{"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/7","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":7,"pages_in_order":67,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/image-generation/papers/8","papers":[{"url":"/paper/deligan-generative-adversarial-networks-for","slug":"deligan-generative-adversarial-networks-for","title":"DeLiGAN : Generative Adversarial Networks for Diverse and Limited Data","date":"2017-06-07","arxiv_id":"1706.02071","repositories_listed":2,"syntology":null},{"url":"/paper/pose-guided-person-image-generation","slug":"pose-guided-person-image-generation","title":"Pose Guided Person Image Generation","date":"2017-05-25","arxiv_id":"1705.09368","repositories_listed":2,"syntology":null},{"url":"/paper/genegan-learning-object-transfiguration-and","slug":"genegan-learning-object-transfiguration-and","title":"GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data","date":"2017-05-14","arxiv_id":"1705.04932","repositories_listed":2,"syntology":null},{"url":"/paper/gp-gan-towards-realistic-high-resolution","slug":"gp-gan-towards-realistic-high-resolution","title":"GP-GAN: Towards Realistic High-Resolution Image Blending","date":"2017-03-21","arxiv_id":"1703.07195","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/gp-gan-towards-realistic-high-resolution#ran","syntology_url":"https://syntology.ai/paper/1703.07195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.07195"}},"official":{"repos":["wuhuikai/GP-GAN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/transformation-grounded-image-generation","slug":"transformation-grounded-image-generation","title":"Transformation-Grounded Image Generation Network for Novel 3D View Synthesis","date":"2017-03-08","arxiv_id":"1703.02921","repositories_listed":2,"syntology":null},{"url":"/paper/improved-variational-inference-with-inverse","slug":"improved-variational-inference-with-inverse","title":"Improved Variational Inference with Inverse Autoregressive Flow","date":"2016-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/neural-photo-editing-with-introspective","slug":"neural-photo-editing-with-introspective","title":"Neural Photo Editing with Introspective Adversarial Networks","date":"2016-09-22","arxiv_id":"1609.07093","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"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; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/neural-photo-editing-with-introspective#ran","syntology_url":"https://syntology.ai/paper/1609.07093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07093"}},"official":{"repos":["ajbrock/Neural-Photo-Editor"],"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/image-style-transfer-using-convolutional","slug":"image-style-transfer-using-convolutional","title":"Image Style Transfer Using Convolutional Neural Networks","date":"2016-06-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/generating-images-from-captions-with","slug":"generating-images-from-captions-with","title":"Generating Images from Captions with Attention","date":"2015-11-09","arxiv_id":"1511.02793","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generating-images-from-captions-with#ran","syntology_url":"https://syntology.ai/paper/1511.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.02793"}},"official":{"repos":["emansim/text2image"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multiscale-structural-similarity-for-image","slug":"multiscale-structural-similarity-for-image","title":"Multiscale structural similarity for image quality assessment","date":"2004-05-04","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/characonsist-fine-grained-consistent","slug":"characonsist-fine-grained-consistent","title":"CharaConsist: Fine-Grained Consistent Character Generation","date":"2025-07-15","arxiv_id":"2507.11533","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/characonsist-fine-grained-consistent#ran","syntology_url":"https://syntology.ai/paper/2507.11533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11533"}},"official":{"repos":["murray-wang/characonsist"],"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/implementing-adaptations-for-vision","slug":"implementing-adaptations-for-vision","title":"Implementing Adaptations for Vision AutoRegressive Model","date":"2025-07-15","arxiv_id":"2507.11441","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":8,"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/implementing-adaptations-for-vision#ran","syntology_url":"https://syntology.ai/paper/2507.11441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.11441"}},"official":{"repos":["sprintml/finetuning_var_dp"],"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/mfgdiffusion-mask-guided-smoke-synthesis-for","slug":"mfgdiffusion-mask-guided-smoke-synthesis-for","title":"MFGDiffusion: Mask-Guided Smoke Synthesis for Enhanced Forest Fire