syntology":null}],"record_sha256":"29df1cb43277b44157cfa7586a1f342dec70b5b7e0c583fae15c1d596e29380f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}