{"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/12","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":12,"pages_in_order":67,"rows_per_page":100,"rows":[1101,1200],"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/11","next":"/task/image-generation/papers/13","papers":[{"url":"/paper/embedding-an-ethical-mind-aligning-text-to","slug":"embedding-an-ethical-mind-aligning-text-to","title":"Embedding an Ethical Mind: Aligning Text-to-Image Synthesis via Lightweight Value Optimization","date":"2024-10-16","arxiv_id":"2410.12700","repositories_listed":1,"syntology":null},{"url":"/paper/facechain-fact-face-adapter-with-decoupled","slug":"facechain-fact-face-adapter-with-decoupled","title":"FaceChain-FACT: Face Adapter with Decoupled Training for Identity-preserved Personalization","date":"2024-10-16","arxiv_id":"2410.12312","repositories_listed":1,"syntology":null},{"url":"/paper/stabilize-the-latent-space-for-image","slug":"stabilize-the-latent-space-for-image","title":"Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective","date":"2024-10-16","arxiv_id":"2410.12490","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 2 unverified","sample_list":"/paper/stabilize-the-latent-space-for-image#ran","syntology_url":"https://syntology.ai/paper/2410.12490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.12490"}},"official":{"repos":["DAMO-NLP-SG/DiGIT"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/chathousediffusion-prompt-guided-generation","slug":"chathousediffusion-prompt-guided-generation","title":"ChatHouseDiffusion: Prompt-Guided Generation and Editing of Floor Plans","date":"2024-10-15","arxiv_id":"2410.11908","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-diffusion-models-a-comprehensive","slug":"efficient-diffusion-models-a-comprehensive","title":"Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices","date":"2024-10-15","arxiv_id":"2410.11795","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-effectiveness-of-dataset-alignment-for","slug":"on-the-effectiveness-of-dataset-alignment-for","title":"On the Effectiveness of Dataset Alignment for Fake Image Detection","date":"2024-10-15","arxiv_id":"2410.11835","repositories_listed":1,"syntology":null},{"url":"/paper/anatomical-feature-prioritized-loss-for","slug":"anatomical-feature-prioritized-loss-for","title":"Anatomical feature-prioritized loss for enhanced MR to CT translation","date":"2024-10-14","arxiv_id":"2410.10328","repositories_listed":1,"syntology":null},{"url":"/paper/customize-your-visual-autoregressive-recipe","slug":"customize-your-visual-autoregressive-recipe","title":"Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling","date":"2024-10-14","arxiv_id":"2410.10511","repositories_listed":1,"syntology":null},{"url":"/paper/deep-compression-autoencoder-for-efficient","slug":"deep-compression-autoencoder-for-efficient","title":"Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models","date":"2024-10-14","arxiv_id":"2410.10733","repositories_listed":1,"syntology":{"n":30,"n_ran":7,"n_constructed":6,"n_ran_checked":7,"n_instrument":0,"n_unverified":23,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 6 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) · 23 unverified","sample_list":"/paper/deep-compression-autoencoder-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2410.10733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10733"}},"official":{"repos":["mit-han-lab/efficientvit"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":23,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluating-semantic-variation-in-text-to","slug":"evaluating-semantic-variation-in-text-to","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","date":"2024-10-14","arxiv_id":"2410.10291","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evaluating-semantic-variation-in-text-to#ran","syntology_url":"https://syntology.ai/paper/2410.10291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10291"}},"official":{"repos":["zhuxiangru/semvarbench"],"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"]}}},{"url":"/paper/fasterdit-towards-faster-diffusion","slug":"fasterdit-towards-faster-diffusion","title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","date":"2024-10-14","arxiv_id":"2410.10356","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":6,"n_ran_checked":6,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 6 samples that ran constructed an object rather than computing a result","sample_list":"/paper/fasterdit-towards-faster-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.10356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10356"}},"official":null}},{"url":"/paper/first-creating-backgrounds-then-rendering","slug":"first-creating-backgrounds-then-rendering","title":"First Creating Backgrounds Then Rendering Texts: A New Paradigm for Visual Text