Detection","date":"2025-07-15","arxiv_id":"2507.11252","repositories_listed":1,"syntology":null},{"url":"/paper/mgvq-could-vq-vae-beat-vae-a-generalizable","slug":"mgvq-could-vq-vae-beat-vae-a-generalizable","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","date":"2025-07-14","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neobabel-a-multilingual-open-tower-for-visual","slug":"neobabel-a-multilingual-open-tower-for-visual","title":"NeoBabel: A Multilingual Open Tower for Visual Generation","date":"2025-07-08","arxiv_id":"2507.06137","repositories_listed":1,"syntology":null},{"url":"/paper/ai-driven-cytomorphology-image-synthesis-for","slug":"ai-driven-cytomorphology-image-synthesis-for","title":"AI-Driven Cytomorphology Image Synthesis for Medical Diagnostics","date":"2025-07-07","arxiv_id":"2507.05063","repositories_listed":1,"syntology":null},{"url":"/paper/sv-drr-high-fidelity-novel-view-x-ray","slug":"sv-drr-high-fidelity-novel-view-x-ray","title":"SV-DRR: High-Fidelity Novel View X-Ray Synthesis Using Diffusion Model","date":"2025-07-07","arxiv_id":"2507.05148","repositories_listed":1,"syntology":null},{"url":"/paper/dreamvla-a-vision-language-action-model-1","slug":"dreamvla-a-vision-language-action-model-1","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","date":"2025-07-06","arxiv_id":"2507.04447","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dreamvla-a-vision-language-action-model-1#ran","syntology_url":"https://syntology.ai/paper/2507.04447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.04447"}},"official":{"repos":["Zhangwenyao1/DreamVLA"],"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/flow-anchored-consistency-models","slug":"flow-anchored-consistency-models","title":"Flow-Anchored Consistency Models","date":"2025-07-04","arxiv_id":"2507.03738","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-anchored-consistency-models#ran","syntology_url":"https://syntology.ai/paper/2507.03738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.03738"}},"official":{"repos":["ali-vilab/FACM"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cyclevar-repurposing-autoregressive-model-for","slug":"cyclevar-repurposing-autoregressive-model-for","title":"CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation","date":"2025-06-29","arxiv_id":"2506.23347","repositories_listed":1,"syntology":null},{"url":"/paper/ovis-u1-technical-report","slug":"ovis-u1-technical-report","title":"Ovis-U1 Technical Report","date":"2025-06-29","arxiv_id":"2506.23044","repositories_listed":1,"syntology":null},{"url":"/paper/rethink-sparse-signals-for-pose-guided-text","slug":"rethink-sparse-signals-for-pose-guided-text","title":"Rethink Sparse Signals for Pose-guided Text-to-image Generation","date":"2025-06-26","arxiv_id":"2506.20983","repositories_listed":1,"syntology":null},{"url":"/paper/textrm-ode-t-left-textrm-ode-l-right","slug":"textrm-ode-t-left-textrm-ode-l-right","title":"$\\textrm{ODE}_t \\left(\\textrm{ODE}_l \\right)$: Shortcutting the Time and Length in Diffusion and Flow Models for Faster Sampling","date":"2025-06-26","arxiv_id":"2506.21714","repositories_listed":1,"syntology":null},{"url":"/paper/xverse-consistent-multi-subject-control-of","slug":"xverse-consistent-multi-subject-control-of","title":"XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation","date":"2025-06-26","arxiv_id":"2506.21416","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/xverse-consistent-multi-subject-control-of#ran","syntology_url":"https://syntology.ai/paper/2506.21416","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.21416"}},"official":{"repos":["bytedance/xverse"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/ear-erasing-concepts-from-unified","slug":"ear-erasing-concepts-from-unified","title":"EAR: Erasing Concepts from Unified Autoregressive Models","date":"2025-06-25","arxiv_id":"2506.20151","repositories_listed":1,"syntology":null},{"url":"/paper/angio-diff-learning-a-self-supervised","slug":"angio-diff-learning-a-self-supervised","title":"Angio-Diff: Learning a Self-Supervised Adversarial Diffusion Model for Angiographic Geometry Generation","date":"2025-06-24","arxiv_id":"2506.19455","repositories_listed":1,"syntology":null},{"url":"/paper/morse-dual-sampling-for-lossless-acceleration","slug":"morse-dual-sampling-for-lossless-acceleration","title":"Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models","date":"2025-06-23","arxiv_id":"2506.18251","repositories_listed":1,"syntology":null},{"url":"/paper/omnigen2-exploration-to-advanced-multimodal","slug":"omnigen2-exploration-to-advanced-multimodal","title":"OmniGen2: Exploration to Advanced Multimodal