{"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":"/method/latent-diffusion-model/papers/3","list_of":"/method/latent-diffusion-model","method":"Latent Diffusion Model","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":3,"pages_in_order":4,"rows_per_page":100,"rows":[201,300],"of":366,"counts":{"archive_papers_tagged":366,"with_a_code_link":158,"where_syntology_ran_a_sample":50,"not_listed_spam_title":0,"listed":366,"listed_where_code_ran":50,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":44,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":44,"listed_every_run_a_failure_of_syntologys_instrument":6,"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":"/method/latent-diffusion-model","prev":"/method/latent-diffusion-model/papers/2","next":"/method/latent-diffusion-model/papers/4","papers":[{"paper":null,"slug":"full-event-particle-level-unfolding-with","title":"Full Event Particle-Level Unfolding with Variable-Length Latent Variational Diffusion","date":"2024-04-22","arxiv_id":"2404.14332","n_code_links":0,"syntology":null},{"paper":"/paper/tavgbench-benchmarking-text-to-audible-video","slug":"tavgbench-benchmarking-text-to-audible-video","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","date":"2024-04-22","arxiv_id":"2404.14381","n_code_links":1,"syntology":{"ran":11,"of":11,"n_ran_checked":8,"n_instrument":3,"unverified":0,"pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["opennlplab/tavgbench"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/accelerating-the-generation-of-molecular","slug":"accelerating-the-generation-of-molecular","title":"Accelerating the Generation of Molecular Conformations with Progressive Distillation of Equivariant Latent Diffusion Models","date":"2024-04-21","arxiv_id":"2404.13491","n_code_links":1,"syntology":null},{"paper":"/paper/pixel-is-a-barrier-diffusion-models-are-more","slug":"pixel-is-a-barrier-diffusion-models-are-more","title":"Pixel is a Barrier: Diffusion Models Are More Adversarially Robust Than We Think","date":"2024-04-20","arxiv_id":"2404.13320","n_code_links":1,"syntology":null},{"paper":"/paper/training-and-prompt-free-general-painterly","slug":"training-and-prompt-free-general-painterly","title":"Training-and-Prompt-Free General Painterly Harmonization via Zero-Shot Disentenglement on Style and Content References","date":"2024-04-19","arxiv_id":"2404.12900","n_code_links":1,"syntology":null},{"paper":"/paper/zero-shot-medical-phrase-grounding-with-off","slug":"zero-shot-medical-phrase-grounding-with-off","title":"Zero-Shot Medical Phrase Grounding with Off-the-shelf Diffusion Models","date":"2024-04-19","arxiv_id":"2404.12920","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["vios-s/ldm-phrase-grounding"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generating-counterfactual-trajectories-with","title":"Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discovery","date":"2024-04-16","arxiv_id":"2404.10356","n_code_links":0,"syntology":null},{"paper":"/paper/magic-clothing-controllable-garment-driven","slug":"magic-clothing-controllable-garment-driven","title":"Magic Clothing: Controllable Garment-Driven Image Synthesis","date":"2024-04-15","arxiv_id":"2404.09512","n_code_links":1,"syntology":null},{"paper":"/paper/changeanywhere-sample-generation-for-remote","slug":"changeanywhere-sample-generation-for-remote","title":"ChangeAnywhere: Sample Generation for Remote Sensing Change Detection via Semantic Latent Diffusion Model","date":"2024-04-13","arxiv_id":"2404.08892","n_code_links":1,"syntology":null},{"paper":"/paper/diffharmony-latent-diffusion-model-meets","slug":"diffharmony-latent-diffusion-model-meets","title":"DiffHarmony: Latent Diffusion Model Meets Image Harmonization","date":"2024-04-09","arxiv_id":"2404.06139","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["nicecv/diffharmony"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"structldm-structured-latent-diffusion-for-3d","title":"StructLDM: Structured Latent Diffusion for 3D Human