{"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/14","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":14,"pages_in_order":67,"rows_per_page":100,"rows":[1301,1400],"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/13","next":"/task/image-generation/papers/15","papers":[{"url":"/paper/seed-story-multimodal-long-story-generation","slug":"seed-story-multimodal-long-story-generation","title":"SEED-Story: Multimodal Long Story Generation with Large Language Model","date":"2024-07-11","arxiv_id":"2407.08683","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":17,"phrase":"14 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/seed-story-multimodal-long-story-generation#ran","syntology_url":"https://syntology.ai/paper/2407.08683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.08683"}},"official":{"repos":["tencentarc/seed-story"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-attacks-and-defenses-on-text-to","slug":"adversarial-attacks-and-defenses-on-text-to","title":"Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey","date":"2024-07-10","arxiv_id":"2407.15861","repositories_listed":1,"syntology":null},{"url":"/paper/deformation-recovery-diffusion-model-drdm","slug":"deformation-recovery-diffusion-model-drdm","title":"Deformation-Recovery Diffusion Model (DRDM): Instance Deformation for Image Manipulation and Synthesis","date":"2024-07-10","arxiv_id":"2407.07295","repositories_listed":1,"syntology":null},{"url":"/paper/generative-image-as-action-models","slug":"generative-image-as-action-models","title":"Generative Image as Action Models","date":"2024-07-10","arxiv_id":"2407.07875","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/generative-image-as-action-models#ran","syntology_url":"https://syntology.ai/paper/2407.07875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07875"}},"official":{"repos":["MohitShridhar/genima"],"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/mars-mixture-of-auto-regressive-models-for","slug":"mars-mixture-of-auto-regressive-models-for","title":"MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis","date":"2024-07-10","arxiv_id":"2407.07614","repositories_listed":1,"syntology":null},{"url":"/paper/trainable-highly-expressive-activation","slug":"trainable-highly-expressive-activation","title":"Trainable Highly-expressive Activation Functions","date":"2024-07-10","arxiv_id":"2407.07564","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/trainable-highly-expressive-activation#ran","syntology_url":"https://syntology.ai/paper/2407.07564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07564"}},"official":{"repos":["bgu-cs-vil/ditac"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/conceptexpress-harnessing-diffusion-models","slug":"conceptexpress-harnessing-diffusion-models","title":"ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction","date":"2024-07-09","arxiv_id":"2407.07077","repositories_listed":1,"syntology":null},{"url":"/paper/humanrefiner-benchmarking-abnormal-human","slug":"humanrefiner-benchmarking-abnormal-human","title":"HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance","date":"2024-07-09","arxiv_id":"2407.06937","repositories_listed":1,"syntology":null},{"url":"/paper/powerful-and-flexible-personalized-text-to","slug":"powerful-and-flexible-personalized-text-to","title":"Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning","date":"2024-07-09","arxiv_id":"2407.06642","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"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) · 2 unverified","sample_list":"/paper/powerful-and-flexible-personalized-text-to#ran","syntology_url":"https://syntology.ai/paper/2407.06642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06642"}},"official":{"repos":["wfanyue/dpg-t2i-personalization"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/spanish-trocr-leveraging-transfer-learning","slug":"spanish-trocr-leveraging-transfer-learning","title":"Spanish TrOCR: Leveraging Transfer Learning for Language Adaptation","date":"2024-07-09","arxiv_id":"2407.06950","repositories_listed":1,"syntology":null},{"url":"/paper/3d-vessel-graph-generation-using-denoising","slug":"3d-vessel-graph-generation-using-denoising","title":"3D Vessel Graph Generation Using Denoising Diffusion","date":"2024-07-08","arxiv_id":"2407.05842","repositories_listed":1,"syntology":null},{"url":"/paper/fairdiff-fair-segmentation-with-point-image","slug":"fairdiff-fair-segmentation-with-point-image","title":"FairDiff: Fair Segmentation with Point-Image Diffusion","date":"2024-07-08","arxiv_id":"2407.06250","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/fairdiff-fair-segmentation-with-point-image#ran","syntology_url":"https://syntology.ai/paper/2407.06250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.06250"}},"official":{"repos":["wenyi-li/fairdiff"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/perldiff-controllable-street-view-synthesis","slug":"perldiff-controllable-street-view-synthesis","title":"PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Models","date":"2024-07-08","arxiv_id":"2407.06109","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-as-sound-propagation-physics","slug":"diffusion-as-sound-propagation-physics","title":"Diffusion