Blending","date":"2024-10-14","arxiv_id":"2410.10168","repositories_listed":1,"syntology":null},{"url":"/paper/high-precision-dichotomous-image-segmentation","slug":"high-precision-dichotomous-image-segmentation","title":"High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity","date":"2024-10-14","arxiv_id":"2410.10105","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/high-precision-dichotomous-image-segmentation#ran","syntology_url":"https://syntology.ai/paper/2410.10105","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10105"}},"official":null}},{"url":"/paper/how-to-backdoor-consistency-models","slug":"how-to-backdoor-consistency-models","title":"How to Backdoor Consistency Models?","date":"2024-10-14","arxiv_id":"2410.19785","repositories_listed":1,"syntology":null},{"url":"/paper/textctrl-diffusion-based-scene-text-editing","slug":"textctrl-diffusion-based-scene-text-editing","title":"TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control","date":"2024-10-14","arxiv_id":"2410.10133","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/textctrl-diffusion-based-scene-text-editing#ran","syntology_url":"https://syntology.ai/paper/2410.10133","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10133"}},"official":{"repos":["weichaozeng/textctrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vision-guided-and-mask-enhanced-adaptive","slug":"vision-guided-and-mask-enhanced-adaptive","title":"Vision-guided and Mask-enhanced Adaptive Denoising for Prompt-based Image Editing","date":"2024-10-14","arxiv_id":"2410.10496","repositories_listed":1,"syntology":null},{"url":"/paper/when-does-perceptual-alignment-benefit-vision","slug":"when-does-perceptual-alignment-benefit-vision","title":"When Does Perceptual Alignment Benefit Vision Representations?","date":"2024-10-14","arxiv_id":"2410.10817","repositories_listed":1,"syntology":null},{"url":"/paper/intermediate-representations-for-enhanced","slug":"intermediate-representations-for-enhanced","title":"Generating Intermediate Representations for Compositional Text-To-Image Generation","date":"2024-10-13","arxiv_id":"2410.09792","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_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) · 0 unverified","sample_list":"/paper/intermediate-representations-for-enhanced#ran","syntology_url":"https://syntology.ai/paper/2410.09792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09792"}},"official":{"repos":["rang1991/public-intermediate-semantics-for-generation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-class-activity-classification-in-videos","slug":"multi-class-activity-classification-in-videos","title":"Multi class activity classification in videos using Motion History Image generation","date":"2024-10-13","arxiv_id":"2410.09902","repositories_listed":1,"syntology":null},{"url":"/paper/tulip-token-length-upgraded-clip","slug":"tulip-token-length-upgraded-clip","title":"TULIP: Token-length Upgraded CLIP","date":"2024-10-13","arxiv_id":"2410.10034","repositories_listed":1,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":7,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/tulip-token-length-upgraded-clip#ran","syntology_url":"https://syntology.ai/paper/2410.10034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10034"}},"official":{"repos":["ivonajdenkoska/tulip"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/ctrlora-an-extensible-and-efficient-framework","slug":"ctrlora-an-extensible-and-efficient-framework","title":"CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation","date":"2024-10-12","arxiv_id":"2410.09400","repositories_listed":1,"syntology":{"n":22,"n_ran":13,"n_constructed":6,"n_ran_checked":10,"n_instrument":3,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/ctrlora-an-extensible-and-efficient-framework#ran","syntology_url":"https://syntology.ai/paper/2410.09400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09400"}},"official":{"repos":["xyfjason/ctrlora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["community","official","unlocated"]}}},{"url":"/paper/duodiff-accelerating-diffusion-models-with-a","slug":"duodiff-accelerating-diffusion-models-with-a","title":"DuoDiff: Accelerating Diffusion Models with a Dual-Backbone Approach","date":"2024-10-12","arxiv_id":"2410.09633","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/duodiff-accelerating-diffusion-models-with-a#ran","syntology_url":"https://syntology.ai/paper/2410.09633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09633"}},"official":{"repos":["razvanmatisan/duodiff"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/one-shot-generative-domain-adaptation-in-3d","slug":"one-shot-generative-domain-adaptation-in-3d","title":"One-shot Generative Domain Adaptation in 3D GANs","date":"2024-10-11","arxiv_id":"2410.08824","repositories_listed":1,"syntology":null},{"url":"/paper/scenecraft-layout-guided-3d-scene-generation","slug":"scenecraft-layout-guided-3d-scene-generation","title":"SceneCraft: Layout-Guided 3D Scene