Generation","date":"2024-04-01","arxiv_id":"2404.01241","n_code_links":0,"syntology":null},{"paper":null,"slug":"bend-bagging-deep-learning-training-based-on","title":"BEND: Bagging Deep Learning Training Based on Efficient Neural Network Diffusion","date":"2024-03-23","arxiv_id":"2403.15766","n_code_links":0,"syntology":null},{"paper":"/paper/champ-controllable-and-consistent-human-image","slug":"champ-controllable-and-consistent-human-image","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","date":"2024-03-21","arxiv_id":"2403.14781","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":1,"n_instrument":1,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["fudan-generative-vision/champ"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"efficient-video-diffusion-models-via-content","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","date":"2024-03-21","arxiv_id":"2403.14148","n_code_links":0,"syntology":null},{"paper":null,"slug":"locating-and-mitigating-gender-bias-in-large","title":"Locating and Mitigating Gender Bias in Large Language Models","date":"2024-03-21","arxiv_id":"2403.14409","n_code_links":0,"syntology":null},{"paper":"/paper/towards-learning-contrast-kinetics-with-multi","slug":"towards-learning-contrast-kinetics-with-multi","title":"Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models","date":"2024-03-20","arxiv_id":"2403.13890","n_code_links":2,"syntology":null},{"paper":"/paper/vstar-generative-temporal-nursing-for-longer","slug":"vstar-generative-temporal-nursing-for-longer","title":"VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis","date":"2024-03-20","arxiv_id":"2403.13501","n_code_links":1,"syntology":{"ran":12,"of":14,"n_ran_checked":9,"n_instrument":3,"unverified":2,"pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["boschresearch/VSTAR"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"d-cubed-latent-diffusion-trajectory","title":"D-Cubed: Latent Diffusion Trajectory Optimisation for Dexterous Deformable Manipulation","date":"2024-03-19","arxiv_id":"2403.12861","n_code_links":0,"syntology":null},{"paper":null,"slug":"sc-diff-3d-shape-completion-with-latent","title":"SC-Diff: 3D Shape Completion with Latent Diffusion Models","date":"2024-03-19","arxiv_id":"2403.12470","n_code_links":0,"syntology":null},{"paper":"/paper/towards-controllable-face-generation-with","slug":"towards-controllable-face-generation-with","title":"Controllable Face Synthesis with Semantic Latent Diffusion Models","date":"2024-03-19","arxiv_id":"2403.12743","n_code_links":2,"syntology":null},{"paper":"/paper/one-step-image-translation-with-text-to-image","slug":"one-step-image-translation-with-text-to-image","title":"One-Step Image Translation with Text-to-Image Models","date":"2024-03-18","arxiv_id":"2403.12036","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["gaparmar/img2img-turbo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/efficient-diffusion-driven-corruption-editor","slug":"efficient-diffusion-driven-corruption-editor","title":"Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation","date":"2024-03-16","arxiv_id":"2403.10911","n_code_links":1,"syntology":null},{"paper":null,"slug":"reward-guided-latent-consistency-distillation","title":"Reward Guided Latent Consistency Distillation","date":"2024-03-16","arxiv_id":"2403.11027","n_code_links":0,"syntology":null},{"paper":null,"slug":"st-ldm-a-universal-framework-for-text","title":"ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images","date":"2024-03-15","arxiv_id":"2403.10004","n_code_links":0,"syntology":null},{"paper":null,"slug":"explore-in-context-segmentation-via-latent","title":"Explore In-Context Segmentation via Latent Diffusion Models","date":"2024-03-14","arxiv_id":"2403.09616","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantifying-and-mitigating-privacy-risks-for","title":"Quantifying and Mitigating Privacy Risks for Tabular Generative