{"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/37","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":37,"pages_in_order":67,"rows_per_page":100,"rows":[3601,3700],"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/36","next":"/task/image-generation/papers/38","papers":[{"url":null,"slug":"skrr-skip-and-re-use-text-encoder-layers-for","title":"Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation","date":"2025-02-12","arxiv_id":"2502.08690","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultrasound-image-generation-using-latent","title":"Ultrasound Image Generation using Latent Diffusion Models","date":"2025-02-12","arxiv_id":"2502.08580","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-of-representation-learning","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","date":"2025-02-11","arxiv_id":"2502.10444","repositories_listed":0,"syntology":null},{"url":null,"slug":"articulate-that-object-part-atop-3d-part","title":"Articulate That Object Part (ATOP): 3D Part Articulation from Text and Motion Personalization","date":"2025-02-11","arxiv_id":"2502.07278","repositories_listed":0,"syntology":null},{"url":null,"slug":"causalged-blending-causality-and-diffusion","title":"CausalGeD: Blending Causality and Diffusion for Spatial Gene Expression Generation","date":"2025-02-11","arxiv_id":"2502.07751","repositories_listed":0,"syntology":null},{"url":null,"slug":"classifier-free-guidance-from-high","title":"Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms","date":"2025-02-11","arxiv_id":"2502.07849","repositories_listed":0,"syntology":null},{"url":null,"slug":"flexcontrol-computation-aware-controlnet-with","title":"FlexControl: Computation-Aware ControlNet with Differentiable Router for Text-to-Image Generation","date":"2025-02-11","arxiv_id":"2502.10451","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-knowledge-distillation-in","title":"Optimizing Knowledge Distillation in Transformers: Enabling Multi-Head Attention without Alignment Barriers","date":"2025-02-11","arxiv_id":"2502.07436","repositories_listed":0,"syntology":null},{"url":null,"slug":"surgrid-controllable-surgical-simulation-via","title":"SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion","date":"2025-02-11","arxiv_id":"2502.07945","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-safe-denoisers-for-safe-use-of","title":"Training-Free Safe Denoisers for Safe Use of Diffusion Models","date":"2025-02-11","arxiv_id":"2502.08011","repositories_listed":0,"syntology":null},{"url":null,"slug":"customvideox-3d-reference-attention-driven","title":"CustomVideoX: 3D Reference Attention Driven Dynamic Adaptation for Zero-Shot Customized Video Diffusion Transformers","date":"2025-02-10","arxiv_id":"2502.06527","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-image-to-video-an-empirical-study-of","title":"From Image to Video: An Empirical Study of Diffusion Representations","date":"2025-02-10","arxiv_id":"2502.07001","repositories_listed":0,"syntology":null},{"url":null,"slug":"outsourced-diffusion-sampling-efficient","title":"Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models","date":"2025-02-10","arxiv_id":"2502.06999","repositories_listed":0,"syntology":null},{"url":null,"slug":"preference-alignment-on-diffusion-model-a","title":"Preference Alignment on Diffusion Model: A Comprehensive Survey for Image Generation and Editing","date":"2025-02-10","arxiv_id":"2502.07829","repositories_listed":0,"syntology":null},{"url":null,"slug":"c2gm-cascading-conditional-generation-of","title":"Bridging Scales in Map Generation: A scale-aware cascaded generative mapping framework for seamless and consistent multi-scale cartographic representation","date":"2025-02-07","arxiv_id":"2502.04991","repositories_listed":0,"syntology":null},{"url":null,"slug":"g2pdiffusion-genotype-to-phenotype-prediction","title":"G2PDiffusion: Genotype-to-Phenotype Prediction with Diffusion Models","date":"2025-02-07","arxiv_id":"2502.04684","repositories_listed":0,"syntology":null},{"url":null,"slug":"hummingbird-high-fidelity-image-generation","title":"Hummingbird: High Fidelity Image Generation via Multimodal Context Alignment","date":"2025-02-07","arxiv_id":"2502.05153","repositories_listed":0,"syntology":null},{"url":null,"slug":"qlip-text-aligned-visual-tokenization-unifies","title":"QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation","date":"2025-02-07","arxiv_id":"2502.05178","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmented-conditioning-is-enough-for","title":"Augmented Conditioning Is Enough For Effective Training Image