Generation","date":"2024-10-11","arxiv_id":"2410.09049","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scenecraft-layout-guided-3d-scene-generation#ran","syntology_url":"https://syntology.ai/paper/2410.09049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09049"}},"official":{"repos":["orangesodahub/scenecraft"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/synth-sonar-sonar-image-synthesis-with","slug":"synth-sonar-sonar-image-synthesis-with","title":"Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting","date":"2024-10-11","arxiv_id":"2410.08612","repositories_listed":1,"syntology":null},{"url":"/paper/a-unified-debiasing-approach-for-vision","slug":"a-unified-debiasing-approach-for-vision","title":"A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks","date":"2024-10-10","arxiv_id":"2410.07593","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/a-unified-debiasing-approach-for-vision#ran","syntology_url":"https://syntology.ai/paper/2410.07593","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07593"}},"official":{"repos":["HoinJung/Unified-Debiaisng-VLM-SFID"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/meissonic-revitalizing-masked-generative","slug":"meissonic-revitalizing-masked-generative","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","date":"2024-10-10","arxiv_id":"2410.08261","repositories_listed":1,"syntology":{"n":12,"n_ran":4,"n_constructed":1,"n_ran_checked":1,"n_instrument":3,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/meissonic-revitalizing-masked-generative#ran","syntology_url":"https://syntology.ai/paper/2410.08261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08261"}},"official":{"repos":["viiika/Meissonic"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/minorityprompt-text-to-minority-image","slug":"minorityprompt-text-to-minority-image","title":"Minority-Focused Text-to-Image Generation via Prompt Optimization","date":"2024-10-10","arxiv_id":"2410.07838","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"8 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minorityprompt-text-to-minority-image#ran","syntology_url":"https://syntology.ai/paper/2410.07838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07838"}},"official":{"repos":["anonymous5293/minorityprompt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/relational-diffusion-distillation-for","slug":"relational-diffusion-distillation-for","title":"Relational Diffusion Distillation for Efficient Image Generation","date":"2024-10-10","arxiv_id":"2410.07679","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"6 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/relational-diffusion-distillation-for#ran","syntology_url":"https://syntology.ai/paper/2410.07679","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07679"}},"official":{"repos":["cantbebetter2/rdd"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/synthesizing-multi-class-surgical-datasets","slug":"synthesizing-multi-class-surgical-datasets","title":"Data Augmentation for Surgical Scene Segmentation with Anatomy-Aware Diffusion Models","date":"2024-10-10","arxiv_id":"2410.07753","repositories_listed":1,"syntology":null},{"url":"/paper/evolvedirector-approaching-advanced-text-to","slug":"evolvedirector-approaching-advanced-text-to","title":"EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models","date":"2024-10-09","arxiv_id":"2410.07133","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-visual-instruction-tuning","slug":"personalized-visual-instruction-tuning","title":"Personalized Visual Instruction Tuning","date":"2024-10-09","arxiv_id":"2410.07113","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/personalized-visual-instruction-tuning#ran","syntology_url":"https://syntology.ai/paper/2410.07113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07113"}},"official":{"repos":["sterzhang/pvit"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/representation-alignment-for-generation","slug":"representation-alignment-for-generation","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","date":"2024-10-09","arxiv_id":"2410.06940","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":0,"n_instrument":7,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"7 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; 7 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/representation-alignment-for-generation#ran","syntology_url":"https://syntology.ai/paper/2410.06940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06940"}},"official":{"repos":["sihyun-yu/REPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/textlap-customizing-language-models-for-text","slug":"textlap-customizing-language-models-for-text","title":"TextLap: Customizing Language Models for Text-to-Layout Planning","date":"2024-10-09","arxiv_id":"2410.12844","repositories_listed":1,"syntology":null},{"url":"/paper/ap-ldm-attentive-and-progressive-latent","slug":"ap-ldm-attentive-and-progressive-latent","title":"AP-LDM: Attentive and Progressive Latent Diffusion Model for Training-Free High-Resolution Image