Models","date":"2024-03-12","arxiv_id":"2403.07842","n_code_links":0,"syntology":null},{"paper":null,"slug":"style2talker-high-resolution-talking-head","title":"Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style","date":"2024-03-11","arxiv_id":"2403.06365","n_code_links":0,"syntology":null},{"paper":"/paper/a-novel-approach-to-industrial-defect","slug":"a-novel-approach-to-industrial-defect","title":"A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation","date":"2024-02-29","arxiv_id":"2402.19330","n_code_links":1,"syntology":null},{"paper":"/paper/diffusion-based-neural-network-weights","slug":"diffusion-based-neural-network-weights","title":"Diffusion-Based Neural Network Weights Generation","date":"2024-02-28","arxiv_id":"2402.18153","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":1,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sorobedio/dnnwg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/transparent-image-layer-diffusion-using","slug":"transparent-image-layer-diffusion-using","title":"Transparent Image Layer Diffusion using Latent Transparency","date":"2024-02-27","arxiv_id":"2402.17113","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"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","official":{"repos":["layerdiffusion/layerdiffuse","layerdiffusion/layerdiffusion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"visual-concept-driven-image-generation-with","title":"Visual Concept-driven Image Generation with Text-to-Image Diffusion Model","date":"2024-02-18","arxiv_id":"2402.11487","n_code_links":0,"syntology":null},{"paper":"/paper/u-2-mrpd-unsupervised-undersampled-mri","slug":"u-2-mrpd-unsupervised-undersampled-mri","title":"MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion model","date":"2024-02-16","arxiv_id":"2402.10609","n_code_links":1,"syntology":null},{"paper":null,"slug":"avatarmmc-3d-head-avatar-generation-and","title":"AvatarMMC: 3D Head Avatar Generation and Editing with Multi-Modal Conditioning","date":"2024-02-08","arxiv_id":"2402.05803","n_code_links":0,"syntology":null},{"paper":"/paper/discdiff-latent-diffusion-model-for-dna","slug":"discdiff-latent-diffusion-model-for-dna","title":"DiscDiff: Latent Diffusion Model for DNA Sequence Generation","date":"2024-02-08","arxiv_id":"2402.06079","n_code_links":0,"syntology":null},{"paper":null,"slug":"bass-accompaniment-generation-via-latent","title":"Bass Accompaniment Generation via Latent Diffusion","date":"2024-02-02","arxiv_id":"2402.01412","n_code_links":0,"syntology":null},{"paper":"/paper/ddmi-domain-agnostic-latent-diffusion-models","slug":"ddmi-domain-agnostic-latent-diffusion-models","title":"DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations","date":"2024-01-23","arxiv_id":"2401.12517","n_code_links":1,"syntology":{"ran":18,"of":21,"n_ran_checked":12,"n_instrument":6,"unverified":3,"pointer_only":6,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","official":{"repos":["mlvlab/DDMI"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hicast-highly-customized-arbitrary-style","title":"HiCAST: Highly Customized Arbitrary Style Transfer with Adapter Enhanced Diffusion Models","date":"2024-01-11","arxiv_id":"2401.05870","n_code_links":0,"syntology":null},{"paper":"/paper/colorizediffusion-adjustable-sketch","slug":"colorizediffusion-adjustable-sketch","title":"ColorizeDiffusion: Adjustable Sketch Colorization with Reference Image and Text","date":"2024-01-02","arxiv_id":"2401.01456","n_code_links":2,"syntology":null},{"paper":"/paper/arbitrary-motion-style-transfer-with-multi","slug":"arbitrary-motion-style-transfer-with-multi","title":"Arbitrary Motion Style Transfer with Multi-condition Motion Latent Diffusion Model","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/d-4-dataset-distillation-via-disentangled","slug":"d-4-dataset-distillation-via-disentangled","title":"D^4: Dataset Distillation via Disentangled Diffusion Model","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/r-cyclic-diffuser-reductive-and-cyclic-latent","slug":"r-cyclic-diffuser-reductive-and-cyclic-latent","title":"R-Cyclic Diffuser: Reductive and Cyclic Latent Diffusion for 3D Clothed Human