Generation","date":"2025-02-06","arxiv_id":"2502.04475","repositories_listed":0,"syntology":null},{"url":null,"slug":"decoder-only-llms-are-better-controllers-for","title":"Decoder-Only LLMs are Better Controllers for Diffusion Models","date":"2025-02-06","arxiv_id":"2502.04412","repositories_listed":0,"syntology":null},{"url":null,"slug":"dice-distilling-classifier-free-guidance-into","title":"DICE: Distilling Classifier-Free Guidance into Text Embeddings","date":"2025-02-06","arxiv_id":"2502.03726","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairt2i-mitigating-social-bias-in-text-to","title":"FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing","date":"2025-02-06","arxiv_id":"2502.03826","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-adversarial-networks-bridging-art","title":"Generative Adversarial Networks Bridging Art and Machine Intelligence","date":"2025-02-06","arxiv_id":"2502.04116","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-fair-and-robust-face-parsing-for","title":"Towards Fair and Robust Face Parsing for Generative AI: A Multi-Objective Approach","date":"2025-02-06","arxiv_id":"2502.04391","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-autoencoders-are-effective-tokenizers","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","date":"2025-02-05","arxiv_id":"2502.03444","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-fairness-of-unified-multimodal-large","title":"On Fairness of Unified Multimodal Large Language Model for Image Generation","date":"2025-02-05","arxiv_id":"2502.03429","repositories_listed":0,"syntology":null},{"url":null,"slug":"poisson-flow-joint-model-for-multiphase","title":"Poisson Flow Joint Model for Multiphase contrast-enhanced CT","date":"2025-02-05","arxiv_id":"2502.03079","repositories_listed":0,"syntology":null},{"url":null,"slug":"truepose-human-parsing-guided-attention","title":"TruePose: Human-Parsing-guided Attention Diffusion for Full-ID Preserving Pose Transfer","date":"2025-02-05","arxiv_id":"2502.03426","repositories_listed":0,"syntology":null},{"url":null,"slug":"corpa-adversarial-image-generation-for-chest","title":"CoRPA: Adversarial Image Generation for Chest X-rays Using Concept Vector Perturbations and Generative Models","date":"2025-02-04","arxiv_id":"2502.05214","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-instruction-tuning","title":"Diffusion Instruction Tuning","date":"2025-02-04","arxiv_id":"2502.06814","repositories_listed":0,"syntology":null},{"url":null,"slug":"layer-separation-adjustable-joint-space-width","title":"Layer Separation: Adjustable Joint Space Width Images Synthesis in Conventional Radiography","date":"2025-02-04","arxiv_id":"2502.01972","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-consistent-and-controllable-image","title":"Towards Consistent and Controllable Image Synthesis for Face Editing","date":"2025-02-04","arxiv_id":"2502.02465","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-are-diffusion-priors-helpful-in-sparse","title":"When are Diffusion Priors Helpful in Sparse Reconstruction? A Study with Sparse-view CT","date":"2025-02-04","arxiv_id":"2502.02771","repositories_listed":0,"syntology":null},{"url":null,"slug":"texture-image-synthesis-using-spatial-gan","title":"Texture Image Synthesis Using Spatial GAN Based on Vision Transformers","date":"2025-02-03","arxiv_id":"2502.01842","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpaired-deblurring-via-decoupled-diffusion","title":"Unpaired Deblurring via Decoupled Diffusion Model","date":"2025-02-03","arxiv_id":"2502.01522","repositories_listed":0,"syntology":null},{"url":null,"slug":"realrag-retrieval-augmented-realistic-image","title":"RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning","date":"2025-02-02","arxiv_id":"2502.00848","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-solvers-for-discrete-diffusion-models","title":"Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms","date":"2025-02-01","arxiv_id":"2502.00234","repositories_listed":0,"syntology":null},{"url":null,"slug":"video-latent-flow-matching-optimal-polynomial","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","date":"2025-02-01","arxiv_id":"2502.00500","repositories_listed":0,"syntology":null},{"url":null,"slug":"ambient-denoising-diffusion-generative","title":"Ambient Denoising Diffusion Generative Adversarial Networks for Establishing Stochastic Object Models from Noisy Image Data","date":"2025-01-31","arxiv_id":"2501.19094","repositories_listed":0,"syntology":null},{"url":null,"slug":"bcat-a-block-causal-transformer-for-pde","title":"BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics","date":"2025-01-31","arxiv_id":"2501.18972","repositories_listed":0,"syntology":null},{"url":"/paper/reg-rectified-gradient-guidance-for","slug":"reg-rectified-gradient-guidance-for","title":"REG: Rectified Gradient Guidance for Conditional Diffusion Models","date":"2025-01-31","arxiv_id":"2501.18865","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/reg-rectified-gradient-guidance-for#ran","syntology_url":"https://syntology.ai/paper/2501.18865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18865"}},"official":null}},{"url":null,"slug":"diffusion-autoencoders-are-scalable-image","title":"Diffusion Autoencoders are Scalable Image Tokenizers","date":"2025-01-30","arxiv_id":"2501.18593","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-ai-for-vision-a-comprehensive","title":"Generative AI for Vision: A Comprehensive Study of Frameworks and Applications","date":"2025-01-29","arxiv_id":"2501.18033","repositories_listed":0,"syntology":null},{"url":null,"slug":"debiaspi-inference-time-debiasing-by-prompt","title":"DebiasPI: Inference-time Debiasing by Prompt Iteration of a Text-to-Image Generative Model","date":"2025-01-28","arxiv_id":"2501.18642","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-to-image-generation-for-vocabulary","title":"Text-to-Image Generation for Vocabulary Learning Using the Keyword Method","date":"2025-01-28","arxiv_id":"2501.17099","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-schrodinger-momentum-diffusion","title":"Variational Schrödinger Momentum Diffusion","date":"2025-01-28","arxiv_id":"2501.16675","repositories_listed":0,"syntology":null},{"url":null,"slug":"lora-x-bridging-foundation-models-with","title":"LoRA-X: Bridging Foundation Models with Training-Free Cross-Model Adaptation","date":"2025-01-27","arxiv_id":"2501.16559","repositories_listed":0,"syntology":null},{"url":null,"slug":"metadecorator-generating-immersive-virtual","title":"MetaDecorator: Generating Immersive Virtual Tours through Multimodality","date":"2025-01-27","arxiv_id":"2501.16164","repositories_listed":0,"syntology":null},{"url":null,"slug":"relightvid-temporal-consistent-diffusion","title":"RelightVid: Temporal-Consistent Diffusion Model for Video Relighting","date":"2025-01-27","arxiv_id":"2501.16330","repositories_listed":0,"syntology":null},{"url":null,"slug":"slot-guided-adaptation-of-pre-trained","title":"Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation","date":"2025-01-27","arxiv_id":"2501.15878","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-clinical-evaluation-of-memory","title":"Comparative clinical evaluation of \"memory-efficient\" synthetic 3d generative adversarial networks (gan) head-to-head to state of art: results on computed tomography of the chest","date":"2025-01-26","arxiv_id":"2501.15572","repositories_listed":0,"syntology":null},{"url":null,"slug":"sq-dm-accelerating-diffusion-models-with","title":"SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity","date":"2025-01-26","arxiv_id":"2501.15448","repositories_listed":0,"syntology":null},{"url":null,"slug":"stochsync-stochastic-diffusion","title":"StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces","date":"2025-01-26","arxiv_id":"2501.15445","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-intent-understanding-for-ambiguous","title":"Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy","date":"2025-01-25","arxiv_id":"2501.15167","repositories_listed":0,"syntology":null},{"url":null,"slug":"stones-from-other-hills-can-polish-jade-zero","title":"\"Stones from Other Hills can Polish Jade\": Zero-shot Anomaly Image Synthesis via Cross-domain Anomaly Injection","date":"2025-01-25","arxiv_id":"2501.15211","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-guided-neural-schrodinger-bridge-for","title":"Fully Guided Neural Schrödinger bridge for Brain MR image synthesis","date":"2025-01-24","arxiv_id":"2501.14171","repositories_listed":0,"syntology":null},{"url":null,"slug":"paid-a-framework-of-product-centric","title":"PAID: A Framework of Product-Centric Advertising Image Design","date":"2025-01-24","arxiv_id":"2501.14316","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-scalable-topological-regularizers","title":"Towards Scalable Topological Regularizers","date":"2025-01-24","arxiv_id":"2501.14641","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-free-style-and-content-transfer-by","title":"Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusion 2.