{"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/35","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":35,"pages_in_order":67,"rows_per_page":100,"rows":[3401,3500],"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/34","next":"/task/image-generation/papers/36","papers":[{"url":"/paper/training-free-dense-aligned-diffusion","slug":"training-free-dense-aligned-diffusion","title":"Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis","date":"2025-04-02","arxiv_id":"2504.01515","repositories_listed":0,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/training-free-dense-aligned-diffusion#ran","syntology_url":"https://syntology.ai/paper/2504.01515","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01515"}},"official":null}},{"url":null,"slug":"geometric-median-matching-for-robust-k-subset","title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data","date":"2025-04-01","arxiv_id":"2504.00564","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompting-forgetting-unlearning-in-gans-via","title":"Prompting Forgetting: Unlearning in GANs via Textual Guidance","date":"2025-04-01","arxiv_id":"2504.01218","repositories_listed":0,"syntology":null},{"url":null,"slug":"shieldgemma-2-robust-and-tractable-image","title":"ShieldGemma 2: Robust and Tractable Image Content Moderation","date":"2025-04-01","arxiv_id":"2504.01081","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-complex-prompts-to-identify-fine","title":"Using complex prompts to identify fine-grained biases in image generation through ChatGPT-4o","date":"2025-04-01","arxiv_id":"2504.00388","repositories_listed":0,"syntology":null},{"url":null,"slug":"detail-aware-multi-view-stereo-network-for","title":"Detail-aware multi-view stereo network for depth estimation","date":"2025-03-31","arxiv_id":"2503.23684","repositories_listed":0,"syntology":null},{"url":null,"slug":"erupt-efficient-rendering-with-unposed-patch","title":"ERUPT: Efficient Rendering with Unposed Patch Transformer","date":"2025-03-31","arxiv_id":"2503.24374","repositories_listed":0,"syntology":null},{"url":null,"slug":"fakescope-large-multimodal-expert-model-for","title":"FakeScope: Large Multimodal Expert Model for Transparent AI-Generated Image Forensics","date":"2025-03-31","arxiv_id":"2503.24267","repositories_listed":0,"syntology":null},{"url":null,"slug":"rig-synergizing-reasoning-and-imagination-in","title":"RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy","date":"2025-03-31","arxiv_id":"2503.24388","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-packet-aggregation-and-repeated","title":"Semantic Packet Aggregation and Repeated Transmission for Text-to-Image Generation","date":"2025-03-31","arxiv_id":"2503.23734","repositories_listed":0,"syntology":null},{"url":null,"slug":"sonarsplat-novel-view-synthesis-of-imaging","title":"SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting","date":"2025-03-31","arxiv_id":"2504.00159","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-analysis-of-gender-biases-in","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","date":"2025-03-30","arxiv_id":"2503.23398","repositories_listed":0,"syntology":null},{"url":null,"slug":"dit4sr-taming-diffusion-transformer-for-real","title":"DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution","date":"2025-03-30","arxiv_id":"2503.23580","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-guided-trajectory-traversal-in","title":"Language-Guided Trajectory Traversal in Disentangled Stable Diffusion Latent Space for Factorized Medical Image Generation","date":"2025-03-30","arxiv_id":"2503.23623","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-vision-language-foundation-models-1","title":"Leveraging Vision-Language Foundation Models to Reveal Hidden Image-Attribute Relationships in Medical Imaging","date":"2025-03-30","arxiv_id":"2503.23618","repositories_listed":0,"syntology":null},{"url":null,"slug":"make-autoregressive-great-again-diffusion","title":"Make Autoregressive Great Again: Diffusion-Free Graph Generation with Next-Scale Prediction","date":"2025-03-30","arxiv_id":"2503.23612","repositories_listed":0,"syntology":null},{"url":null,"slug":"quantum-generative-models-for-image","title":"Quantum Generative Models for Image Generation: Insights from MNIST and MedMNIST","date":"2025-03-30","arxiv_id":"2504.00034","repositories_listed":0,"syntology":null},{"url":null,"slug":"tracemark-ldm-authenticatable-watermarking","title":"TraceMark-LDM: Authenticatable Watermarking for Latent Diffusion Models via Binary-Guided