as Sound Propagation: Physics-inspired Model for Ultrasound Image Generation","date":"2024-07-07","arxiv_id":"2407.05428","repositories_listed":1,"syntology":null},{"url":"/paper/mj-bench-is-your-multimodal-reward-model","slug":"mj-bench-is-your-multimodal-reward-model","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","date":"2024-07-05","arxiv_id":"2407.04842","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/mj-bench-is-your-multimodal-reward-model#ran","syntology_url":"https://syntology.ai/paper/2407.04842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04842"}},"official":{"repos":["MJ-Bench/MJ-Bench"],"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/proud-pareto-guided-diffusion-model-for-multi","slug":"proud-pareto-guided-diffusion-model-for-multi","title":"PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation","date":"2024-07-05","arxiv_id":"2407.04493","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":18,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/proud-pareto-guided-diffusion-model-for-multi#ran","syntology_url":"https://syntology.ai/paper/2407.04493","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.04493"}},"official":{"repos":["EvaFlower/Pareto-guided-diffusion-model"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/leveraging-latent-diffusion-models-for","slug":"leveraging-latent-diffusion-models-for","title":"Leveraging Latent Diffusion Models for Training-Free In-Distribution Data Augmentation for Surface Defect Detection","date":"2024-07-04","arxiv_id":"2407.03961","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/leveraging-latent-diffusion-models-for#ran","syntology_url":"https://syntology.ai/paper/2407.03961","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03961"}},"official":{"repos":["intelligolabs/diag"],"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"]}}},{"url":"/paper/performance-of-medical-image-fusion-in-high","slug":"performance-of-medical-image-fusion-in-high","title":"Medical Image Fusion for High-Level Analysis: A Mutual Enhancement Framework for Unaligned PAT and MRI","date":"2024-07-04","arxiv_id":"2407.03992","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/performance-of-medical-image-fusion-in-high#ran","syntology_url":"https://syntology.ai/paper/2407.03992","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03992"}},"official":{"repos":["zhongniuniu/PAMRFuse-plus"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/an-organism-starts-with-a-single-pix-cell-a","slug":"an-organism-starts-with-a-single-pix-cell-a","title":"An Organism Starts with a Single Pix-Cell: A Neural Cellular Diffusion for High-Resolution Image Synthesis","date":"2024-07-03","arxiv_id":"2407.03018","repositories_listed":1,"syntology":null},{"url":"/paper/disco-diff-enhancing-continuous-diffusion","slug":"disco-diff-enhancing-continuous-diffusion","title":"DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents","date":"2024-07-03","arxiv_id":"2407.03300","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":1,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disco-diff-enhancing-continuous-diffusion#ran","syntology_url":"https://syntology.ai/paper/2407.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03300"}},"official":{"repos":["gcorso/disco-diffdock"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mobile-edge-generation-enabled-digital-twin","slug":"mobile-edge-generation-enabled-digital-twin","title":"Mobile Edge Generation-Enabled Digital Twin: Architecture Design and Research Opportunities","date":"2024-07-03","arxiv_id":"2407.02804","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-flow-matching-defining-straight","slug":"consistency-flow-matching-defining-straight","title":"Consistency Flow Matching: Defining Straight Flows with Velocity Consistency","date":"2024-07-02","arxiv_id":"2407.02398","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":7,"phrase":"11 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/consistency-flow-matching-defining-straight#ran","syntology_url":"https://syntology.ai/paper/2407.02398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02398"}},"official":{"repos":["yangling0818/consistency_flow_matching"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/migc-advanced-multi-instance-generation","slug":"migc-advanced-multi-instance-generation","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","date":"2024-07-02","arxiv_id":"2407.02329","repositories_listed":1,"syntology":null},{"url":"/paper/stochastic-solutions-for-simultaneous-seismic","slug":"stochastic-solutions-for-simultaneous-seismic","title":"Stochastic Solutions for Simultaneous Seismic Data Denoising