Generation","date":"2024-10-08","arxiv_id":"2410.06055","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ap-ldm-attentive-and-progressive-latent#ran","syntology_url":"https://syntology.ai/paper/2410.06055","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06055"}},"official":{"repos":["kmittle/ap-ldm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/story-adapter-a-training-free-iterative","slug":"story-adapter-a-training-free-iterative","title":"Story-Adapter: A Training-free Iterative Framework for Long Story Visualization","date":"2024-10-08","arxiv_id":"2410.06244","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/story-adapter-a-training-free-iterative#ran","syntology_url":"https://syntology.ai/paper/2410.06244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06244"}},"official":null}},{"url":"/paper/think-while-you-generate-discrete-diffusion","slug":"think-while-you-generate-discrete-diffusion","title":"Think While You Generate: Discrete Diffusion with Planned Denoising","date":"2024-10-08","arxiv_id":"2410.06264","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":2,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/think-while-you-generate-discrete-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.06264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.06264"}},"official":{"repos":["liusulin/ddpd"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/training-free-diffusion-model-alignment-with","slug":"training-free-diffusion-model-alignment-with","title":"Training-free Diffusion Model Alignment with Sampling Demons","date":"2024-10-08","arxiv_id":"2410.05760","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-free-diffusion-model-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2410.05760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05760"}},"official":{"repos":["aiiu-lab/DemonSampling"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/test-time-adaptation-for-keypoint-based","slug":"test-time-adaptation-for-keypoint-based","title":"Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis","date":"2024-10-05","arxiv_id":"2410.04298","repositories_listed":1,"syntology":null},{"url":"/paper/images-speak-volumes-user-centric-assessment","slug":"images-speak-volumes-user-centric-assessment","title":"Images Speak Volumes: User-Centric Assessment of Image Generation for Accessible Communication","date":"2024-10-04","arxiv_id":"2410.03430","repositories_listed":1,"syntology":null},{"url":"/paper/lantern-accelerating-visual-autoregressive","slug":"lantern-accelerating-visual-autoregressive","title":"LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding","date":"2024-10-04","arxiv_id":"2410.03355","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-diffusion-model-activations-have-been","slug":"not-all-diffusion-model-activations-have-been","title":"Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features","date":"2024-10-04","arxiv_id":"2410.03558","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 2 unverified","sample_list":"/paper/not-all-diffusion-model-activations-have-been#ran","syntology_url":"https://syntology.ai/paper/2410.03558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03558"}},"official":{"repos":["darkbblue/generic-diffusion-feature"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/redefining-temporal-modeling-in-video","slug":"redefining-temporal-modeling-in-video","title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","date":"2024-10-04","arxiv_id":"2410.03160","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/redefining-temporal-modeling-in-video#ran","syntology_url":"https://syntology.ai/paper/2410.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03160"}},"official":{"repos":["yaofang-liu/fvdm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/controlar-controllable-image-generation-with","slug":"controlar-controllable-image-generation-with","title":"ControlAR: Controllable Image Generation with Autoregressive Models","date":"2024-10-03","arxiv_id":"2410.02705","repositories_listed":1,"syntology":{"n":24,"n_ran":17,"n_constructed":8,"n_ran_checked":17,"n_instrument":0,"n_unverified":7,"n_honours":2,"n_violates":1,"n_no_contract":14,"n_pointer_only":4,"phrase":"17 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 2 honoured, 1 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/controlar-controllable-image-generation-with#ran","syntology_url":"https://syntology.ai/paper/2410.02705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02705"}},"official":{"repos":["hustvl/controlar"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":8,"n_ran_no_instrument_failure":17,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/sageattention-accurate-8-bit-attention-for","slug":"sageattention-accurate-8-bit-attention-for","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","date":"2024-10-03","arxiv_id":"2410.02367","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/sageattention-accurate-8-bit-attention-for#ran","syntology_url":"https://syntology.ai/paper/2410.02367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02367"}},"official":{"repos":["thu-ml/SageAttention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/unleashing-the-potential-of-the-diffusion","slug":"unleashing-the-potential-of-the