{"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/36","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":36,"pages_in_order":67,"rows_per_page":100,"rows":[3501,3600],"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/35","next":"/task/image-generation/papers/37","papers":[{"url":null,"slug":"active-learning-inspired-controlnet-guidance","title":"Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets","date":"2025-03-12","arxiv_id":"2503.09221","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoupled-doubly-contrastive-learning-for","title":"Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection","date":"2025-03-12","arxiv_id":"2503.08977","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-position-encoding-in-diffusion-u","title":"Exploring Position Encoding in Diffusion U-Net for Training-free High-resolution Image Generation","date":"2025-03-12","arxiv_id":"2503.09830","repositories_listed":0,"syntology":null},{"url":null,"slug":"fcas-fine-grained-cardiac-image-synthesis","title":"FCaS: Fine-grained Cardiac Image Synthesis based on 3D Template Conditional Diffusion Model","date":"2025-03-12","arxiv_id":"2503.09560","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-semantic-attribute-binding-for","title":"Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09864","repositories_listed":0,"syntology":null},{"url":null,"slug":"nami-efficient-image-generation-via","title":"NAMI: Efficient Image Generation via Progressive Rectified Flow Transformers","date":"2025-03-12","arxiv_id":"2503.09242","repositories_listed":0,"syntology":null},{"url":"/paper/unicombine-unified-multi-conditional","slug":"unicombine-unified-multi-conditional","title":"UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer","date":"2025-03-12","arxiv_id":"2503.09277","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unicombine-unified-multi-conditional#ran","syntology_url":"https://syntology.ai/paper/2503.09277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09277"}},"official":null}},{"url":null,"slug":"zero-shot-subject-centric-generation-for","title":"Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion","date":"2025-03-12","arxiv_id":"2503.10697","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-bayesian-nonparametric-framework-for","title":"A Deep Bayesian Nonparametric Framework for Robust Mutual Information Estimation","date":"2025-03-11","arxiv_id":"2503.08902","repositories_listed":0,"syntology":null},{"url":null,"slug":"garmentcrafter-progressive-novel-view","title":"GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing","date":"2025-03-11","arxiv_id":"2503.08678","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-robot-constitutions-benchmarks-for","title":"Generating Robot Constitutions & Benchmarks for Semantic Safety","date":"2025-03-11","arxiv_id":"2503.08663","repositories_listed":0,"syntology":null},{"url":null,"slug":"layton-latent-consistency-tokenizer-for-1024","title":"Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens","date":"2025-03-11","arxiv_id":"2503.08377","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-for-just-work-constructing-diverse","title":"AI for Just Work: Constructing Diverse Imaginations of AI beyond \"Replacing Humans\"","date":"2025-03-10","arxiv_id":"2503.08720","repositories_listed":0,"syntology":null},{"url":"/paper/can-generative-geospatial-diffusion-models","slug":"can-generative-geospatial-diffusion-models","title":"Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?","date":"2025-03-10","arxiv_id":"2503.07890","repositories_listed":0,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/can-generative-geospatial-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2503.07890","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07890"}},"official":null}},{"url":null,"slug":"easycontrol-adding-efficient-and-flexible","title":"EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer","date":"2025-03-10","arxiv_id":"2503.07027","repositories_listed":0,"syntology":null},{"url":null,"slug":"latexblend-scaling-multi-concept-customized","title":"LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending","date":"2025-03-10","arxiv_id":"2503.06956","repositories_listed":0,"syntology":null},{"url":null,"slug":"neas-3d-reconstruction-from-x-ray-images","title":"NeAS: 3D Reconstruction from X-ray Images using Neural Attenuation Surface","date":"2025-03-10","arxiv_id":"2503.07491","repositories_listed":0,"syntology":null},{"url":null,"slug":"nfig-autoregressive-image-generation-with","title":"NFIG: Autoregressive Image Generation with Next-Frequency