and Reconstruction via Score-based Generative Models","date":"2024-07-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/efficient-personalized-text-to-image","slug":"efficient-personalized-text-to-image","title":"Efficient Personalized Text-to-image Generation by Leveraging Textual Subspace","date":"2024-06-30","arxiv_id":"2407.00608","repositories_listed":1,"syntology":null},{"url":"/paper/instantstyle-plus-style-transfer-with-content","slug":"instantstyle-plus-style-transfer-with-content","title":"InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation","date":"2024-06-30","arxiv_id":"2407.00788","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":12,"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) · 4 unverified","sample_list":"/paper/instantstyle-plus-style-transfer-with-content#ran","syntology_url":"https://syntology.ai/paper/2407.00788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.00788"}},"official":{"repos":["instantx-research/instantstyle-plus"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llm4gen-leveraging-semantic-representation-of","slug":"llm4gen-leveraging-semantic-representation-of","title":"LLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation","date":"2024-06-30","arxiv_id":"2407.00737","repositories_listed":1,"syntology":null},{"url":"/paper/the-factuality-tax-of-diversity-intervened","slug":"the-factuality-tax-of-diversity-intervened","title":"The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention","date":"2024-06-29","arxiv_id":"2407.00377","repositories_listed":1,"syntology":null},{"url":"/paper/mimicmotion-high-quality-human-motion-video","slug":"mimicmotion-high-quality-human-motion-video","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","date":"2024-06-28","arxiv_id":"2406.19680","repositories_listed":1,"syntology":null},{"url":"/paper/network-bending-of-diffusion-models-for-audio","slug":"network-bending-of-diffusion-models-for-audio","title":"Network Bending of Diffusion Models for Audio-Visual Generation","date":"2024-06-28","arxiv_id":"2406.19589","repositories_listed":1,"syntology":null},{"url":"/paper/popalign-population-level-alignment-for-fair","slug":"popalign-population-level-alignment-for-fair","title":"PopAlign: Population-Level Alignment for Fair Text-to-Image Generation","date":"2024-06-28","arxiv_id":"2406.19668","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-refinement-with-image-pivot-for-text","slug":"prompt-refinement-with-image-pivot-for-text","title":"Prompt Refinement with Image Pivot for Text-to-Image Generation","date":"2024-06-28","arxiv_id":"2407.00247","repositories_listed":1,"syntology":null},{"url":"/paper/anycontrol-create-your-artwork-with-versatile","slug":"anycontrol-create-your-artwork-with-versatile","title":"AnyControl: Create Your Artwork with Versatile Control on Text-to-Image Generation","date":"2024-06-27","arxiv_id":"2406.18958","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/anycontrol-create-your-artwork-with-versatile#ran","syntology_url":"https://syntology.ai/paper/2406.18958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18958"}},"official":{"repos":["open-mmlab/anycontrol"],"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"]}}},{"url":"/paper/investigating-and-defending-shortcut-learning","slug":"investigating-and-defending-shortcut-learning","title":"Rethinking and Defending Protective Perturbation in Personalized Diffusion Models","date":"2024-06-27","arxiv_id":"2406.18944","repositories_listed":1,"syntology":null},{"url":"/paper/structural-attention-rethinking-transformer","slug":"structural-attention-rethinking-transformer","title":"Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis","date":"2024-06-27","arxiv_id":"2406.18967","repositories_listed":1,"syntology":null},{"url":"/paper/using-diffusion-model-as-constraint-empower","slug":"using-diffusion-model-as-constraint-empower","title":"DiffLoss: unleashing diffusion model as constraint for training image restoration network","date":"2024-06-27","arxiv_id":"2406.19030","repositories_listed":1,"syntology":null},{"url":"/paper/diffusehigh-training-free-progressive-high","slug":"diffusehigh-training-free-progressive-high","title":"DiffuseHigh: Training-free Progressive High-Resolution Image Synthesis through Structure Guidance","date":"2024-06-26","arxiv_id":"2406.18459","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/diffusehigh-training-free-progressive-high#ran","syntology_url":"https://syntology.ai/paper/2406.18459","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18459"}},"official":{"repos":["yhyun225/DiffuseHigh"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/q-dit-accurate-post-training-quantization-for","slug":"q-dit-accurate-post-training-quantization-for","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","date":"2024-06-25","arxiv_id":"2406.17343","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":7,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/q-dit-accurate-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17343"}},"official":{"repos":["juanerx/q-dit"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/character-adapter-prompt-guided-region","slug":"character-adapter-prompt-guided-region","title":"Character-Adapter: Prompt-Guided Region Control for High-Fidelity Character Customization","date":"2024-06-24","arxiv_id":"2406.16537","repositories_listed":1,"syntology":null},{"url":"/paper/dreambench-a-human-aligned-benchmark-for","slug":"dreambench-a-human-aligned-benchmark-for","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","date":"2024-06-24","arxiv_id":"2406.16855","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/dreambench-a-human-aligned-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2406.16855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16855"}},"official":{"repos":["yuangpeng/dreambench_plus"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evalalign-evaluating-text-to-image-models","slug":"evalalign-evaluating-text-to-image-models","title":"EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models","date":"2024-06-24","arxiv_id":"2406.16562","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/evalalign-evaluating-text-to-image-models#ran","syntology_url":"https://syntology.ai/paper/2406.16562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16562"}},"official":{"repos":["sais-fuxi/evalalign"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/fine-tuning-diffusion-models-for-enhancing","slug":"fine-tuning-diffusion-models-for-enhancing","title":"FaceScore: Benchmarking and Enhancing Face Quality in Human Generation","date":"2024-06-24","arxiv_id":"2406.17100","repositories_listed":1,"syntology":null},{"url":"/paper/repairing-catastrophic-neglect-in-text-to","slug":"repairing-catastrophic-neglect-in-text-to","title":"Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement","date":"2024-06-24","arxiv_id":"2406.16272","repositories_listed":1,"syntology":null},{"url":"/paper/repulsive-score-distillation-for-diverse","slug":"repulsive-score-distillation-for-diverse","title":"Repulsive Latent Score Distillation for Solving Inverse Problems","date":"2024-06-24","arxiv_id":"2406.16683","repositories_listed":1,"syntology":null},{"url":"/paper/soft-masked-mamba-diffusion-model-for-ct-to","slug":"soft-masked-mamba-diffusion-model-for-ct-to","title":"Soft Masked Mamba Diffusion Model for CT to MRI Conversion","date":"2024-06-22","arxiv_id":"2406.15910","repositories_listed":1,"syntology":null},{"url":"/paper/injecting-bias-in-text-to-image-models-via","slug":"injecting-bias-in-text-to-image-models-via","title":"Backdooring Bias into Text-to-Image Models","date":"2024-06-21","arxiv_id":"2406.15213","repositories_listed":1,"syntology":null},{"url":"/paper/collafuse-collaborative-diffusion-models","slug":"collafuse-collaborative-diffusion-models","title":"CollaFuse: Collaborative Diffusion Models","date":"2024-06-20","arxiv_id":"2406.14429","repositories_listed":1,"syntology":null},{"url":"/paper/consistency-models-made-easy","slug":"consistency-models-made-easy","title":"Consistency Models Made Easy","date":"2024-06-20","arxiv_id":"2406.14548","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/consistency-models-made-easy#ran","syntology_url":"https://syntology.ai/paper/2406.14548","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14548"}},"official":{"repos":["locuslab/ect"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/fantastic-copyrighted-beasts-and-how-not-to","slug":"fantastic-copyrighted-beasts-and-how-not-to","title":"Fantastic Copyrighted Beasts and How (Not) to Generate Them","date":"2024-06-20","arxiv_id":"2406.14526","repositories_listed":1,"syntology":null},{"url":"/paper/df40-toward-next-generation-deepfake","slug":"df40-toward-next-generation-deepfake","title":"DF40: Toward Next-Generation Deepfake Detection","date":"2024-06-19","arxiv_id":"2406.13495","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":1,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/df40-toward-next-generation-deepfake#ran","syntology_url":"https://syntology.ai/paper/2406.13495","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.13495"}},"official":{"repos":["YZY-stack/DF40"],"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/improving-visual-commonsense-in-language","slug":"improving-visual-commonsense-in-language","title":"Improving Visual Commonsense in Language Models via Multiple Image Generation","date":"2024-06-19","arxiv_id":"2406.13621","repositories_listed":1,"syntology":null},{"url":"/paper/aitti-learning-adaptive-inclusive-token-for","slug":"aitti-learning-adaptive-inclusive-token-for","title":"AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation","date":"2024-06-18","arxiv_id":"2406.12805","repositories_listed":1,"syntology":null},{"url":"/paper/cyclic-2-5d-perceptual-loss-for-cross-modal","slug":"cyclic-2-5d-perceptual-loss-for-cross-modal","title":"Cyclic 2.5D Perceptual Loss