Rearrangement","date":"2025-03-30","arxiv_id":"2503.23332","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-geometrical-properties-of-text-token","title":"On Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation","date":"2025-03-29","arxiv_id":"2503.23011","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-interpretable-counterfactual","title":"Towards Interpretable Counterfactual Generation via Multimodal Autoregression","date":"2025-03-29","arxiv_id":"2503.23149","repositories_listed":0,"syntology":null},{"url":null,"slug":"ditfastattnv2-head-wise-attention-compression","title":"DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers","date":"2025-03-28","arxiv_id":"2503.22796","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluation-of-machine-generated-biomedical","title":"Evaluation of Machine-generated Biomedical Images via A Tally-based Similarity Measure","date":"2025-03-28","arxiv_id":"2503.22658","repositories_listed":0,"syntology":null},{"url":null,"slug":"origen-zero-shot-3d-orientation-grounding-in","title":"ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation","date":"2025-03-28","arxiv_id":"2503.22194","repositories_listed":0,"syntology":null},{"url":null,"slug":"patronus-bringing-transparency-to-diffusion","title":"Patronus: Bringing Transparency to Diffusion Models with Prototypes","date":"2025-03-28","arxiv_id":"2503.22782","repositories_listed":0,"syntology":null},{"url":null,"slug":"sell-it-before-you-make-it-revolutionizing-e","title":"Sell It Before You Make It: Revolutionizing E-Commerce with Personalized AI-Generated Items","date":"2025-03-28","arxiv_id":"2503.22182","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-transport-optimization-by","title":"Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis","date":"2025-03-28","arxiv_id":"2503.22168","repositories_listed":0,"syntology":null},{"url":null,"slug":"3dgen-bench-comprehensive-benchmark-suite-for","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models","date":"2025-03-27","arxiv_id":"2503.21745","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-framework-for-diffusion-bridge","title":"A Unified Framework for Diffusion Bridge Problems: Flow Matching and Schrödinger Matching into One","date":"2025-03-27","arxiv_id":"2503.21756","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctrl-o-language-controllable-object-centric","title":"CTRL-O: Language-Controllable Object-Centric Visual Representation Learning","date":"2025-03-27","arxiv_id":"2503.21747","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-multi-instance-generation-with","title":"Efficient Multi-Instance Generation with Janus-Pro-Dirven Prompt Parsing","date":"2025-03-27","arxiv_id":"2503.21069","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-text-to-image-synthesis-with-a","title":"Evaluating Text-to-Image Synthesis with a Conditional Fréchet Distance","date":"2025-03-27","arxiv_id":"2503.21721","repositories_listed":0,"syntology":null},{"url":null,"slug":"lex-art-rethinking-text-generation-via","title":"LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis","date":"2025-03-27","arxiv_id":"2503.21749","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-as-a-game-on-numerical-and-spatial","title":"Model as a Game: On Numerical and Spatial Consistency for Generative Games","date":"2025-03-27","arxiv_id":"2503.21172","repositories_listed":0,"syntology":null},{"url":null,"slug":"ugen-unified-autoregressive-multimodal-model","title":"UGen: Unified Autoregressive Multimodal Model with Progressive Vocabulary Learning","date":"2025-03-27","arxiv_id":"2503.21193","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-words-advancing-long-text-image","title":"Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models","date":"2025-03-26","arxiv_id":"2503.20198","repositories_listed":0,"syntology":null},{"url":null,"slug":"bizgen-advancing-article-level-visual-text","title":"BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation","date":"2025-03-26","arxiv_id":"2503.20672","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-quality-diffusion-distillation-on-a","title":"High Quality Diffusion Distillation on a Single GPU with Relative and Absolute Position Matching","date":"2025-03-26","arxiv_id":"2503.20744","repositories_listed":0,"syntology":null},{"url":null,"slug":"mmgen-unified-multi-modal-image-generation","title":"MMGen: Unified Multi-modal Image Generation and Understanding in One Go","date":"2025-03-26","arxiv_id":"2503.20644","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-disentangled-and-controllable-human","title":"Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage","date":"2025-03-25","arxiv_id":"2503.19486","repositories_listed":0,"syntology":null},{"url":null,"slug":"layercraft-enhancing-text-to-image-generation","title":"LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration","date":"2025-03-25","arxiv_id":"2504.00010","repositories_listed":0,"syntology":null},{"url":null,"slug":"pcm-picard-consistency-model-for-fast","title":"PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models","date":"2025-03-25","arxiv_id":"2503.19731","repositories_listed":0,"syntology":null},{"url":null,"slug":"reverse-prompt-cracking-the-recipe-inside","title":"Reverse