*","date":"2025-01-24","arxiv_id":"2501.14524","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mutual-information-perspective-on-multiple","title":"A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation","date":"2025-01-23","arxiv_id":"2501.13718","repositories_listed":0,"syntology":null},{"url":null,"slug":"binary-diffusion-probabilistic-model","title":"Binary Diffusion Probabilistic Model","date":"2025-01-23","arxiv_id":"2501.13915","repositories_listed":0,"syntology":null},{"url":null,"slug":"imagine-e-image-generation-intelligence","title":"IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models","date":"2025-01-23","arxiv_id":"2501.13920","repositories_listed":0,"syntology":null},{"url":null,"slug":"msf-efficient-diffusion-model-via-multi-scale","title":"MSF: Efficient Diffusion Model Via Multi-Scale Latent Factorize","date":"2025-01-23","arxiv_id":"2501.13349","repositories_listed":0,"syntology":null},{"url":null,"slug":"photogan-generative-adversarial-neural","title":"PhotoGAN: Generative Adversarial Neural Network Acceleration with Silicon Photonics","date":"2025-01-23","arxiv_id":"2501.13828","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerate-high-quality-diffusion-models-with","title":"Accelerate High-Quality Diffusion Models with Inner Loop Feedback","date":"2025-01-22","arxiv_id":"2501.13107","repositories_listed":0,"syntology":null},{"url":null,"slug":"lit-delving-into-a-simplified-linear","title":"LiT: Delving into a Simplified Linear Diffusion Transformer for Image Generation","date":"2025-01-22","arxiv_id":"2501.12976","repositories_listed":0,"syntology":null},{"url":null,"slug":"orchid-image-latent-diffusion-for-joint","title":"Orchid: Image Latent Diffusion for Joint Appearance and Geometry Generation","date":"2025-01-22","arxiv_id":"2501.13087","repositories_listed":0,"syntology":null},{"url":null,"slug":"precisecam-precise-camera-control-for-text-to","title":"PreciseCam: Precise Camera Control for Text-to-Image Generation","date":"2025-01-22","arxiv_id":"2501.12910","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-ct-image-generation-from-cbct-a","title":"Synthetic CT image generation from CBCT: A Systematic Review","date":"2025-01-22","arxiv_id":"2501.13972","repositories_listed":0,"syntology":null},{"url":null,"slug":"triplet-synthesis-for-enhancing-composed","title":"Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation","date":"2025-01-22","arxiv_id":"2501.13968","repositories_listed":0,"syntology":null},{"url":null,"slug":"bidirectional-brain-image-translation-using","title":"Bidirectional Brain Image Translation using Transfer Learning from Generic Pre-trained Models","date":"2025-01-21","arxiv_id":"2501.12488","repositories_listed":0,"syntology":null},{"url":null,"slug":"gps-as-a-control-signal-for-image-generation","title":"GPS as a Control Signal for Image Generation","date":"2025-01-21","arxiv_id":"2501.12390","repositories_listed":0,"syntology":null},{"url":null,"slug":"owls-are-wise-and-foxes-are-unfaithful","title":"Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language models","date":"2025-01-21","arxiv_id":"2501.12433","repositories_listed":0,"syntology":null},{"url":null,"slug":"parallel-sequence-modeling-via-generalized","title":"Parallel Sequence Modeling via Generalized Spatial Propagation Network","date":"2025-01-21","arxiv_id":"2501.12381","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-generative-models-fair-a-study-of-racial","title":"Are generative models fair? A study of racial bias in dermatological image generation","date":"2025-01-20","arxiv_id":"2501.11752","repositories_listed":0,"syntology":null},{"url":null,"slug":"ditto-accelerating-diffusion-model-via","title":"Ditto: Accelerating Diffusion Model via Temporal Value Similarity","date":"2025-01-20","arxiv_id":"2501.11211","repositories_listed":0,"syntology":null},{"url":null,"slug":"nested-annealed-training-scheme-for","title":"Nested Annealed Training Scheme for Generative Adversarial Networks","date":"2025-01-20","arxiv_id":"2501.11318","repositories_listed":0,"syntology":null},{"url":null,"slug":"know-no-better-a-data-driven-approach-for","title":"Know \"No'' Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","date":"2025-01-19","arxiv_id":"2501.10913","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffvsr-enhancing-real-world-video-super","title":"DiffVSR: Enhancing Real-World Video Super-Resolution with Diffusion Models for Advanced Visual Quality and Temporal Consistency","date":"2025-01-17","arxiv_id":"2501.10110","repositories_listed":0,"syntology":null},{"url":null,"slug":"ie-bench-advancing-the-measurement-of-text","title":"IE-Bench: Advancing the Measurement of Text-Driven Image Editing for Human Perception Alignment","date":"2025-01-17","arxiv_id":"2501.09927","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-neural-style-transfer-for-artistic","title":"Dynamic Neural Style Transfer for Artistic Image Generation using