Prediction","date":"2025-03-10","arxiv_id":"2503.07076","repositories_listed":0,"syntology":null},{"url":null,"slug":"nukesformers-unpaired-hyperspectral-image","title":"NukesFormers: Unpaired Hyperspectral Image Generation with Non-Uniform Domain Alignment","date":"2025-03-10","arxiv_id":"2503.07004","repositories_listed":0,"syntology":null},{"url":null,"slug":"post-training-quantization-for-diffusion","title":"Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping","date":"2025-03-10","arxiv_id":"2503.06930","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-lung-x-ray-generation-through-cross","title":"Synthetic Lung X-ray Generation through Cross-Attention and Affinity Transformation","date":"2025-03-10","arxiv_id":"2503.07209","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-to-image-diffusion-models-cannot-count","title":"Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help","date":"2025-03-10","arxiv_id":"2503.06884","repositories_listed":0,"syntology":null},{"url":null,"slug":"tide-temporal-aware-sparse-autoencoders-for","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation","date":"2025-03-10","arxiv_id":"2503.07050","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generalization-of-tactile-image","title":"Towards Generalization of Tactile Image Generation: Reference-Free Evaluation in a Leakage-Free Setting","date":"2025-03-10","arxiv_id":"2503.06860","repositories_listed":0,"syntology":null},{"url":null,"slug":"adding-additional-control-to-one-step","title":"Adding Additional Control to One-Step Diffusion with Joint Distribution Matching","date":"2025-03-09","arxiv_id":"2503.06652","repositories_listed":0,"syntology":null},{"url":null,"slug":"armor-v0-1-empowering-autoregressive","title":"ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy","date":"2025-03-09","arxiv_id":"2503.06542","repositories_listed":0,"syntology":null},{"url":null,"slug":"color-alignment-in-diffusion","title":"Color Alignment in Diffusion","date":"2025-03-09","arxiv_id":"2503.06746","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistent-image-layout-editing-with","title":"Consistent Image Layout Editing with Diffusion Models","date":"2025-03-09","arxiv_id":"2503.06419","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamicid-zero-shot-multi-id-image","title":"DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability","date":"2025-03-09","arxiv_id":"2503.06505","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixelponder-dynamic-patch-adaptation-for","title":"PixelPonder: Dynamic Patch Adaptation for Enhanced Multi-Conditional Text-to-Image Generation","date":"2025-03-09","arxiv_id":"2503.06684","repositories_listed":0,"syntology":null},{"url":null,"slug":"tr-dq-time-rotation-diffusion-quantization","title":"TR-DQ: Time-Rotation Diffusion Quantization","date":"2025-03-09","arxiv_id":"2503.06564","repositories_listed":0,"syntology":null},{"url":null,"slug":"disrupting-model-merging-a-parameter-level","title":"Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy","date":"2025-03-08","arxiv_id":"2503.07661","repositories_listed":0,"syntology":null},{"url":null,"slug":"text2story-advancing-video-storytelling-with","title":"Text2Story: Advancing Video Storytelling with Text Guidance","date":"2025-03-08","arxiv_id":"2503.06310","repositories_listed":0,"syntology":null},{"url":null,"slug":"vlforgery-face-triad-detection-localization","title":"VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models","date":"2025-03-08","arxiv_id":"2503.06142","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-autoregressive-image-generation","title":"Frequency Autoregressive Image Generation with Continuous Tokens","date":"2025-03-07","arxiv_id":"2503.05305","repositories_listed":0,"syntology":null},{"url":null,"slug":"laploss-laplacian-pyramid-based-multiscale","title":"LapLoss: Laplacian Pyramid-based Multiscale loss for Image Translation","date":"2025-03-07","arxiv_id":"2503.05974","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-guided-optimization-for-personalized","title":"Energy-Guided Optimization for Personalized Image Editing with Pretrained Text-to-Image Diffusion Models","date":"2025-03-06","arxiv_id":"2503.04215","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-is-an-elegant-gift-for","title":"Synthetic Data is an Elegant GIFT for Continual Vision-Language Models","date":"2025-03-06","arxiv_id":"2503.04229","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-generative-approach-to-high-fidelity-3d","title":"A Generative Approach to High Fidelity 3D Reconstruction from Text Data","date":"2025-03-05","arxiv_id":"2503.03664","repositories_listed":0,"syntology":null},{"url":null,"slug":"find-matching-faces-based-on-face-parameters","title":"Find