{"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/34","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":34,"pages_in_order":67,"rows_per_page":100,"rows":[3301,3400],"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/33","next":"/task/image-generation/papers/35","papers":[{"url":null,"slug":"discrete-spatial-diffusion-intensity","title":"Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling","date":"2025-05-03","arxiv_id":"2505.01917","repositories_listed":0,"syntology":null},{"url":null,"slug":"ragar-retrieval-augment-personalized-image","title":"RAGAR: Retrieval Augment Personalized Image Generation Guided by Recommendation","date":"2025-05-03","arxiv_id":"2505.01657","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-editability-in-image-generation","title":"Improving Editability in Image Generation with Layer-wise Memory","date":"2025-05-02","arxiv_id":"2505.01079","repositories_listed":0,"syntology":null},{"url":null,"slug":"worldgenbench-a-world-knowledge-integrated","title":"WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation","date":"2025-05-02","arxiv_id":"2505.01490","repositories_listed":0,"syntology":null},{"url":null,"slug":"jointdit-enhancing-rgb-depth-joint-modeling","title":"JointDiT: Enhancing RGB-Depth Joint Modeling with Diffusion Transformers","date":"2025-05-01","arxiv_id":"2505.00482","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-compress-what-you-can-generate-when-gpt","title":"Why Compress What You Can Generate? When GPT-4o Generation Ushers in Image Compression Fields","date":"2025-04-30","arxiv_id":"2504.21814","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-picture-is-worth-a-thousand-prompts","title":"A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks","date":"2025-04-29","arxiv_id":"2504.20340","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-listener-dyadic-facial-motion","title":"Efficient Listener: Dyadic Facial Motion Synthesis via Action Diffusion","date":"2025-04-29","arxiv_id":"2504.20685","repositories_listed":0,"syntology":null},{"url":null,"slug":"inception-jailbreak-the-memory-mechanism-of","title":"Inception: Jailbreak the Memory Mechanism of Text-to-Image Generation Systems","date":"2025-04-29","arxiv_id":"2504.20376","repositories_listed":0,"syntology":null},{"url":null,"slug":"yochameleon-personalized-vision-and-language","title":"YoChameleon: Personalized Vision and Language Generation","date":"2025-04-29","arxiv_id":"2504.20998","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-driven-universal-model-inversion","title":"DiffUMI: Training-Free Universal Model Inversion via Unconditional Diffusion for Face Recognition","date":"2025-04-25","arxiv_id":"2504.18015","repositories_listed":0,"syntology":null},{"url":null,"slug":"hepatogen-generating-hepatobiliary-phase-mri","title":"HepatoGEN: Generating Hepatobiliary Phase MRI with Perceptual and Adversarial Models","date":"2025-04-25","arxiv_id":"2504.18405","repositories_listed":0,"syntology":null},{"url":null,"slug":"drc-enhancing-personalized-image-generation","title":"DRC: Enhancing Personalized Image Generation via Disentangled Representation Composition","date":"2025-04-24","arxiv_id":"2504.17349","repositories_listed":0,"syntology":null},{"url":"/paper/fashionm3-multimodal-multitask-and-multiround","slug":"fashionm3-multimodal-multitask-and-multiround","title":"FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model","date":"2025-04-24","arxiv_id":"2504.17826","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-autoregressive-models-for-continuous","title":"Fast Autoregressive Models for Continuous Latent Generation","date":"2025-04-24","arxiv_id":"2504.18391","repositories_listed":0,"syntology":null},{"url":null,"slug":"refvnli-towards-scalable-evaluation-of","title":"RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation","date":"2025-04-24","arxiv_id":"2504.17502","repositories_listed":0,"syntology":null},{"url":null,"slug":"token-shuffle-towards-high-resolution-image","title":"Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models","date":"2025-04-24","arxiv_id":"2504.17789","repositories_listed":0,"syntology":null},{"url":null,"slug":"distilling-semantically-aware-orders-for","title":"Distilling semantically aware orders for autoregressive image generation","date":"2025-04-23","arxiv_id":"2504.17069","repositories_listed":0,"syntology":null},{"url":null,"slug":"epbr-extended-pbr-materials-in-image","title":"ePBR: Extended PBR Materials in Image