-diffusion","title":"Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation","date":"2024-10-03","arxiv_id":"2410.02369","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unleashing-the-potential-of-the-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.02369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02369"}},"official":{"repos":["aim-uofa/diffews"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-spark-of-vision-language-intelligence-2","slug":"a-spark-of-vision-language-intelligence-2","title":"A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation","date":"2024-10-02","arxiv_id":"2410.01912","repositories_listed":1,"syntology":null},{"url":"/paper/aggregation-of-multi-diffusion-models-for","slug":"aggregation-of-multi-diffusion-models-for","title":"Improving Fine-Grained Control via Aggregation of Multiple Diffusion Models","date":"2024-10-02","arxiv_id":"2410.01262","repositories_listed":1,"syntology":null},{"url":"/paper/data-extrapolation-for-text-to-image","slug":"data-extrapolation-for-text-to-image","title":"Data Extrapolation for Text-to-image Generation on Small Datasets","date":"2024-10-02","arxiv_id":"2410.01638","repositories_listed":1,"syntology":null},{"url":"/paper/edge-preserving-noise-for-diffusion-models","slug":"edge-preserving-noise-for-diffusion-models","title":"Edge-preserving noise for diffusion models","date":"2024-10-02","arxiv_id":"2410.01540","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/edge-preserving-noise-for-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2410.01540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01540"}},"official":null}},{"url":"/paper/imagefolder-autoregressive-image-generation","slug":"imagefolder-autoregressive-image-generation","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","date":"2024-10-02","arxiv_id":"2410.01756","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/imagefolder-autoregressive-image-generation#ran","syntology_url":"https://syntology.ai/paper/2410.01756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01756"}},"official":{"repos":["lxa9867/imagefolder"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/knobgen-controlling-the-sophistication-of","slug":"knobgen-controlling-the-sophistication-of","title":"KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models","date":"2024-10-02","arxiv_id":"2410.01595","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/knobgen-controlling-the-sophistication-of#ran","syntology_url":"https://syntology.ai/paper/2410.01595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01595"}},"official":{"repos":["aminK8/KnobGen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/normalizing-flow-based-metric-for-image","slug":"normalizing-flow-based-metric-for-image","title":"Normalizing Flow-Based Metric for Image Generation","date":"2024-10-02","arxiv_id":"2410.02004","repositories_listed":1,"syntology":null},{"url":"/paper/cusconcept-customized-visual-concept","slug":"cusconcept-customized-visual-concept","title":"CusConcept: Customized Visual Concept Decomposition with Diffusion Models","date":"2024-10-01","arxiv_id":"2410.00398","repositories_listed":1,"syntology":null},{"url":"/paper/necomimi-neural-cognitive-multimodal-eeg","slug":"necomimi-neural-cognitive-multimodal-eeg","title":"NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Models","date":"2024-10-01","arxiv_id":"2410.00712","repositories_listed":1,"syntology":null},{"url":"/paper/clr-gan-improving-gans-stability-and-quality","slug":"clr-gan-improving-gans-stability-and-quality","title":"CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction","date":"2024-09-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/devil-is-in-details-locality-aware-3d","slug":"devil-is-in-details-locality-aware-3d","title":"Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation","date":"2024-09-30","arxiv_id":"2409.20332","repositories_listed":1,"syntology":null},{"url":"/paper/effective-diffusion-transformer-architecture","slug":"effective-diffusion-transformer-architecture","title":"Effective Diffusion Transformer Architecture for Image Super-Resolution","date":"2024-09-29","arxiv_id":"2409.19589","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-image-synthesis-with-diffusion","slug":"conditional-image-synthesis-with-diffusion","title":"Conditional Image Synthesis with Diffusion Models: A