Matching Faces Based On Face Parameters","date":"2025-03-05","arxiv_id":"2503.03204","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-depth-consistent-image-generation","title":"Multi-View Depth Consistent Image Generation Using Generative AI Models: Application on Architectural Design of University Buildings","date":"2025-03-05","arxiv_id":"2503.03068","repositories_listed":0,"syntology":null},{"url":null,"slug":"q-c-when-quantization-meets-cache-in","title":"Q&C: When Quantization Meets Cache in Efficient Image Generation","date":"2025-03-04","arxiv_id":"2503.02508","repositories_listed":0,"syntology":null},{"url":null,"slug":"rectifiedhr-enable-efficient-high-resolution","title":"RectifiedHR: Enable Efficient High-Resolution Image Generation via Energy Rectification","date":"2025-03-04","arxiv_id":"2503.02537","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-time-series-generation-via-schrodinger","title":"Robust time series generation via Schrödinger Bridge: a comprehensive evaluation","date":"2025-03-04","arxiv_id":"2503.02943","repositories_listed":0,"syntology":null},{"url":null,"slug":"teaching-metric-distance-to-autoregressive","title":"Teaching Metric Distance to Autoregressive Multimodal Foundational Models","date":"2025-03-04","arxiv_id":"2503.02379","repositories_listed":0,"syntology":null},{"url":null,"slug":"accord-alleviating-concept-coupling-through","title":"ACCORD: Alleviating Concept Coupling through Dependence Regularization for Text-to-Image Diffusion Personalization","date":"2025-03-03","arxiv_id":"2503.01122","repositories_listed":0,"syntology":null},{"url":null,"slug":"designdiffusion-high-quality-text-to-design","title":"DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models","date":"2025-03-03","arxiv_id":"2503.01645","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-retinal-vessel-segmentation","title":"Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling","date":"2025-03-03","arxiv_id":"2503.01190","repositories_listed":0,"syntology":null},{"url":null,"slug":"frmd-fast-robot-motion-diffusion-with","title":"FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action Generation","date":"2025-03-03","arxiv_id":"2503.02048","repositories_listed":0,"syntology":null},{"url":null,"slug":"handrawer-leveraging-spatial-information-to","title":"HanDrawer: Leveraging Spatial Information to Render Realistic Hands Using a Conditional Diffusion Model in Single Stage","date":"2025-03-03","arxiv_id":"2503.02127","repositories_listed":0,"syntology":null},{"url":null,"slug":"tactstyle-generating-tactile-textures-with","title":"TactStyle: Generating Tactile Textures with Generative AI for Digital Fabrication","date":"2025-03-03","arxiv_id":"2503.02007","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-improved-text-aligned-codebook","title":"Towards Improved Text-Aligned Codebook Learning: Multi-Hierarchical Codebook-Text Alignment with Long Text","date":"2025-03-03","arxiv_id":"2503.01261","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-00945","title":"Cross Modality Medical Image Synthesis for Improving Liver Segmentation","date":"2025-03-02","arxiv_id":"2503.00945","repositories_listed":0,"syntology":null},{"url":null,"slug":"2503-01019","title":"MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations","date":"2025-03-02","arxiv_id":"2503.01019","repositories_listed":0,"syntology":null},{"url":null,"slug":"development-of-an-unpaired-deep-neural","title":"Development of an Unpaired Deep Neural Network for Synthesizing X-ray Fluoroscopic Images from Digitally Reconstructed Tomography in Image Guided Radiotherapy","date":"2025-03-01","arxiv_id":"2503.00665","repositories_listed":0,"syntology":null},{"url":null,"slug":"2502-21318","title":"How far can we go with ImageNet for Text-to-Image generation?","date":"2025-02-28","arxiv_id":"2502.21318","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffbrush-just-painting-the-art-by-your-hands","title":"DiffBrush:Just Painting the Art by Your Hands","date":"2025-02-28","arxiv_id":"2502.20904","repositories_listed":0,"syntology":null},{"url":null,"slug":"safetext-safe-text-to-image-models-via","title":"SafeText: Safe Text-to-image Models via Aligning the Text Encoder","date":"2025-02-28","arxiv_id":"2502.20623","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-clip-s-performance-limitations-in","title":"Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study","date":"2025-02-27","arxiv_id":"2502.19828","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexidit-your-diffusion-transformer-can","title":"FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute","date":"2025-02-27","arxiv_id":"2502.20126","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-informed-hyperspectral-image","title":"Language-Informed