Prompt: Cracking the Recipe Inside Text-to-Image Generation","date":"2025-03-25","arxiv_id":"2503.19937","repositories_listed":0,"syntology":null},{"url":null,"slug":"vectorfit-adaptive-singular-bias-vector-fine","title":"VectorFit : Adaptive Singular & Bias Vector Fine-Tuning of Pre-trained Foundation Models","date":"2025-03-25","arxiv_id":"2503.19530","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-resolution-generalization-of","title":"Boosting Resolution Generalization of Diffusion Transformers with Randomized Positional Encodings","date":"2025-03-24","arxiv_id":"2503.18719","repositories_listed":0,"syntology":null},{"url":null,"slug":"plug-and-play-interpretable-responsible-text","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","date":"2025-03-24","arxiv_id":"2503.18324","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-diffusion-acceleration-with","title":"Training-free Diffusion Acceleration with Bottleneck Sampling","date":"2025-03-24","arxiv_id":"2503.18940","repositories_listed":0,"syntology":null},{"url":null,"slug":"adoption-of-watermarking-for-generative-ai","title":"Adoption of Watermarking Measures for AI-Generated Content and Implications under the EU AI Act","date":"2025-03-23","arxiv_id":"2503.18156","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-image-like-diffusion-method-for-human","title":"An Image-like Diffusion Method for Human-Object Interaction Detection","date":"2025-03-23","arxiv_id":"2503.18134","repositories_listed":0,"syntology":null},{"url":null,"slug":"tcfg-tangential-damping-classifier-free","title":"TCFG: Tangential Damping Classifier-free Guidance","date":"2025-03-23","arxiv_id":"2503.18137","repositories_listed":0,"syntology":null},{"url":null,"slug":"transanimate-taming-layer-diffusion-to","title":"TransAnimate: Taming Layer Diffusion to Generate RGBA Video","date":"2025-03-23","arxiv_id":"2503.17934","repositories_listed":0,"syntology":null},{"url":null,"slug":"comfygpt-a-self-optimizing-multi-agent-system","title":"ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation","date":"2025-03-22","arxiv_id":"2503.17671","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynasyn-multi-subject-personalization","title":"DynASyn: Multi-Subject Personalization Enabling Dynamic Action Synthesis","date":"2025-03-22","arxiv_id":"2503.17728","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-diffusion-training-through","title":"Efficient Diffusion Training through Parallelization with Truncated Karhunen-Loève Expansion","date":"2025-03-22","arxiv_id":"2503.17657","repositories_listed":0,"syntology":null},{"url":null,"slug":"fundusgan-a-hierarchical-feature-aware","title":"FundusGAN: A Hierarchical Feature-Aware Generative Framework for High-Fidelity Fundus Image Generation","date":"2025-03-22","arxiv_id":"2503.17831","repositories_listed":0,"syntology":null},{"url":null,"slug":"omr-diffusion-optimizing-multi-round-enhanced","title":"OMR-Diffusion:Optimizing Multi-Round Enhanced Training in Diffusion Models for Improved Intent Understanding","date":"2025-03-22","arxiv_id":"2503.17660","repositories_listed":0,"syntology":null},{"url":null,"slug":"tdri-two-phase-dialogue-refinement-and-co","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","date":"2025-03-22","arxiv_id":"2503.17669","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-generative-models-can-flag","title":"Bayesian generative models can flag performance loss, bias, and out-of-distribution image content","date":"2025-03-21","arxiv_id":"2503.17477","repositories_listed":0,"syntology":null},{"url":null,"slug":"d2c-unlocking-the-potential-of-continuous","title":"D2C: Unlocking the Potential of Continuous Autoregressive Image Generation with Discrete Tokens","date":"2025-03-21","arxiv_id":"2503.17155","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-text-to-image-generation-for","title":"Leveraging Text-to-Image Generation for Handling Spurious Correlation","date":"2025-03-21","arxiv_id":"2503.17226","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-styled-text-image-generation-but","title":"Zero-Shot Styled Text Image Generation, but Make It Autoregressive","date":"2025-03-21","arxiv_id":"2503.17074","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-fmri-based-brain-decoding-for","title":"A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli","date":"2025-03-20","arxiv_id":"2503.15978","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention2d-communication-efficient","title":"ATTENTION2D: Communication Efficient Distributed Self-Attention Mechanism","date":"2025-03-20","arxiv_id":"2503.15758","repositories_listed":0,"syntology":null},{"url":null,"slug":"edit-efficient-diffusion-transformers-with","title":"EDiT: Efficient Diffusion Transformers with Linear Compressed Attention","date":"2025-03-20","arxiv_id":"2503.16726","repositories_listed":0,"syntology":null},{"url":null,"slug":"freeflux-understanding-and-exploiting-layer","title":"FreeFlux: Understanding and Exploiting Layer-Specific Roles in RoPE-Based MMDiT for Versatile Image Editing","date":"2025-03-20","arxiv_id":"2503.16153","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-autoregressive-image-generation","title":"Improving Autoregressive Image Generation through Coarse-to-Fine Token Prediction","date":"2025-03-20","arxiv_id":"2503.16194","repositories_listed":0,"syntology":null},{"url":null,"slug":"lapig-cross-modal-generation-of-paired","title":"LaPIG: Cross-Modal Generation of Paired Thermal and Visible Facial Images","date":"2025-03-20","arxiv_id":"2503.16376","repositories_listed":0,"syntology":null},{"url":null,"slug":"promptmobile-efficient-promptus-for-low","title":"PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming","date":"2025-03-20","arxiv_id":"2503.16112","repositories_listed":0,"syntology":null},{"url":null,"slug":"rl4med-ddpo-reinforcement-learning-for","title":"RL4Med-DDPO: Reinforcement Learning for Controlled Guidance Towards Diverse Medical Image Generation using Vision-Language Foundation Models","date":"2025-03-20","arxiv_id":"2503.15784","repositories_listed":0,"syntology":null},{"url":null,"slug":"world-knowledge-from-ai-image-generation-for","title":"World Knowledge from AI Image Generation for Robot Control","date":"2025-03-20","arxiv_id":"2503.16579","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-deep-learning-through-probability","title":"Advancing Deep Learning through Probability Engineering: A Pragmatic Paradigm for Modern AI","date":"2025-03-19","arxiv_id":"2503.18958","repositories_listed":0,"syntology":null},{"url":null,"slug":"conjuring-positive-pairs-for-efficient","title":"Conjuring Positive Pairs for Efficient Unification of Representation Learning and Image Synthesis","date":"2025-03-19","arxiv_id":"2503.15060","repositories_listed":0,"syntology":null},{"url":null,"slug":"di-mathtt-m-o-distilling-masked-diffusion","title":"Di$\\mathtt{[M]}$O: Distilling Masked Diffusion Models into One-step Generator","date":"2025-03-19","arxiv_id":"2503.15457","repositories_listed":0,"syntology":null},{"url":null,"slug":"fetalflex-anatomy-guided-diffusion-model-for","title":"FetalFlex: Anatomy-Guided Diffusion Model for Flexible Control on Fetal Ultrasound Image Synthesis","date":"2025-03-19","arxiv_id":"2503.14906","repositories_listed":0,"syntology":null},{"url":null,"slug":"guardians-of-generation-dynamic-inference","title":"Guardians of Generation: Dynamic Inference-Time Copyright Shielding with Adaptive Guidance for AI Image Generation","date":"2025-03-19","arxiv_id":"2503.16171","repositories_listed":0,"syntology":null},{"url":null,"slug":"tf-ti2i-training-free-text-and-image-to-image","title":"TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models","date":"2025-03-19","arxiv_id":"2503.15283","repositories_listed":0,"syntology":null},{"url":null,"slug":"deeply-supervised-flow-based-generative","title":"Deeply Supervised Flow-Based Generative Models","date":"2025-03-18","arxiv_id":"2503.14494","repositories_listed":0,"syntology":null},{"url":null,"slug":"defectfill-realistic-defect-generation-with","title":"DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection","date":"2025-03-18","arxiv_id":"2503.13985","repositories_listed":0,"syntology":null},{"url":"/paper/diffmoe-dynamic-token-selection-for-scalable","slug":"diffmoe-dynamic-token-selection-for-scalable","title":"DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers","date":"2025-03-18","arxiv_id":"2503.14487","repositories_listed":0,"syntology":null},{"url":null,"slug":"free-lunch-color-texture-disentanglement-for","title":"Free-Lunch Color-Texture Disentanglement for Stylized Image Generation","date":"2025-03-18","arxiv_id":"2503.14275","repositories_listed":0,"syntology":null},{"url":null,"slug":"ice-bench-a-unified-and-comprehensive","title":"ICE-Bench: A Unified and Comprehensive Benchmark for Image Creating and Editing","date":"2025-03-18","arxiv_id":"2503.14482","repositories_listed":0,"syntology":null},{"url":null,"slug":"whole-body-image-to-image-translation-for-a","title":"Whole-Body Image-to-Image Translation for a Virtual