Survey","date":"2024-09-28","arxiv_id":"2409.19365","repositories_listed":1,"syntology":null},{"url":"/paper/pruning-then-reweighting-towards-data","slug":"pruning-then-reweighting-towards-data","title":"Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models","date":"2024-09-27","arxiv_id":"2409.19128","repositories_listed":1,"syntology":null},{"url":"/paper/flowturbo-towards-real-time-flow-based-image","slug":"flowturbo-towards-real-time-flow-based-image","title":"FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner","date":"2024-09-26","arxiv_id":"2409.18128","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/flowturbo-towards-real-time-flow-based-image#ran","syntology_url":"https://syntology.ai/paper/2409.18128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18128"}},"official":{"repos":["shiml20/flowturbo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/lotus-diffusion-based-visual-foundation-model","slug":"lotus-diffusion-based-visual-foundation-model","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","date":"2024-09-26","arxiv_id":"2409.18124","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":12,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lotus-diffusion-based-visual-foundation-model#ran","syntology_url":"https://syntology.ai/paper/2409.18124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18124"}},"official":null}},{"url":"/paper/pioneering-reliable-assessment-in-text-to","slug":"pioneering-reliable-assessment-in-text-to","title":"Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion","date":"2024-09-26","arxiv_id":"2409.17928","repositories_listed":1,"syntology":null},{"url":"/paper/realistic-evaluation-of-model-merging-for","slug":"realistic-evaluation-of-model-merging-for","title":"Realistic Evaluation of Model Merging for Compositional Generalization","date":"2024-09-26","arxiv_id":"2409.18314","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/realistic-evaluation-of-model-merging-for#ran","syntology_url":"https://syntology.ai/paper/2409.18314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18314"}},"official":{"repos":["r-three/realistic_evaluation_of_model_merging_for_compositional_generalization"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/resolving-multi-condition-confusion-for","slug":"resolving-multi-condition-confusion-for","title":"Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation","date":"2024-09-26","arxiv_id":"2409.17920","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/resolving-multi-condition-confusion-for#ran","syntology_url":"https://syntology.ai/paper/2409.17920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17920"}},"official":{"repos":["hqhqaq/mip-adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/trustworthy-text-to-image-diffusion-models-a","slug":"trustworthy-text-to-image-diffusion-models-a","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","date":"2024-09-26","arxiv_id":"2409.18214","repositories_listed":1,"syntology":null},{"url":"/paper/pix2next-leveraging-vision-foundation-models","slug":"pix2next-leveraging-vision-foundation-models","title":"Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation","date":"2024-09-25","arxiv_id":"2409.16706","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-sliders-for-fine-grained-control","slug":"prompt-sliders-for-fine-grained-control","title":"Prompt Sliders for Fine-Grained Control, Editing and Erasing of Concepts in Diffusion Models","date":"2024-09-25","arxiv_id":"2409.16535","repositories_listed":1,"syntology":null},{"url":"/paper/towards-general-text-guided-image-synthesis","slug":"towards-general-text-guided-image-synthesis","title":"Towards General Text-guided Image Synthesis for Customized Multimodal Brain MRI Generation","date":"2024-09-25","arxiv_id":"2409.16818","repositories_listed":1,"syntology":null},{"url":"/paper/deep-chroma-compression-of-tone-mapped-images","slug":"deep-chroma-compression-of-tone-mapped-images","title":"Deep chroma compression of tone-mapped images","date":"2024-09-24","arxiv_id":"2409.16032","repositories_listed":1,"syntology":null},{"url":"/paper/maskbit-embedding-free-image-generation-via","slug":"maskbit-embedding-free-image-generation-via","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","date":"2024-09-24","arxiv_id":"2409.16211","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":1,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 1 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) · 1 unverified","sample_list":"/paper/maskbit-embedding-free-image-generation-via#ran","syntology_url":"https://syntology.ai/paper/2409.16211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16211"}},"official":{"repos":["markweberdev/maskbit"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":1,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/monoformer-one-transformer-for-both-diffusion","slug":"monoformer-one-transformer-for-both-diffusion","title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","date":"2024-09-24","arxiv_id":"2409.16280","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/monoformer-one-transformer-for-both-diffusion#ran","syntology_url":"https://syntology.ai/paper/2409.16280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16280"}},"official":{"repos":["MonoFormer/MonoFormer"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fine-tuning-text-to-image-diffusion-models-1","slug":"fine-tuning-text-to-image-diffusion-models-1","title":"Fine Tuning Text-to-Image Diffusion Models for Correcting Anomalous