Hyperspectral Image Synthesis for Imbalanced-Small Sample Classification via Semi-Supervised Conditional Diffusion Model","date":"2025-02-27","arxiv_id":"2502.19700","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-nephrographic-image-synthesis-in-ct","title":"3D Nephrographic Image Synthesis in CT Urography with the Diffusion Model and Swin Transformer","date":"2025-02-26","arxiv_id":"2502.19623","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-instruments-embodying-prompts-as","title":"AI-Instruments: Embodying Prompts as Instruments to Abstract & Reflect Graphical Interface Commands as General-Purpose Tools","date":"2025-02-26","arxiv_id":"2502.18736","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-contrastive-learning-for-tumor","title":"Multi-modal Contrastive Learning for Tumor-specific Missing Modality Synthesis","date":"2025-02-26","arxiv_id":"2502.19390","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimal-stochastic-trace-estimation-in","title":"Optimal Stochastic Trace Estimation in Generative Modeling","date":"2025-02-26","arxiv_id":"2502.18808","repositories_listed":0,"syntology":null},{"url":null,"slug":"asurvey-spatiotemporal-consistency-in-video","title":"ASurvey: Spatiotemporal Consistency in Video Generation","date":"2025-02-25","arxiv_id":"2502.17863","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-optimization-for-controlled-image","title":"Bayesian Optimization for Controlled Image Editing via LLMs","date":"2025-02-25","arxiv_id":"2502.18116","repositories_listed":0,"syntology":null},{"url":null,"slug":"ldgen-enhancing-text-to-image-synthesis-via","title":"LDGen: Enhancing Text-to-Image Synthesis via Large Language Model-Driven Language Representation","date":"2025-02-25","arxiv_id":"2502.18302","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-polyp-detection-and-diagnosis-through","title":"Robust Polyp Detection and Diagnosis through Compositional Prompt-Guided Diffusion Models","date":"2025-02-25","arxiv_id":"2502.17951","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-pragmatic-note-on-evaluating-generative","title":"A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis","date":"2025-02-24","arxiv_id":"2502.17160","repositories_listed":0,"syntology":null},{"url":null,"slug":"autoregressive-image-generation-guided-by","title":"Autoregressive Image Generation Guided by Chains of Thought","date":"2025-02-24","arxiv_id":"2502.16965","repositories_listed":0,"syntology":null},{"url":null,"slug":"culture-trip-culturally-aware-text-to-image","title":"Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement","date":"2025-02-24","arxiv_id":"2502.16902","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributional-vision-language-alignment-by","title":"Distributional Vision-Language Alignment by Cauchy-Schwarz Divergence","date":"2025-02-24","arxiv_id":"2502.17028","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthrad2025-grand-challenge-dataset","title":"SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapy","date":"2025-02-24","arxiv_id":"2502.17609","repositories_listed":0,"syntology":null},{"url":null,"slug":"iterative-flow-matching-path-correction-and","title":"Iterative Flow Matching -- Path Correction and Gradual Refinement for Enhanced Generative Modeling","date":"2025-02-23","arxiv_id":"2502.16445","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-prompt-attack-against-text-to-image","title":"Unified Prompt Attack Against Text-to-Image Generation Models","date":"2025-02-23","arxiv_id":"2502.16423","repositories_listed":0,"syntology":null},{"url":null,"slug":"dualnerf-text-driven-3d-scene-editing-via","title":"DualNeRF: Text-Driven 3D Scene Editing via Dual-Field Representation","date":"2025-02-22","arxiv_id":"2502.16302","repositories_listed":0,"syntology":null},{"url":null,"slug":"flipconcept-tuning-free-multi-concept","title":"FlipConcept: Tuning-Free Multi-Concept Personalization for Text-to-Image Generation","date":"2025-02-21","arxiv_id":"2502.15203","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-step-diffusion-models-with-f-divergence","title":"One-step Diffusion Models with $f$-Divergence Distribution Matching","date":"2025-02-21","arxiv_id":"2502.15681","repositories_listed":0,"syntology":null},{"url":null,"slug":"dc-controlnet-decoupling-inter-and-intra","title":"DC-ControlNet: Decoupling Inter- and Intra-Element Conditions in Image