Digitalization","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"text-conditioned-generative-model-of-3d","title":"Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles","date":"2024-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/uv-idm-identity-conditioned-latent-diffusion","slug":"uv-idm-identity-conditioned-latent-diffusion","title":"UV-IDM: Identity-Conditioned Latent Diffusion Model for Face UV-Texture Generation","date":"2024-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/data-augmentation-for-supervised-graph","slug":"data-augmentation-for-supervised-graph","title":"Data Augmentation for Supervised Graph Outlier Detection via Latent Diffusion Models","date":"2023-12-29","arxiv_id":"2312.17679","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["kayzliu/godm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"pangu-draw-advancing-resource-efficient-text","title":"PanGu-Draw: Advancing Resource-Efficient Text-to-Image Synthesis with Time-Decoupled Training and Reusable Coop-Diffusion","date":"2023-12-27","arxiv_id":"2312.16486","n_code_links":0,"syntology":null},{"paper":"/paper/adv-diffusion-imperceptible-adversarial-face","slug":"adv-diffusion-imperceptible-adversarial-face","title":"Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model","date":"2023-12-18","arxiv_id":"2312.11285","n_code_links":1,"syntology":null},{"paper":"/paper/haar-text-conditioned-generative-model-of-3d","slug":"haar-text-conditioned-generative-model-of-3d","title":"HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles","date":"2023-12-18","arxiv_id":"2312.11666","n_code_links":1,"syntology":null},{"paper":"/paper/facetalk-audio-driven-motion-diffusion-for","slug":"facetalk-audio-driven-motion-diffusion-for","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","date":"2023-12-13","arxiv_id":"2312.08459","n_code_links":1,"syntology":null},{"paper":null,"slug":"permod-perceptually-grounded-voice","title":"PerMod: Perceptually Grounded Voice Modification with Latent Diffusion Models","date":"2023-12-13","arxiv_id":"2312.08494","n_code_links":0,"syntology":null},{"paper":"/paper/anomalydiffusion-few-shot-anomaly-image","slug":"anomalydiffusion-few-shot-anomaly-image","title":"AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model","date":"2023-12-10","arxiv_id":"2312.05767","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["sjtuplayer/anomalydiffusion"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/interactdiffusion-interaction-control-in-text","slug":"interactdiffusion-interaction-control-in-text","title":"InteractDiffusion: Interaction Control in Text-to-Image Diffusion Models","date":"2023-12-10","arxiv_id":"2312.05849","n_code_links":1,"syntology":null},{"paper":null,"slug":"cascade-zero123-one-image-to-highly","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","date":"2023-12-07","arxiv_id":"2312.04424","n_code_links":0,"syntology":null},{"paper":"/paper/emotional-speech-driven-3d-body-animation-via","slug":"emotional-speech-driven-3d-body-animation-via","title":"Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion","date":"2023-12-07","arxiv_id":"2312.04466","n_code_links":1,"syntology":null},{"paper":null,"slug":"koala-self-attention-matters-in-knowledge","title":"KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis","date":"2023-12-07","arxiv_id":"2312.04005","n_code_links":0,"syntology":null},{"paper":null,"slug":"lsegdiff-a-latent-diffusion-model-for-medical","title":"LSegDiff: A Latent Diffusion Model for Medical Image Segmentation","date":"2023-12-07","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"foodfusion-a-latent-diffusion-model-for","title":"FoodFusion: A Latent Diffusion Model for Realistic Food Image Generation","date":"2023-12-06","arxiv_id":"2312.03540","n_code_links":0,"syntology":null},{"paper":"/paper/tokencompose-grounding-diffusion-with-token","slug":"tokencompose-grounding-diffusion-with-token","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","date":"2023-12-06","arxiv_id":"2312.03626","n_code_links":1,"syntology":null},{"paper":"/paper/xcube-mathcal-x-3-large-scale-3d-generative","slug":"xcube-mathcal-x-3-large-scale-3d-generative","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","date":"2023-12-06","arxiv_id":"2312.03806","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["nv-tlabs/XCube"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/genie-generative-hard-negative-images-through","slug":"genie-generative-hard-negative-images-through","title":"GeNIe: Generative Hard Negative Images Through Diffusion","date":"2023-12-05","arxiv_id":"2312.02548","n_code_links":1,"syntology":null},{"paper":"/paper/visconet-bridging-and-harmonizing-visual-and","slug":"visconet-bridging-and-harmonizing-visual-and","title":"ViscoNet: Bridging and Harmonizing Visual and Textual Conditioning for ControlNet","date":"2023-12-05","arxiv_id":"2312.03154","n_code_links":1,"syntology":null},{"paper":null,"slug":"taming-latent-diffusion-models-to-see-in-the","title":"LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models","date":"2023-12-02","arxiv_id":"2312.01027","n_code_links":0,"syntology":null},{"paper":null,"slug":"s2st-image-to-image-translation-in-the-seed","title":"S2ST: Image-to-Image Translation in the Seed Space of Latent Diffusion","date":"2023-11-30","arxiv_id":"2312.00116","n_code_links":0,"syntology":null},{"paper":null,"slug":"surf-d-high-quality-surface-generation-for","title":"Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models","date":"2023-11-28","arxiv_id":"2311.17050","n_code_links":0,"syntology":null},{"paper":"/paper/street-tryon-learning-in-the-wild-virtual-try","slug":"street-tryon-learning-in-the-wild-virtual-try","title":"Street TryOn: Learning In-the-Wild Virtual Try-On from Unpaired Person Images","date":"2023-11-27","arxiv_id":"2311.16094","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-anomaly-detection-via-spatio-temporal","title":"Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach","date":"2023-11-27","arxiv_id":"2311.16514","n_code_links":0,"syntology":null},{"paper":"/paper/latent-diffusion-prior-enhanced-deep","slug":"latent-diffusion-prior-enhanced-deep","title":"Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging","date":"2023-11-24","arxiv_id":"2311.14280","n_code_links":1,"syntology":null},{"paper":"/paper/generative-de-quantization-for-neural-speech","slug":"generative-de-quantization-for-neural-speech","title":"Generative De-Quantization for Neural Speech Codec via Latent Diffusion","date":"2023-11-14","arxiv_id":"2311.08330","n_code_links":1,"syntology":null},{"paper":"/paper/impus-image-morphing-with-perceptually","slug":"impus-image-morphing-with-perceptually","title":"IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models","date":"2023-11-12","arxiv_id":"2311.06792","n_code_links":1,"syntology":null},{"paper":null,"slug":"brainnetdiff-generative-ai-empowers-brain","title":"BrainNetDiff: Generative AI Empowers Brain Network Generation via Multimodal Diffusion Model","date":"2023-11-09","arxiv_id":"2311.05199","n_code_links":0,"syntology":null},{"paper":"/paper/latent-diffusion-model-for-conditional","slug":"latent-diffusion-model-for-conditional","title":"Latent Diffusion Model for Conditional Reservoir Facies Generation","date":"2023-11-03","arxiv_id":"2311.01968","n_code_links":1,"syntology":null},{"paper":"/paper/adaptive-latent-diffusion-model-for-3d","slug":"adaptive-latent-diffusion-model-for-3d","title":"Adaptive Latent Diffusion Model for 3D Medical Image to Image Translation: Multi-modal Magnetic Resonance Imaging Study","date":"2023-11-01","arxiv_id":"2311.00265","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":5,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["jongdory/aldm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/attribute-based-interpretable-evaluation","slug":"attribute-based-interpretable-evaluation","title":"Attribute Based Interpretable Evaluation Metrics for Generative Models","date":"2023-10-26","arxiv_id":"2310.17261","n_code_links":1,"syntology":null},{"paper":"/paper/enhancing-high-resolution-3d-generation","slug":"enhancing-high-resolution-3d-generation","title":"Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping","date":"2023-10-19","arxiv_id":"2310.12474","n_code_links":1,"syntology":{"ran":3,"of":9,"n_ran_checked":3,"n_instrument":0,"unverified":6,"pointer_only":0,"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) · 