for Cross-Modal 3D Medical Image Synthesis: T1w MRI to Tau PET","date":"2024-06-18","arxiv_id":"2406.12632","repositories_listed":1,"syntology":null},{"url":"/paper/generative-visual-instruction-tuning","slug":"generative-visual-instruction-tuning","title":"Generative Visual Instruction Tuning","date":"2024-06-17","arxiv_id":"2406.11262","repositories_listed":1,"syntology":null},{"url":"/paper/geogpt4v-towards-geometric-multi-modal-large","slug":"geogpt4v-towards-geometric-multi-modal-large","title":"GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation","date":"2024-06-17","arxiv_id":"2406.11503","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/geogpt4v-towards-geometric-multi-modal-large#ran","syntology_url":"https://syntology.ai/paper/2406.11503","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11503"}},"official":{"repos":["lanyu0303/geogpt4v_project"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-denoising-diffusion-gan-faster","slug":"latent-denoising-diffusion-gan-faster","title":"Latent Denoising Diffusion GAN: Faster sampling, Higher image quality","date":"2024-06-17","arxiv_id":"2406.11713","repositories_listed":1,"syntology":null},{"url":"/paper/not-all-prompts-are-made-equal-prompt-based","slug":"not-all-prompts-are-made-equal-prompt-based","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","date":"2024-06-17","arxiv_id":"2406.12042","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/not-all-prompts-are-made-equal-prompt-based#ran","syntology_url":"https://syntology.ai/paper/2406.12042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12042"}},"official":{"repos":["rezashkv/diffusion_pruning"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-the-codebook-size-of-vqgan-to-100000","slug":"scaling-the-codebook-size-of-vqgan-to-100000","title":"Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%","date":"2024-06-17","arxiv_id":"2406.11837","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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","sample_list":"/paper/scaling-the-codebook-size-of-vqgan-to-100000#ran","syntology_url":"https://syntology.ai/paper/2406.11837","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11837"}},"official":{"repos":["zh460045050/vqgan-lc"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/mixture-of-subspaces-in-low-rank-adaptation","slug":"mixture-of-subspaces-in-low-rank-adaptation","title":"Mixture-of-Subspaces in Low-Rank Adaptation","date":"2024-06-16","arxiv_id":"2406.11909","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":6,"phrase":"4 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mixture-of-subspaces-in-low-rank-adaptation#ran","syntology_url":"https://syntology.ai/paper/2406.11909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11909"}},"official":{"repos":["wutaiqiang/moslora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/star-scale-wise-text-to-image-generation-via","slug":"star-scale-wise-text-to-image-generation-via","title":"STAR: Scale-wise Text-to-image generation via Auto-Regressive representations","date":"2024-06-16","arxiv_id":"2406.10797","repositories_listed":1,"syntology":null},{"url":"/paper/mint-a-multi-modal-image-and-narrative-text","slug":"mint-a-multi-modal-image-and-narrative-text","title":"MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation","date":"2024-06-15","arxiv_id":"2406.10591","repositories_listed":1,"syntology":null},{"url":"/paper/controlvar-exploring-controllable-visual","slug":"controlvar-exploring-controllable-visual","title":"ControlVAR: Exploring Controllable Visual Autoregressive Modeling","date":"2024-06-14","arxiv_id":"2406.09750","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":14,"phrase":"12 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; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/controlvar-exploring-controllable-visual#ran","syntology_url":"https://syntology.ai/paper/2406.09750","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09750"}},"official":{"repos":["lxa9867/ControlVAR"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/make-it-count-text-to-image-generation-with","slug":"make-it-count-text-to-image-generation-with","title":"Make It Count: Text-to-Image Generation with an Accurate Number of Objects","date":"2024-06-14","arxiv_id":"2406.10210","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/make-it-count-text-to-image-generation-with#ran","syntology_url":"https://syntology.ai/paper/2406.10210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10210"}},"official":null}},{"url":"/paper/alleviating-distortion-in-image-generation","slug":"alleviating-distortion-in-image-generation","title":"Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization","date":"2024-06-13","arxiv_id":"2406.09416","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":6,"phrase":"13 