Synthesis","date":"2025-04-23","arxiv_id":"2504.17062","repositories_listed":0,"syntology":null},{"url":null,"slug":"univg-a-generalist-diffusion-model-for","title":"UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing","date":"2025-04-22","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"acquire-and-then-adapt-squeezing-out-text-to","title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","date":"2025-04-21","arxiv_id":"2504.15159","repositories_listed":0,"syntology":null},{"url":null,"slug":"emergence-and-evolution-of-interpretable","title":"Emergence and Evolution of Interpretable Concepts in Diffusion Models","date":"2025-04-21","arxiv_id":"2504.15473","repositories_listed":0,"syntology":null},{"url":null,"slug":"twig-two-step-image-generation-using","title":"TWIG: Two-Step Image Generation using Segmentation Masks in Diffusion Models","date":"2025-04-21","arxiv_id":"2504.14933","repositories_listed":0,"syntology":null},{"url":null,"slug":"twin-co-adaptive-dialogue-for-progressive","title":"Twin Co-Adaptive Dialogue for Progressive Image Generation","date":"2025-04-21","arxiv_id":"2504.14868","repositories_listed":0,"syntology":null},{"url":null,"slug":"vistadepth-frequency-modulation-with-bias","title":"VistaDepth: Frequency Modulation With Bias Reweighting For Enhanced Long-Range Depth Estimation","date":"2025-04-21","arxiv_id":"2504.15095","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-lurks-within-concept-auditing-for-shared","title":"What Lurks Within? Concept Auditing for Shared Diffusion Models at Scale","date":"2025-04-21","arxiv_id":"2504.14815","repositories_listed":0,"syntology":null},{"url":null,"slug":"causal-disentanglement-for-robust-long-tail","title":"Causal Disentanglement for Robust Long-tail Medical Image Generation","date":"2025-04-20","arxiv_id":"2504.14450","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-multimodal-pretraining-with","title":"Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens","date":"2025-04-20","arxiv_id":"2504.14666","repositories_listed":0,"syntology":null},{"url":null,"slug":"redediting-relationship-driven-precise","title":"REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models","date":"2025-04-20","arxiv_id":"2504.14554","repositories_listed":0,"syntology":null},{"url":null,"slug":"vgnc-reducing-the-overfitting-of-sparse-view","title":"VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control","date":"2025-04-20","arxiv_id":"2504.14548","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-language-patterns-of-prompts-in","title":"Exploring Language Patterns of Prompts in Text-to-Image Generation and Their Impact on Visual Diversity","date":"2025-04-19","arxiv_id":"2504.14125","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-joint-id-textual-representation-for","title":"Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis","date":"2025-04-19","arxiv_id":"2504.14202","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-generative-ai-models-to-explore","title":"Leveraging Generative AI Models to Explore Human Identity","date":"2025-04-19","arxiv_id":"2505.14843","repositories_listed":0,"syntology":null},{"url":null,"slug":"prism-a-unified-framework-for-photorealistic","title":"PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling","date":"2025-04-19","arxiv_id":"2504.14219","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-audio-visual-conditioned-diffusion-model","title":"Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction","date":"2025-04-19","arxiv_id":"2504.14267","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-explainable-fake-image-detection-with","title":"Towards Explainable Fake Image Detection with Multi-Modal Large Language Models","date":"2025-04-19","arxiv_id":"2504.14245","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-nsfw-free-text-to-image-generation","title":"Towards NSFW-Free Text-to-Image Generation via Safety-Constraint Direct Preference Optimization","date":"2025-04-19","arxiv_id":"2504.14290","repositories_listed":0,"syntology":null},{"url":null,"slug":"collective-learning-mechanism-based-optimal","title":"Collective Learning Mechanism based Optimal Transport Generative Adversarial Network for Non-parallel Voice Conversion","date":"2025-04-18","arxiv_id":"2504.13791","repositories_listed":0,"syntology":null},{"url":null,"slug":"early-timestep-zero-shot-candidate-selection","title":"Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing","date":"2025-04-18","arxiv_id":"2504.13490","repositories_listed":0,"syntology":null},{"url":null,"slug":"entropy-rectifying-guidance-for-diffusion-and","title":"Entropy Rectifying Guidance for Diffusion and Flow