Generation","date":"2025-06-23","arxiv_id":"2506.18871","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":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/omnigen2-exploration-to-advanced-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.18871","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18871"}},"official":{"repos":["vectorspacelab/omnigen2"],"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/sharegpt-4o-image-aligning-multimodal-models","slug":"sharegpt-4o-image-aligning-multimodal-models","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","date":"2025-06-22","arxiv_id":"2506.18095","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/sharegpt-4o-image-aligning-multimodal-models#ran","syntology_url":"https://syntology.ai/paper/2506.18095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18095"}},"official":{"repos":["freedomintelligence/sharegpt-4o-image"],"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","unlocated"]}}},{"url":"/paper/machine-mental-imagery-empower-multimodal","slug":"machine-mental-imagery-empower-multimodal","title":"Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens","date":"2025-06-20","arxiv_id":"2506.17218","repositories_listed":1,"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":17,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/machine-mental-imagery-empower-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.17218","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.17218"}},"official":{"repos":["umass-embodied-agi/mirage"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/watermarking-autoregressive-image-generation","slug":"watermarking-autoregressive-image-generation","title":"Watermarking Autoregressive Image Generation","date":"2025-06-19","arxiv_id":"2506.16349","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":8,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/watermarking-autoregressive-image-generation#ran","syntology_url":"https://syntology.ai/paper/2506.16349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.16349"}},"official":{"repos":["facebookresearch/wmar"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}},{"url":"/paper/evolutionary-caching-to-accelerate-your-off","slug":"evolutionary-caching-to-accelerate-your-off","title":"Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model","date":"2025-06-18","arxiv_id":"2506.15682","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/evolutionary-caching-to-accelerate-your-off#ran","syntology_url":"https://syntology.ai/paper/2506.15682","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15682"}},"official":{"repos":["aniaggarwal/ecad"],"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/consistent-story-generation-with-asymmetry","slug":"consistent-story-generation-with-asymmetry","title":"Consistent Story Generation with Asymmetry Zigzag Sampling","date":"2025-06-11","arxiv_id":"2506.09612","repositories_listed":1,"syntology":null},{"url":"/paper/marrying-autoregressive-transformer-and","slug":"marrying-autoregressive-transformer-and","title":"Marrying Autoregressive Transformer and Diffusion with Multi-Reference Autoregression","date":"2025-06-11","arxiv_id":"2506.09482","repositories_listed":1,"syntology":null},{"url":"/paper/ming-omni-a-unified-multimodal-model-for","slug":"ming-omni-a-unified-multimodal-model-for","title":"Ming-Omni: A Unified Multimodal Model for Perception and Generation","date":"2025-06-11","arxiv_id":"2506.09344","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ming-omni-a-unified-multimodal-model-for#ran","syntology_url":"https://syntology.ai/paper/2506.09344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09344"}},"official":{"repos":["inclusionai/ming"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/noise-conditional-variational-score","slug":"noise-conditional-variational-score","title":"Noise Conditional Variational Score Distillation","date":"2025-06-11","arxiv_id":"2506.09416","repositories_listed":1,"syntology":null},{"url":"/paper/sage-exploring-the-boundaries-of-unsafe","slug":"sage-exploring-the-boundaries-of-unsafe","title":"SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing","date":"2025-06-11","arxiv_id":"2506.09363","repositories_listed":1,"syntology":null},{"url":"/paper/autoregressive-semantic-visual-reconstruction","slug":"autoregressive-semantic-visual-reconstruction","title":"Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better","date":"2025-06-10","arxiv_id":"2506.09040","repositories_listed":1,"syntology":null},{"url":"/paper/skipvar-accelerating-visual-autoregressive","slug":"skipvar-accelerating-visual-autoregressive","title":"SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping","date":"2025-06-10","arxiv_id":"2506.08908","repositories_listed":1,"syntology":null},{"url":"/paper/diffuse-everything-multimodal-diffusion","slug":"diffuse-everything-multimodal-diffusion","title":"Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces","date":"2025-06-09","arxiv_id":"2506.07903","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-counterfactual-generation-with","slug":"diffusion-counterfactual-generation-with","title":"Diffusion Counterfactual Generation with Semantic Abduction","date":"2025-06-09","arxiv_id":"2506.07883","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"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 