VGG19","date":"2025-01-16","arxiv_id":"2501.09420","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-time-scaling-for-diffusion-models","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","date":"2025-01-16","arxiv_id":"2501.09732","repositories_listed":0,"syntology":null},{"url":null,"slug":"learnings-from-scaling-visual-tokenizers-for","title":"Learnings from Scaling Visual Tokenizers for Reconstruction and Generation","date":"2025-01-16","arxiv_id":"2501.09755","repositories_listed":0,"syntology":null},{"url":null,"slug":"seal-entangled-white-box-watermarks-on-low","title":"SEAL: Entangled White-box Watermarks on Low-Rank Adaptation","date":"2025-01-16","arxiv_id":"2501.09284","repositories_listed":0,"syntology":null},{"url":null,"slug":"cookingdiffusion-cooking-procedural-image","title":"CookingDiffusion: Cooking Procedural Image Generation with Stable Diffusion","date":"2025-01-15","arxiv_id":"2501.09042","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-multi-scale-cross-attention-for","title":"Enhanced Multi-Scale Cross-Attention for Person Image Generation","date":"2025-01-15","arxiv_id":"2501.08900","repositories_listed":0,"syntology":null},{"url":null,"slug":"grounding-text-to-image-diffusion-models-for","title":"Grounding Text-To-Image Diffusion Models For Controlled High-Quality Image Generation","date":"2025-01-15","arxiv_id":"2501.09194","repositories_listed":0,"syntology":null},{"url":null,"slug":"shyi-action-support-for-contrastive-learning","title":"SHYI: Action Support for Contrastive Learning in High-Fidelity Text-to-Image Generation","date":"2025-01-15","arxiv_id":"2501.09055","repositories_listed":0,"syntology":null},{"url":null,"slug":"stereogen-high-quality-stereo-image","title":"StereoGen: High-quality Stereo Image Generation from a Single Image","date":"2025-01-15","arxiv_id":"2501.08654","repositories_listed":0,"syntology":null},{"url":null,"slug":"watermarking-in-diffusion-model-gaussian","title":"Watermarking in Diffusion Model: Gaussian Shading with Exact Diffusion Inversion via Coupled Transformations (EDICT)","date":"2025-01-15","arxiv_id":"2501.08604","repositories_listed":0,"syntology":null},{"url":"/paper/xmusic-towards-a-generalized-and-controllable","slug":"xmusic-towards-a-generalized-and-controllable","title":"XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework","date":"2025-01-15","arxiv_id":"2501.08809","repositories_listed":0,"syntology":null},{"url":null,"slug":"supernerf-gan-a-universal-3d-consistent-super","title":"SuperNeRF-GAN: A Universal 3D-Consistent Super-Resolution Framework for Efficient and Enhanced 3D-Aware Image Synthesis","date":"2025-01-12","arxiv_id":"2501.06770","repositories_listed":0,"syntology":null},{"url":null,"slug":"focus-n-fix-region-aware-fine-tuning-for-text","title":"Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation","date":"2025-01-11","arxiv_id":"2501.06481","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaffolding-creativity-integrating-generative","title":"Scaffolding Creativity: Integrating Generative AI Tools and Real-world Experiences in Business Education","date":"2025-01-11","arxiv_id":"2501.06527","repositories_listed":0,"syntology":null},{"url":null,"slug":"emoticrafter-text-to-emotional-image","title":"EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model","date":"2025-01-10","arxiv_id":"2501.05710","repositories_listed":0,"syntology":null},{"url":null,"slug":"met3r-measuring-multi-view-consistency-in","title":"MEt3R: Measuring Multi-View Consistency in Generated Images","date":"2025-01-10","arxiv_id":"2501.06336","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultrasound-image-synthesis-using-generative","title":"Ultrasound Image Synthesis Using Generative AI for Lung Ultrasound Detection","date":"2025-01-10","arxiv_id":"2501.06356","repositories_listed":0,"syntology":null},{"url":null,"slug":"crops-model-agnostic-training-free-framework","title":"CROPS: Model-Agnostic Training-Free Framework for Safe Image Synthesis with Latent Diffusion Models","date":"2025-01-09","arxiv_id":"2501.05359","repositories_listed":0,"syntology":null},{"url":null,"slug":"patch-gan-transfer-learning-with","title":"Patch-GAN Transfer Learning with Reconstructive Models for Cloud Removal","date":"2025-01-09","arxiv_id":"2501.05265","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-sound-assembling-sounds-from-visuals","title":"Seeing Sound: Assembling Sounds from Visuals for Audio-to-Image Generation","date":"2025-01-09","arxiv_id":"2501.05413","repositories_listed":0,"syntology":null}],"record_sha256":"3df7b2ce3ebba8c85193ffd41ec3f8120af119afd71752c38611afbeb2bba8a7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}