Models","date":"2025-04-18","arxiv_id":"2504.13987","repositories_listed":0,"syntology":null},{"url":null,"slug":"mlep-multi-granularity-local-entropy-patterns","title":"MLEP: Multi-granularity Local Entropy Patterns for Universal AI-generated Image Detection","date":"2025-04-18","arxiv_id":"2504.13726","repositories_listed":0,"syntology":null},{"url":null,"slug":"poet-supporting-prompting-creativity-and","title":"POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation","date":"2025-04-18","arxiv_id":"2504.13392","repositories_listed":0,"syntology":null},{"url":null,"slug":"point-driven-interactive-text-and-image-layer","title":"Point-Driven Interactive Text and Image Layer Editing Using Diffusion Models","date":"2025-04-18","arxiv_id":"2504.14108","repositories_listed":0,"syntology":null},{"url":null,"slug":"hiscene-creating-hierarchical-3d-scenes-with","title":"HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation","date":"2025-04-17","arxiv_id":"2504.13072","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-protection-against-personalized-text","title":"Privacy Protection Against Personalized Text-to-Image Synthesis via Cross-image Consistency Constraints","date":"2025-04-17","arxiv_id":"2504.12747","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-driven-and-training-free-forgetting","title":"ForgetMe: Evaluating Selective Forgetting in Generative Models","date":"2025-04-17","arxiv_id":"2504.12574","repositories_listed":0,"syntology":null},{"url":null,"slug":"science-t2i-addressing-scientific-illusions","title":"Science-T2I: Addressing Scientific Illusions in Image Synthesis","date":"2025-04-17","arxiv_id":"2504.13129","repositories_listed":0,"syntology":null},{"url":null,"slug":"smpl-gptexture-dual-view-3d-human-texture","title":"SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models","date":"2025-04-17","arxiv_id":"2504.13378","repositories_listed":0,"syntology":null},{"url":null,"slug":"ace-attentional-concept-erasure-in-diffusion","title":"ACE: Attentional Concept Erasure in Diffusion Models","date":"2025-04-16","arxiv_id":"2504.11850","repositories_listed":0,"syntology":null},{"url":null,"slug":"anti-aesthetics-protecting-facial-privacy","title":"Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis","date":"2025-04-16","arxiv_id":"2504.12129","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-reconstruction-a-physics-based-neural","title":"Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Rendering","date":"2025-04-16","arxiv_id":"2504.12273","repositories_listed":0,"syntology":null},{"url":null,"slug":"cobra-efficient-line-art-colorization-with","title":"Cobra: Efficient Line Art COlorization with BRoAder References","date":"2025-04-16","arxiv_id":"2504.12240","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-augmented-multimodal-alignment","title":"Instruction-augmented Multimodal Alignment for Image-Text and Element Matching","date":"2025-04-16","arxiv_id":"2504.12018","repositories_listed":0,"syntology":null},{"url":null,"slug":"sidme-self-supervised-image-demoireing-via","title":"SIDME: Self-supervised Image Demoiréing via Masked Encoder-Decoder Reconstruction","date":"2025-04-16","arxiv_id":"2504.12245","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-for-blood-vessel-network","title":"Synthetic Data for Blood Vessel Network Extraction","date":"2025-04-16","arxiv_id":"2504.11858","repositories_listed":0,"syntology":null},{"url":null,"slug":"wavelet-based-variational-autoencoders-for","title":"Wavelet-based Variational Autoencoders for High-Resolution Image Generation","date":"2025-04-16","arxiv_id":"2504.13214","repositories_listed":0,"syntology":null},{"url":null,"slug":"adt-tuning-diffusion-models-with-adversarial","title":"ADT: Tuning Diffusion Models with Adversarial Supervision","date":"2025-04-15","arxiv_id":"2504.11423","repositories_listed":0,"syntology":null},{"url":null,"slug":"animedl-2m-million-scale-ai-generated-anime","title":"AnimeDL-2M: Million-Scale AI-Generated Anime Image Detection and Localization in Diffusion Era","date":"2025-04-15","arxiv_id":"2504.11015","repositories_listed":0,"syntology":null},{"url":null,"slug":"bringing-together-invertible-unets-with","title":"Bringing together invertible UNets with invertible attention modules for memory-efficient diffusion models","date":"2025-04-15","arxiv_id":"2504.10883","repositories_listed":0,"syntology":null},{"url":null,"slug":"omni-2-unifying-omnidirectional-image","title":"Omni$^2$: Unifying Omnidirectional Image Generation and Editing in an Omni