Images","date":"2024-09-23","arxiv_id":"2409.16174","repositories_listed":1,"syntology":null},{"url":"/paper/pixwizard-versatile-image-to-image-visual","slug":"pixwizard-versatile-image-to-image-visual","title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions","date":"2024-09-23","arxiv_id":"2409.15278","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":9,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pixwizard-versatile-image-to-image-visual#ran","syntology_url":"https://syntology.ai/paper/2409.15278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15278"}},"official":{"repos":["afeng-x/pixwizard"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vleu-a-method-for-automatic-evaluation-for","slug":"vleu-a-method-for-automatic-evaluation-for","title":"VLEU: a Method for Automatic Evaluation for Generalizability of Text-to-Image Models","date":"2024-09-23","arxiv_id":"2409.14704","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/vleu-a-method-for-automatic-evaluation-for#ran","syntology_url":"https://syntology.ai/paper/2409.14704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.14704"}},"official":{"repos":["mio7690/VLEU"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/implicit-dynamical-flow-fusion-idff-for","slug":"implicit-dynamical-flow-fusion-idff-for","title":"Implicit Dynamical Flow Fusion (IDFF) for Generative Modeling","date":"2024-09-22","arxiv_id":"2409.14599","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-attacks-on-parts-of-speech-an","slug":"adversarial-attacks-on-parts-of-speech-an","title":"Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation","date":"2024-09-21","arxiv_id":"2409.15381","repositories_listed":1,"syntology":null},{"url":"/paper/evaluating-image-hallucination-in-text-to","slug":"evaluating-image-hallucination-in-text-to","title":"Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering","date":"2024-09-19","arxiv_id":"2409.12784","repositories_listed":1,"syntology":null},{"url":"/paper/hsigene-a-foundation-model-for-hyperspectral","slug":"hsigene-a-foundation-model-for-hyperspectral","title":"HSIGene: A Foundation Model For Hyperspectral Image Generation","date":"2024-09-19","arxiv_id":"2409.12470","repositories_listed":1,"syntology":null},{"url":"/paper/storymaker-towards-holistic-consistent","slug":"storymaker-towards-holistic-consistent","title":"StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation","date":"2024-09-19","arxiv_id":"2409.12576","repositories_listed":1,"syntology":null},{"url":"/paper/cheffusion-multimodal-foundation-model","slug":"cheffusion-multimodal-foundation-model","title":"ChefFusion: Multimodal Foundation Model Integrating Recipe and Food Image Generation","date":"2024-09-18","arxiv_id":"2409.12010","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-image-conditional-diffusion","slug":"fine-tuning-image-conditional-diffusion","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","date":"2024-09-17","arxiv_id":"2409.11355","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fine-tuning-image-conditional-diffusion#ran","syntology_url":"https://syntology.ai/paper/2409.11355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11355"}},"official":{"repos":["VisualComputingInstitute/diffusion-e2e-ft"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/guess-what-i-think-streamlined-eeg-to-image","slug":"guess-what-i-think-streamlined-eeg-to-image","title":"Guess What I Think: Streamlined EEG-to-Image Generation with Latent Diffusion Models","date":"2024-09-17","arxiv_id":"2410.02780","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guess-what-i-think-streamlined-eeg-to-image#ran","syntology_url":"https://syntology.ai/paper/2410.02780","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02780"}},"official":{"repos":["luigisigillo/gwit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/improving-the-efficiency-of-visually","slug":"improving-the-efficiency-of-visually","title":"Improving the Efficiency of Visually Augmented Language Models","date":"2024-09-17","arxiv_id":"2409.11148","repositories_listed":1,"syntology":null},{"url":"/paper/mm2latent-text-to-facial-image-generation-and","slug":"mm2latent-text-to-facial-image-generation-and","title":"MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance","date":"2024-09-17","arxiv_id":"2409.11010","repositories_listed":1,"syntology":null},{"url":"/paper/omnigen-unified-image-generation","slug":"omnigen-unified-image-generation","title":"OmniGen: Unified Image Generation","date":"2024-09-17","arxiv_id":"2409.11340","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omnigen-unified-image-generation#ran","syntology_url":"https://syntology.ai/paper/2409.11340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11340"}},"official":{"repos":["vectorspacelab/omnigen"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2s-odis-two-stage-omni-directional-image","slug":"2s-odis-two-stage-omni-directional-image","title":"2S-ODIS: Two-Stage Omni-Directional Image Synthesis by Geometric Distortion Correction","date":"2024-09-16","arxiv_id":"2409.09969","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/2s-odis-two-stage-omni-directional-image#ran","syntology_url":"https://syntology.ai/paper/2409.09969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.09969"}},"official":{"repos":["islab-sophia/2s-odis"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/motioncom-automatic-and-motion-aware-image","slug":"motioncom-automatic-and-motion-aware-image","title":"MotionCom: Automatic and Motion-Aware Image Composition with LLM and Video Diffusion Prior","date":"2024-09-16","arxiv_id":"2409.10090","repositories_listed":1,"syntology":null},{"url":"/paper/robust-image-representations-with","slug":"robust-image-representations-with","title":"Robust image representations with counterfactual contrastive learning","date":"2024-09-16","arxiv_id":"2409.10365","repositories_listed":1,"syntology":null},{"url":"/paper/finetuning-clip-to-reason-about-pairwise","slug":"finetuning-clip-to-reason-about-pairwise","title":"Finetuning CLIP to Reason about Pairwise Differences","date":"2024-09-15","arxiv_id":"2409.09721","repositories_listed":1,"syntology":null},{"url":"/paper/one-shot-learning-for-pose-guided-person","slug":"one-shot-learning-for-pose-guided-person","title":"One-Shot Learning for Pose-Guided Person Image Synthesis in the Wild","date":"2024-09-15","arxiv_id":"2409.09593","repositories_listed":1,"syntology":null},{"url":"/paper/beta-sigma-vae-separating-beta-and-decoder","slug":"beta-sigma-vae-separating-beta-and-decoder","title":"Beta-Sigma VAE: Separating beta and decoder variance in Gaussian variational autoencoder","date":"2024-09-14","arxiv_id":"2409.09361","repositories_listed":1,"syntology":null},{"url":"/paper/click2mask-local-editing-with-dynamic-mask","slug":"click2mask-local-editing-with-dynamic-mask","title":"Click2Mask: Local Editing with Dynamic Mask Generation","date":"2024-09-12","arxiv_id":"2409.08272","repositories_listed":1,"syntology":null},{"url":"/paper/ditas-quantizing-diffusion-transformers-via","slug":"ditas-quantizing-diffusion-transformers-via","title":"DiTAS: Quantizing Diffusion Transformers via Enhanced Activation Smoothing","date":"2024-09-12","arxiv_id":"2409.07756","repositories_listed":1,"syntology":{"n":19,"n_ran":14,"n_constructed":0,"n_ran_checked":7,"n_instrument":7,"n_unverified":5,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ditas-quantizing-diffusion-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2409.07756","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07756"}},"official":{"repos":["DZY122/DiTAS"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/ezigen-enhancing-zero-shot-subject-driven","slug":"ezigen-enhancing-zero-shot-subject-driven","title":"EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance","date":"2024-09-12","arxiv_id":"2409.08091","repositories_listed":1,"syntology":null},{"url":"/paper/high-frequency-anti-dreambooth-robust-defense","slug":"high-frequency-anti-dreambooth-robust-defense","title":"High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis","date":"2024-09-12","arxiv_id":"2409.08167","repositories_listed":1,"syntology":{"n":6,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"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) · 4 unverified","sample_list":"/paper/high-frequency-anti-dreambooth-robust-defense#ran","syntology_url":"https://syntology.ai/paper/2409.08167","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08167"}},"official":{"repos":["mti-lab/HF-ADB"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-virtual-try-on-with-garment-focused","slug":"improving-virtual-try-on-with-garment-focused","title":"Improving Virtual Try-On with Garment-focused Diffusion Models","date":"2024-09-12","arxiv_id":"2409.08258","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improving-virtual-try-on-with-garment-focused#ran","syntology_url":"https://syntology.ai/paper/2409.08258","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08258"}},"official":{"repos":["siqi0905/gardiff"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scribble-guided-diffusion-for-training-free","slug":"scribble-guided-diffusion-for-training-free","title":"Scribble-Guided Diffusion for Training-free Text-to-Image Generation","date":"2024-09-12","arxiv_id":"2409.08026","repositories_listed":1,"syntology":null},{"url":"/paper/textboost-towards-one-shot-personalization-of","slug":"textboost-towards-one-shot-personalization-of","title":"TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder","date":"2024-09-12","arxiv_id":"2409.08248","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/textboost-towards-one-shot-personalization-of#ran","syntology_url":"https://syntology.ai/paper/2409.08248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08248"}},"official":{"repos":["nahyeonkaty/textboost"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/bio-eng-lmm-ai-assist-chatbot-a-comprehensive","slug":"bio-eng-lmm-ai-assist-chatbot-a-comprehensive","title":"Bio-Eng-LMM AI Assist chatbot: A Comprehensive Tool for Research and Education","date":"2024-09-11","arxiv_id":"2409.07110","repositories_listed":1,"syntology":null}],"record_sha256":"2d89e8eed03ac849b853cc59ace209ccfe7ac5f5952e16459613670e8e08e113","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}