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/alleviating-distortion-in-image-generation#ran","syntology_url":"https://syntology.ai/paper/2406.09416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09416"}},"official":{"repos":["qihao067/DiMR"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/batch-instructed-gradient-for-prompt","slug":"batch-instructed-gradient-for-prompt","title":"Batch-Instructed Gradient for Prompt Evolution:Systematic Prompt Optimization for Enhanced Text-to-Image Synthesis","date":"2024-06-13","arxiv_id":"2406.08713","repositories_listed":1,"syntology":null},{"url":"/paper/emma-your-text-to-image-diffusion-model-can","slug":"emma-your-text-to-image-diffusion-model-can","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","date":"2024-06-13","arxiv_id":"2406.09162","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-hallucinations-in-diffusion","slug":"understanding-hallucinations-in-diffusion","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","date":"2024-06-13","arxiv_id":"2406.09358","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/understanding-hallucinations-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.09358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09358"}},"official":{"repos":["locuslab/diffusion-model-hallucination"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cfg-manifold-constrained-classifier-free","slug":"cfg-manifold-constrained-classifier-free","title":"CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08070","repositories_listed":1,"syntology":null},{"url":"/paper/tc-bench-benchmarking-temporal","slug":"tc-bench-benchmarking-temporal","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","date":"2024-06-12","arxiv_id":"2406.08656","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tc-bench-benchmarking-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.08656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08656"}},"official":{"repos":["weixi-feng/tc-bench"],"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"]}}},{"url":"/paper/understanding-and-mitigating-compositional","slug":"understanding-and-mitigating-compositional","title":"Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models","date":"2024-06-12","arxiv_id":"2406.07844","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":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","sample_list":"/paper/understanding-and-mitigating-compositional#ran","syntology_url":"https://syntology.ai/paper/2406.07844","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07844"}},"official":{"repos":["ArmanZarei/Mitigating-T2I-Comp-Issues"],"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"]}}},{"url":"/paper/visionllm-v2-an-end-to-end-generalist","slug":"visionllm-v2-an-end-to-end-generalist","title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","date":"2024-06-12","arxiv_id":"2406.08394","repositories_listed":1,"syntology":null},{"url":"/paper/image-textualization-an-automatic-framework","slug":"image-textualization-an-automatic-framework","title":"Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions","date":"2024-06-11","arxiv_id":"2406.07502","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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","sample_list":"/paper/image-textualization-an-automatic-framework#ran","syntology_url":"https://syntology.ai/paper/2406.07502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07502"}},"official":{"repos":["sterzhang/image-textualization"],"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"]}}},{"url":"/paper/is-one-gpu-enough-pushing-image-generation-at","slug":"is-one-gpu-enough-pushing-image-generation-at","title":"Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models","date":"2024-06-11","arxiv_id":"2406.07251","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/is-one-gpu-enough-pushing-image-generation-at#ran","syntology_url":"https://syntology.ai/paper/2406.07251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07251"}},"official":{"repos":["thanos-db/pixelsmith"],"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"]}}},{"url":"/paper/ms-diffusion-multi-subject-zero-shot-image","slug":"ms-diffusion-multi-subject-zero-shot-image","title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","date":"2024-06-11","arxiv_id":"2406.07209","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":3,"phrase":"7 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ms-diffusion-multi-subject-zero-shot-image#ran","syntology_url":"https://syntology.ai/paper/2406.07209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07209"}},"official":{"repos":["MS-Diffusion/MS-Diffusion"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spin-spacecraft-imagery-for-navigation","slug":"spin-spacecraft-imagery-for-navigation","title":"SPIN: Spacecraft Imagery for Navigation","date":"2024-06-11","arxiv_id":"2406.07500","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-visual-concepts-across-models","slug":"understanding-visual-concepts-across-models","title":"Understanding Visual Concepts Across