Model","date":"2025-04-15","arxiv_id":"2504.11379","repositories_listed":0,"syntology":null},{"url":null,"slug":"seedream-3-0-technical-report","title":"Seedream 3.0 Technical Report","date":"2025-04-15","arxiv_id":"2504.11346","repositories_listed":0,"syntology":null},{"url":null,"slug":"using-llms-as-prompt-modifier-to-avoid-biases","title":"Using LLMs as prompt modifier to avoid biases in AI image generators","date":"2025-04-15","arxiv_id":"2504.11104","repositories_listed":0,"syntology":null},{"url":null,"slug":"art3d-training-free-3d-generation-from-flat","title":"Art3D: Training-Free 3D Generation from Flat-Colored Illustration","date":"2025-04-14","arxiv_id":"2504.10466","repositories_listed":0,"syntology":null},{"url":null,"slug":"instructengine-instruction-driven-text-to","title":"InstructEngine: Instruction-driven Text-to-Image Alignment","date":"2025-04-14","arxiv_id":"2504.10329","repositories_listed":0,"syntology":null},{"url":null,"slug":"seg2med-a-segmentation-based-medical-image","title":"seg2med: a bridge from artificial anatomy to multimodal medical images","date":"2025-04-12","arxiv_id":"2504.09182","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-explainable-partial-aigc-image","title":"Towards Explainable Partial-AIGC Image Quality Assessment","date":"2025-04-12","arxiv_id":"2504.09291","repositories_listed":0,"syntology":null},{"url":null,"slug":"coprosketch-controllable-and-progressive","title":"CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model","date":"2025-04-11","arxiv_id":"2504.08259","repositories_listed":0,"syntology":null},{"url":null,"slug":"discriminator-free-direct-preference","title":"Discriminator-Free Direct Preference Optimization for Video Diffusion","date":"2025-04-11","arxiv_id":"2504.08542","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-fine-details-of-entity","title":"Generating Fine Details of Entity Interactions","date":"2025-04-11","arxiv_id":"2504.08714","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixdit-accelerating-image-diffusion","title":"MixDiT: Accelerating Image Diffusion Transformer Inference with Mixed-Precision MX Quantization","date":"2025-04-11","arxiv_id":"2504.08398","repositories_listed":0,"syntology":null},{"url":null,"slug":"muon-accelerated-attention-distillation-for","title":"Muon-Accelerated Attention Distillation for Real-Time Edge Synthesis via Optimized Latent Diffusion","date":"2025-04-11","arxiv_id":"2504.08451","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-design-of-diffusion-based-neural","title":"On the Design of Diffusion-based Neural Speech Codecs","date":"2025-04-11","arxiv_id":"2504.08470","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverseflow-sample-efficient-diverse-mode","title":"DiverseFlow: Sample-Efficient Diverse Mode Coverage in Flows","date":"2025-04-10","arxiv_id":"2504.07894","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexip-dynamic-control-of-preservation-and","title":"FlexIP: Dynamic Control of Preservation and Personality for Customized Image Generation","date":"2025-04-10","arxiv_id":"2504.07405","repositories_listed":0,"syntology":null},{"url":null,"slug":"marmot-multi-agent-reasoning-for-multi-object","title":"Marmot: Multi-Agent Reasoning for Multi-Object Self-Correcting in Improving Image-Text Alignment","date":"2025-04-10","arxiv_id":"2504.20054","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-discrepancy-learning-synthetic-faces","title":"Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction","date":"2025-04-10","arxiv_id":"2504.07382","repositories_listed":0,"syntology":null},{"url":"/paper/poem-precise-object-level-editing-via-mllm","slug":"poem-precise-object-level-editing-via-mllm","title":"POEM: Precise Object-level Editing via MLLM control","date":"2025-04-10","arxiv_id":"2504.08111","repositories_listed":0,"syntology":null},{"url":null,"slug":"visualcloze-a-universal-image-generation","title":"VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning","date":"2025-04-10","arxiv_id":"2504.07960","repositories_listed":0,"syntology":null},{"url":null,"slug":"compass-control-multi-object-orientation","title":"Compass Control: Multi Object Orientation Control for Text-to-Image Generation","date":"2025-04-09","arxiv_id":"2504.06752","repositories_listed":0,"syntology":null},{"url":null,"slug":"have-we-unified-image-generation-and","title":"Have we unified image generation and understanding yet? An empirical study of GPT-4o's image generation