Scanner in a Healthcare Digital Twin","date":"2025-03-18","arxiv_id":"2503.15555","repositories_listed":0,"syntology":null},{"url":null,"slug":"blobctrl-a-unified-and-flexible-framework-for","title":"BlobCtrl: A Unified and Flexible Framework for Element-level Image Generation and Editing","date":"2025-03-17","arxiv_id":"2503.13434","repositories_listed":0,"syntology":null},{"url":null,"slug":"dreamrenderer-taming-multi-instance-attribute","title":"DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models","date":"2025-03-17","arxiv_id":"2503.12885","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-autoregressive-visual-generation-and","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","date":"2025-03-17","arxiv_id":"2503.13436","repositories_listed":0,"syntology":null},{"url":null,"slug":"editid-training-free-editable-id","title":"EditID: Training-Free Editable ID Customization for Text-to-Image Generation","date":"2025-03-16","arxiv_id":"2503.12526","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalize-anything-for-free-with-diffusion","title":"Personalize Anything for Free with Diffusion Transformer","date":"2025-03-16","arxiv_id":"2503.12590","repositories_listed":0,"syntology":null},{"url":"/paper/diffad-a-unified-diffusion-modeling-approach","slug":"diffad-a-unified-diffusion-modeling-approach","title":"DiffAD: A Unified Diffusion Modeling Approach for Autonomous Driving","date":"2025-03-15","arxiv_id":"2503.12170","repositories_listed":0,"syntology":null},{"url":null,"slug":"lapig-language-guided-projector-image","title":"LAPIG: Language Guided Projector Image Generation with Surface Adaptation and Stylization","date":"2025-03-15","arxiv_id":"2503.12173","repositories_listed":0,"syntology":null},{"url":null,"slug":"direction-aware-diagonal-autoregressive-image","title":"Direction-Aware Diagonal Autoregressive Image Generation","date":"2025-03-14","arxiv_id":"2503.11129","repositories_listed":0,"syntology":null},{"url":null,"slug":"flow-to-the-mode-mode-seeking-diffusion","title":"Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization","date":"2025-03-14","arxiv_id":"2503.11056","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-var-safe-visual-autoregressive-model-for","title":"Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking","date":"2025-03-14","arxiv_id":"2503.11324","repositories_listed":0,"syntology":null},{"url":null,"slug":"conceptguard-continual-personalized-text-to","title":"ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation","date":"2025-03-13","arxiv_id":"2503.10358","repositories_listed":0,"syntology":null},{"url":null,"slug":"dit-air-revisiting-the-efficiency-of","title":"DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation","date":"2025-03-13","arxiv_id":"2503.10618","repositories_listed":0,"syntology":null},{"url":null,"slug":"do-i-look-like-a-cat-n-01-to-you-a-taxonomy","title":"Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark","date":"2025-03-13","arxiv_id":"2503.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"extremeaigc-benchmarking-lmm-vulnerability-to","title":"ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Content","date":"2025-03-13","arxiv_id":"2503.09964","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-efficient-3d-high-resolution-medical","title":"Memory-Efficient 3D High-Resolution Medical Image Synthesis Using CRF-Guided GANs","date":"2025-03-13","arxiv_id":"2503.10899","repositories_listed":0,"syntology":null},{"url":null,"slug":"plangen-towards-unified-layout-planning-and","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","date":"2025-03-13","arxiv_id":"2503.10127","repositories_listed":0,"syntology":null},{"url":null,"slug":"proxy-tuning-tailoring-multimodal","title":"Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation","date":"2025-03-13","arxiv_id":"2503.10125","repositories_listed":0,"syntology":null},{"url":"/paper/realgeneral-unifying-visual-generation-via","slug":"realgeneral-unifying-visual-generation-via","title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","date":"2025-03-13","arxiv_id":"2503.10406","repositories_listed":0,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/realgeneral-unifying-visual-generation-via#ran","syntology_url":"https://syntology.ai/paper/2503.10406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10406"}},"official":null}},{"url":null,"slug":"visual-polarization-measurement-using","title":"Visual Polarization Measurement Using Counterfactual Image Generation","date":"2025-03-13","arxiv_id":"2503.10738","repositories_listed":0,"syntology":null}],"record_sha256":"26c9ed0c0c9a7db80e1ba9b55cc23e79244a1ebc473d6cf54f2facf835d9f627","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}