Models","date":"2024-06-11","arxiv_id":"2406.07506","repositories_listed":1,"syntology":null},{"url":"/paper/processpainter-learn-painting-process-from","slug":"processpainter-learn-painting-process-from","title":"ProcessPainter: Learn Painting Process from Sequence Data","date":"2024-06-10","arxiv_id":"2406.06062","repositories_listed":1,"syntology":null},{"url":"/paper/mlcm-multistep-consistency-distillation-of","slug":"mlcm-multistep-consistency-distillation-of","title":"TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps","date":"2024-06-09","arxiv_id":"2406.05768","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/mlcm-multistep-consistency-distillation-of#ran","syntology_url":"https://syntology.ai/paper/2406.05768","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05768"}},"official":{"repos":["oppo-mente-lab/tlcm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/3d-mri-synthesis-with-slice-based-latent","slug":"3d-mri-synthesis-with-slice-based-latent","title":"3D MRI Synthesis with Slice-Based Latent Diffusion Models: Improving Tumor Segmentation Tasks in Data-Scarce Regimes","date":"2024-06-08","arxiv_id":"2406.05421","repositories_listed":1,"syntology":null},{"url":"/paper/medical-vision-generalist-unifying-medical","slug":"medical-vision-generalist-unifying-medical","title":"Medical Vision Generalist: Unifying Medical Imaging Tasks in Context","date":"2024-06-08","arxiv_id":"2406.05565","repositories_listed":1,"syntology":null},{"url":"/paper/regularized-training-with-generated-datasets","slug":"regularized-training-with-generated-datasets","title":"Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models","date":"2024-06-08","arxiv_id":"2406.05432","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-non-autoregressive-transformers","slug":"revisiting-non-autoregressive-transformers","title":"Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis","date":"2024-06-08","arxiv_id":"2406.05478","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":9,"phrase":"12 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/revisiting-non-autoregressive-transformers#ran","syntology_url":"https://syntology.ai/paper/2406.05478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05478"}},"official":{"repos":["leaplabthu/improvednat"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/clog-benchmarking-continual-learning-of-image","slug":"clog-benchmarking-continual-learning-of-image","title":"CLoG: Benchmarking Continual Learning of Image Generation Models","date":"2024-06-07","arxiv_id":"2406.04584","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clog-benchmarking-continual-learning-of-image#ran","syntology_url":"https://syntology.ai/paper/2406.04584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04584"}},"official":{"repos":["linhaowei1/clog"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ganetic-loss-for-generative-adversarial","slug":"ganetic-loss-for-generative-adversarial","title":"GANetic Loss for Generative Adversarial Networks with a Focus on Medical Applications","date":"2024-06-07","arxiv_id":"2406.05023","repositories_listed":1,"syntology":null},{"url":"/paper/optimal-eye-surgeon-finding-image-priors","slug":"optimal-eye-surgeon-finding-image-priors","title":"Optimal Eye Surgeon: Finding Image Priors through Sparse Generators at Initialization","date":"2024-06-07","arxiv_id":"2406.05288","repositories_listed":1,"syntology":null},{"url":"/paper/pqpp-a-joint-benchmark-for-text-to-image","slug":"pqpp-a-joint-benchmark-for-text-to-image","title":"PQPP: A Joint Benchmark for Text-to-Image Prompt and Query Performance Prediction","date":"2024-06-07","arxiv_id":"2406.04746","repositories_listed":1,"syntology":null},{"url":"/paper/tedi-policy-temporally-entangled-diffusion","slug":"tedi-policy-temporally-entangled-diffusion","title":"Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models","date":"2024-06-07","arxiv_id":"2406.04806","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"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) · 1 unverified","sample_list":"/paper/tedi-policy-temporally-entangled-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.04806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04806"}},"official":{"repos":["Streaming-Diffusion-Policy/streaming_diffusion_policy"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/bitsfusion-1-99-bits-weight-quantization-of","slug":"bitsfusion-1-99-bits-weight-quantization-of","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","date":"2024-06-06","arxiv_id":"2406.04333","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-based-image-inpainting-with","slug":"diffusion-based-image-inpainting-with","title":"Diffusion-based image inpainting with internal learning","date":"2024-06-06","arxiv_id":"2406.04206","repositories_listed":1,"syntology":null},{"url":"/paper/genai-arena-an-open-evaluation-platform-for","slug":"genai-arena-an-open-evaluation-platform-for","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","date":"2024-06-06","arxiv_id":"2406.04485","repositories_listed":1,"syntology":null},{"url":"/paper/quantum-implicit-neural-representations","slug":"quantum-implicit-neural-representations","title":"Quantum