ability","date":"2025-04-09","arxiv_id":"2504.08003","repositories_listed":0,"syntology":null},{"url":null,"slug":"postermaker-towards-high-quality-product","title":"PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering","date":"2025-04-09","arxiv_id":"2504.06632","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-training-free-style-aligned-image","title":"A Training-Free Style-aligned Image Generation with Scale-wise Autoregressive Model","date":"2025-04-08","arxiv_id":"2504.06144","repositories_listed":0,"syntology":null},{"url":null,"slug":"cdm-qta-quantized-training-acceleration-for","title":"CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model","date":"2025-04-08","arxiv_id":"2504.07998","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-feat-occlusions-diffusion-features-for","title":"D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition","date":"2025-04-08","arxiv_id":"2504.06432","repositories_listed":0,"syntology":null},{"url":null,"slug":"parasite-a-steganography-based-backdoor","title":"Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models","date":"2025-04-08","arxiv_id":"2504.05815","repositories_listed":0,"syntology":null},{"url":null,"slug":"storybooth-training-free-multi-subject","title":"Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling","date":"2025-04-08","arxiv_id":"2504.05800","repositories_listed":0,"syntology":null},{"url":"/paper/transfer-between-modalities-with-metaqueries","slug":"transfer-between-modalities-with-metaqueries","title":"Transfer between Modalities with MetaQueries","date":"2025-04-08","arxiv_id":"2504.06256","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-networks-with-limited","title":"Generative Adversarial Networks with Limited Data: A Survey and Benchmarking","date":"2025-04-07","arxiv_id":"2504.05456","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-10005","title":"Multimodal Cinematic Video Synthesis Using Text-to-Image and Audio Generation Models","date":"2025-04-06","arxiv_id":"2506.10005","repositories_listed":0,"syntology":null},{"url":null,"slug":"thermoxels-a-voxel-based-method-to-generate","title":"Thermoxels: a voxel-based method to generate simulation-ready 3D thermal models","date":"2025-04-06","arxiv_id":"2504.04448","repositories_listed":0,"syntology":null},{"url":null,"slug":"digital-gene-learning-about-the-physical","title":"Digital Gene: Learning about the Physical World through Analytic Concepts","date":"2025-04-05","arxiv_id":"2504.04170","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hybrid-wavelet-fourier-method-for-next","title":"A Hybrid Wavelet-Fourier Method for Next-Generation Conditional Diffusion Models","date":"2025-04-04","arxiv_id":"2504.03821","repositories_listed":0,"syntology":null},{"url":null,"slug":"flairbrainseg-fine-grained-brain-segmentation","title":"FLAIRBrainSeg: Fine-grained brain segmentation using FLAIR MRI only","date":"2025-04-04","arxiv_id":"2504.03376","repositories_listed":0,"syntology":null},{"url":null,"slug":"mme-unify-a-comprehensive-benchmark-for","title":"MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models","date":"2025-04-04","arxiv_id":"2504.03641","repositories_listed":0,"syntology":null},{"url":null,"slug":"qirl-boosting-visual-question-answering-via","title":"QIRL: Boosting Visual Question Answering via Optimized Question-Image Relation Learning","date":"2025-04-04","arxiv_id":"2504.03337","repositories_listed":0,"syntology":null},{"url":null,"slug":"ac-lora-auto-component-lora-for-personalized","title":"AC-LoRA: Auto Component LoRA for Personalized Artistic Style Image Generation","date":"2025-04-03","arxiv_id":"2504.02231","repositories_listed":0,"syntology":null},{"url":null,"slug":"bias-in-large-language-models-across-clinical","title":"Bias in Large Language Models Across Clinical Applications: A Systematic Review","date":"2025-04-03","arxiv_id":"2504.02917","repositories_listed":0,"syntology":null},{"url":null,"slug":"finelip-extending-clip-s-reach-via-fine","title":"FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs","date":"2025-04-02","arxiv_id":"2504.01916","repositories_listed":0,"syntology":null},{"url":null,"slug":"foreground-focus-enhancing-coherence-and","title":"Foreground Focus: Enhancing Coherence and Fidelity in Camouflaged Image Generation","date":"2025-04-02","arxiv_id":"2504.02180","repositories_listed":0,"syntology":null},{"url":null,"slug":"pro-dg-procedural-diffusion-guidance-for","title":"Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation","date":"2025-04-02","arxiv_id":"2504.01571","repositories_listed":0,"syntology":null}],"record_sha256":"112642f53b3daaaabb2256ecdf8f30e51016b10e40e4cc5082f1cc42d5ac137b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}