6 unverified","official":{"repos":["fudan-zvg/pgc-3d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"biomedjourney-counterfactual-biomedical-image","title":"BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys","date":"2023-10-16","arxiv_id":"2310.10765","n_code_links":0,"syntology":null},{"paper":"/paper/image-compression-and-decompression-framework","slug":"image-compression-and-decompression-framework","title":"Image Compression and Decompression Framework Based on Latent Diffusion Model for Breast Mammography","date":"2023-10-08","arxiv_id":"2310.05299","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-and-improving-adversarial","slug":"understanding-and-improving-adversarial","title":"Targeted Attack Improves Protection against Unauthorized Diffusion Customization","date":"2023-10-07","arxiv_id":"2310.04687","n_code_links":2,"syntology":{"ran":15,"of":24,"n_ran_checked":13,"n_instrument":2,"unverified":9,"pointer_only":16,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","official":{"repos":["psyker-team/mist-v2","caradryanliang/improvedadvdm"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":8,"ran_from_kinds":["community","official"]}}},{"paper":null,"slug":"realistic-speech-to-face-generation-with","title":"Realistic Speech-to-Face Generation with Speech-Conditioned Latent Diffusion Model with Face Prior","date":"2023-10-05","arxiv_id":"2310.03363","n_code_links":0,"syntology":null},{"paper":null,"slug":"ed-nerf-efficient-text-guided-editing-of-3d","title":"ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF","date":"2023-10-04","arxiv_id":"2310.02712","n_code_links":0,"syntology":null},{"paper":"/paper/conditional-diffusion-distillation","slug":"conditional-diffusion-distillation","title":"CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation","date":"2023-10-02","arxiv_id":"2310.01407","n_code_links":1,"syntology":null},{"paper":null,"slug":"decoding-realistic-images-from-brain-activity","title":"Decoding Realistic Images from Brain Activity with Contrastive Self-supervision and Latent Diffusion","date":"2023-09-30","arxiv_id":"2310.00318","n_code_links":0,"syntology":null},{"paper":null,"slug":"emu-enhancing-image-generation-models-using","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","date":"2023-09-27","arxiv_id":"2309.15807","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-based-holistic-texture","title":"Diffusion-based Holistic Texture Rectification and Synthesis","date":"2023-09-26","arxiv_id":"2309.14759","n_code_links":0,"syntology":null},{"paper":null,"slug":"latent-diffusion-models-for-structural","title":"Latent Diffusion Models for Structural Component Design","date":"2023-09-20","arxiv_id":"2309.11601","n_code_links":0,"syntology":null},{"paper":null,"slug":"light-field-diffusion-for-single-view-novel","title":"Light Field Diffusion for Single-View Novel View Synthesis","date":"2023-09-20","arxiv_id":"2309.11525","n_code_links":0,"syntology":null},{"paper":null,"slug":"promptvc-flexible-stylistic-voice-conversion","title":"PromptVC: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts","date":"2023-09-17","arxiv_id":"2309.09262","n_code_links":0,"syntology":null},{"paper":"/paper/adapt-and-diffuse-sample-adaptive","slug":"adapt-and-diffuse-sample-adaptive","title":"Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models","date":"2023-09-12","arxiv_id":"2309.06642","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["z-fabian/flash-diffusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/from-text-to-mask-localizing-entities-using","slug":"from-text-to-mask-localizing-entities-using","title":"From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models","date":"2023-09-08","arxiv_id":"2309.04109","n_code_links":1,"syntology":null},{"paper":null,"slug":"improving-visual-quality-and-transferability","title":"Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restoration","date":"2023-09-04","arxiv_id":"2309.01582","n_code_links":0,"syntology":null},{"paper":"/paper/pathldm-text-conditioned-latent-diffusion","slug":"pathldm-text-conditioned-latent-diffusion","title":"PathLDM: Text conditioned Latent Diffusion Model for Histopathology","date":"2023-09-01","arxiv_id":"2309.00748","n_code_links":1,"syntology":{"ran":11,"of":12,"n_ran_checked":5,"n_instrument":6,"unverified":1,"pointer_only":12,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 3 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cvlab-stonybrook/pathldm"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/inversesr-3d-brain-mri-super-resolution-using","slug":"inversesr-3d-brain-mri-super-resolution-using","title":"InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model","date":"2023-08-23","arxiv_id":"2308.12465","n_code_links":1,"syntology":{"ran":10,"of":10,"n_ran_checked":6,"n_instrument":4,"unverified":0,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","official":{"repos":["biomedai-ucsc/inversesr"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unibrain-unify-image-reconstruction-and","title":"UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity","date":"2023-08-14","arxiv_id":"2308.07428","n_code_links":0,"syntology":null},{"paper":null,"slug":"shape-guided-conditional-latent-diffusion","title":"Shape-guided Conditional Latent Diffusion Models for Synthesising Brain Vasculature","date":"2023-08-13","arxiv_id":"2308.06781","n_code_links":0,"syntology":null},{"paper":"/paper/audioldm-2-learning-holistic-audio-generation","slug":"audioldm-2-learning-holistic-audio-generation","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","date":"2023-08-10","arxiv_id":"2308.05734","n_code_links":2,"syntology":{"ran":16,"of":27,"n_ran_checked":16,"n_instrument":0,"unverified":11,"pointer_only":19,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","official":{"repos":["haoheliu/AudioLDM2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/idiff-face-synthetic-based-face-recognition","slug":"idiff-face-synthetic-based-face-recognition","title":"IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models","date":"2023-08-09","arxiv_id":"2308.04995","n_code_links":1,"syntology":{"ran":19,"of":21,"n_ran_checked":16,"n_instrument":3,"unverified":2,"pointer_only":21,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["fdbtrs/IDiff-Face"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/synthetic-augmentation-with-large-scale","slug":"synthetic-augmentation-with-large-scale","title":"Synthetic Augmentation with Large-scale Unconditional Pre-training","date":"2023-08-08","arxiv_id":"2308.04020","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-biometric-capacity-of-generative-face","title":"On the Biometric Capacity of Generative Face Models","date":"2023-08-03","arxiv_id":"2308.02065","n_code_links":0,"syntology":null},{"paper":null,"slug":"contrastive-conditional-latent-diffusion-for","title":"Contrastive Conditional Latent Diffusion for Audio-visual Segmentation","date":"2023-07-31","arxiv_id":"2307.16579","n_code_links":0,"syntology":null},{"paper":null,"slug":"seeing-through-the-brain-image-reconstruction","title":"Seeing through the Brain: Image Reconstruction of Visual Perception from Human Brain Signals","date":"2023-07-27","arxiv_id":"2308.02510","n_code_links":0,"syntology":null},{"paper":null,"slug":"iterative-reconstruction-based-on-latent","title":"Fast and Stable Diffusion Inverse Solver with History Gradient Update","date":"2023-07-22","arxiv_id":"2307.12070","n_code_links":0,"syntology":null},{"paper":"/paper/divide-bind-your-attention-for-improved","slug":"divide-bind-your-attention-for-improved","title":"Divide & Bind Your Attention for Improved Generative Semantic Nursing","date":"2023-07-20","arxiv_id":"2307.10864","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["boschresearch/Divide-and-Bind"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"ef64863f87c7aef86f65bc850a619bbe3c6484913e357f9eaac207fb4cc611b4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}