Implicit Neural Representations","date":"2024-06-06","arxiv_id":"2406.03873","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/quantum-implicit-neural-representations#ran","syntology_url":"https://syntology.ai/paper/2406.03873","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03873"}},"official":{"repos":["GGorMM1/QIREN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/step-aware-preference-optimization-aligning","slug":"step-aware-preference-optimization-aligning","title":"Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization","date":"2024-06-06","arxiv_id":"2406.04314","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/step-aware-preference-optimization-aligning#ran","syntology_url":"https://syntology.ai/paper/2406.04314","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04314"}},"official":{"repos":["rockeycoss/spo"],"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/zero-painter-training-free-layout-control-for","slug":"zero-painter-training-free-layout-control-for","title":"Zero-Painter: Training-Free Layout Control for Text-to-Image Synthesis","date":"2024-06-06","arxiv_id":"2406.04032","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/zero-painter-training-free-layout-control-for#ran","syntology_url":"https://syntology.ai/paper/2406.04032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04032"}},"official":{"repos":["picsart-ai-research/zero-painter"],"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/lumina-next-making-lumina-t2x-stronger-and","slug":"lumina-next-making-lumina-t2x-stronger-and","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","date":"2024-06-05","arxiv_id":"2406.18583","repositories_listed":1,"syntology":null},{"url":"/paper/ouroboros3d-image-to-3d-generation-via-3d","slug":"ouroboros3d-image-to-3d-generation-via-3d","title":"Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion","date":"2024-06-05","arxiv_id":"2406.03184","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ouroboros3d-image-to-3d-generation-via-3d#ran","syntology_url":"https://syntology.ai/paper/2406.03184","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03184"}},"official":{"repos":["Costwen/Ouroboros3D"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/tackling-genai-copyright-issues-originality","slug":"tackling-genai-copyright-issues-originality","title":"Tackling Copyright Issues in AI Image Generation Through Originality Estimation and Genericization","date":"2024-06-05","arxiv_id":"2406.03341","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-feature-extractor-networks-for","slug":"analyzing-the-feature-extractor-networks-for","title":"Analyzing the Feature Extractor Networks for Face Image Synthesis","date":"2024-06-04","arxiv_id":"2406.02153","repositories_listed":1,"syntology":null},{"url":"/paper/flash-diffusion-accelerating-any-conditional","slug":"flash-diffusion-accelerating-any-conditional","title":"Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation","date":"2024-06-04","arxiv_id":"2406.02347","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"6 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/flash-diffusion-accelerating-any-conditional#ran","syntology_url":"https://syntology.ai/paper/2406.02347","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02347"}},"official":{"repos":["gojasper/flash-diffusion"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stable-pose-leveraging-transformers-for-pose","slug":"stable-pose-leveraging-transformers-for-pose","title":"Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation","date":"2024-06-04","arxiv_id":"2406.02485","repositories_listed":1,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":4,"n_no_contract":6,"n_pointer_only":13,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 4 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stable-pose-leveraging-transformers-for-pose#ran","syntology_url":"https://syntology.ai/paper/2406.02485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02485"}},"official":{"repos":["ai-med/stablepose"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/autostudio-crafting-consistent-subjects-in","slug":"autostudio-crafting-consistent-subjects-in","title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","date":"2024-06-03","arxiv_id":"2406.01388","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/autostudio-crafting-consistent-subjects-in#ran","syntology_url":"https://syntology.ai/paper/2406.01388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01388"}},"official":{"repos":["donahowe/AutoStudio"],"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"]}}}],"record_sha256":"e97424d0eac9c0291cdf5d992393d9b6e0713cab61e2f0c1bbed3fe0d8b3ecfc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}