Generation with Diffusion Models","date":"2025-02-20","arxiv_id":"2502.14779","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-modeling-of-individual-behavior-at","title":"Generative Modeling of Individual Behavior at Scale","date":"2025-02-20","arxiv_id":"2502.14998","repositories_listed":0,"syntology":null},{"url":"/paper/improving-the-diffusability-of-autoencoders","slug":"improving-the-diffusability-of-autoencoders","title":"Improving the Diffusability of Autoencoders","date":"2025-02-20","arxiv_id":"2502.14831","repositories_listed":0,"syntology":null},{"url":null,"slug":"flextok-resampling-images-into-1d-token","title":"FlexTok: Resampling Images into 1D Token Sequences of Flexible Length","date":"2025-02-19","arxiv_id":"2502.13967","repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-based-generative-models-as-iterative","title":"Flow-based generative models as iterative algorithms in probability space","date":"2025-02-19","arxiv_id":"2502.13394","repositories_listed":0,"syntology":null},{"url":null,"slug":"ip-composer-semantic-composition-of-visual","title":"IP-Composer: Semantic Composition of Visual Concepts","date":"2025-02-19","arxiv_id":"2502.13951","repositories_listed":0,"syntology":null},{"url":null,"slug":"magicgeo-training-free-text-guided-geometric","title":"MagicGeo: Training-Free Text-Guided Geometric Diagram Generation","date":"2025-02-19","arxiv_id":"2502.13855","repositories_listed":0,"syntology":null},{"url":null,"slug":"spherical-dense-text-to-image-synthesis","title":"Spherical Dense Text-to-Image Synthesis","date":"2025-02-18","arxiv_id":"2502.12691","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-bridging-eeg-signals-and","title":"A Survey on Bridging EEG Signals and Generative AI: From Image and Text to Beyond","date":"2025-02-17","arxiv_id":"2502.12048","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphgpt-o-synergistic-multimodal","title":"GRAPHGPT-O: Synergistic Multimodal Comprehension and Generation on Graphs","date":"2025-02-17","arxiv_id":"2502.11925","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-faceted-multimodal-monosemanticity","title":"Multi-Faceted Multimodal Monosemanticity","date":"2025-02-16","arxiv_id":"2502.14888","repositories_listed":0,"syntology":null},{"url":null,"slug":"manitrend-bridging-future-generation-and","title":"ManiTrend: Bridging Future Generation and Action Prediction with 3D Flow for Robotic Manipulation","date":"2025-02-14","arxiv_id":"2502.10028","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-a-conditional-prior-distribution","title":"Designing a Conditional Prior Distribution for Flow-Based Generative Models","date":"2025-02-13","arxiv_id":"2502.09611","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-malicious-concepts-without-image","title":"Detecting Malicious Concepts Without Image Generation in AIGC","date":"2025-02-13","arxiv_id":"2502.08921","repositories_listed":0,"syntology":null},{"url":null,"slug":"eq-vae-equivariance-regularized-latent-space","title":"EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling","date":"2025-02-13","arxiv_id":"2502.09509","repositories_listed":0,"syntology":null},{"url":null,"slug":"imagerag-dynamic-image-retrieval-for","title":"ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation","date":"2025-02-13","arxiv_id":"2502.09411","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-the-lm-misunderstood-the-human-chuckled","title":"When the LM misunderstood the human chuckled: Analyzing garden path effects in humans and language models","date":"2025-02-13","arxiv_id":"2502.09307","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-pre-trained-diffusion-model","title":"A Survey on Pre-Trained Diffusion Model Distillations","date":"2025-02-12","arxiv_id":"2502.08364","repositories_listed":0,"syntology":null},{"url":null,"slug":"bcddm-branch-corrected-denoising-diffusion","title":"BCDDM: Branch-Corrected Denoising Diffusion Model for Black Hole Image Generation","date":"2025-02-12","arxiv_id":"2502.08528","repositories_listed":0,"syntology":null},{"url":null,"slug":"id-cloak-crafting-identity-specific-cloaks","title":"ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation","date":"2025-02-12","arxiv_id":"2502.08097","repositories_listed":0,"syntology":null},{"url":null,"slug":"pogdiff-product-of-gaussians-diffusion-models","title":"PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation","date":"2025-02-12","arxiv_id":"2502.08106","repositories_listed":0,"syntology":null}],"record_sha256":"f39a77303c299e37ce6b77e0aed0cb3e866182669b1c51b6f00a892a9e1f3ca6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}