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) · 1 unverified","sample_list":"/paper/diffusion-counterfactual-generation-with#ran","syntology_url":"https://syntology.ai/paper/2506.07883","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.07883"}},"official":{"repos":["rajatrasal/diffusion-counterfactuals"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/highly-compressed-tokenizer-can-generate","slug":"highly-compressed-tokenizer-can-generate","title":"Highly Compressed Tokenizer Can Generate Without Training","date":"2025-06-09","arxiv_id":"2506.08257","repositories_listed":1,"syntology":null},{"url":"/paper/oneig-bench-omni-dimensional-nuanced","slug":"oneig-bench-omni-dimensional-nuanced","title":"OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation","date":"2025-06-09","arxiv_id":"2506.07977","repositories_listed":1,"syntology":null},{"url":"/paper/ar-rag-autoregressive-retrieval-augmentation","slug":"ar-rag-autoregressive-retrieval-augmentation","title":"AR-RAG: Autoregressive Retrieval Augmentation for Image Generation","date":"2025-06-08","arxiv_id":"2506.06962","repositories_listed":1,"syntology":null},{"url":"/paper/peer-ranked-precision-creating-a-foundational","slug":"peer-ranked-precision-creating-a-foundational","title":"Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery","date":"2025-06-06","arxiv_id":"2506.05673","repositories_listed":1,"syntology":null},{"url":"/paper/alitok-towards-sequence-modeling-alignment-1","slug":"alitok-towards-sequence-modeling-alignment-1","title":"AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","date":"2025-06-05","arxiv_id":"2506.05289","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"4 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/alitok-towards-sequence-modeling-alignment-1#ran","syntology_url":"https://syntology.ai/paper/2506.05289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.05289"}},"official":{"repos":["ali-vilab/alitok"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/invisible-backdoor-triggers-in-image-editing","slug":"invisible-backdoor-triggers-in-image-editing","title":"Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking","date":"2025-06-05","arxiv_id":"2506.04879","repositories_listed":1,"syntology":null},{"url":"/paper/controlthinker-unveiling-latent-semantics-for","slug":"controlthinker-unveiling-latent-semantics-for","title":"ControlThinker: Unveiling Latent Semantics for Controllable Image Generation through Visual Reasoning","date":"2025-06-04","arxiv_id":"2506.03596","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-machine-unlearning-in-image","slug":"rethinking-machine-unlearning-in-image","title":"Rethinking Machine Unlearning in Image Generation Models","date":"2025-06-03","arxiv_id":"2506.02761","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/rethinking-machine-unlearning-in-image#ran","syntology_url":"https://syntology.ai/paper/2506.02761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.02761"}},"official":{"repos":["ryliu68/igmu"],"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/taxadiffusion-progressively-trained-diffusion","slug":"taxadiffusion-progressively-trained-diffusion","title":"TaxaDiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation","date":"2025-06-02","arxiv_id":"2506.01923","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taxadiffusion-progressively-trained-diffusion#ran","syntology_url":"https://syntology.ai/paper/2506.01923","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.01923"}},"official":{"repos":["aminK8/TaxaDiffusion"],"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/ultra-high-resolution-image-synthesis-data","slug":"ultra-high-resolution-image-synthesis-data","title":"Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation","date":"2025-06-02","arxiv_id":"2506.01331","repositories_listed":1,"syntology":null},{"url":"/paper/category-aware-eeg-image-generation-based-on","slug":"category-aware-eeg-image-generation-based-on","title":"Category-aware EEG image generation based on wavelet transform and contrast semantic loss","date":"2025-05-30","arxiv_id":"2505.24301","repositories_listed":1,"syntology":null},{"url":"/paper/draw-all-your-imagine-a-holistic-benchmark","slug":"draw-all-your-imagine-a-holistic-benchmark","title":"Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation","date":"2025-05-30","arxiv_id":"2505.24787","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/draw-all-your-imagine-a-holistic-benchmark#ran","syntology_url":"https://syntology.ai/paper/2505.24787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24787"}},"official":{"repos":["yczhou001/longbench-t2i"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/interpreting-large-text-to-image-diffusion","slug":"interpreting-large-text-to-image-diffusion","title":"Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning","date":"2025-05-30","arxiv_id":"2505.24360","repositories_listed":1,"syntology":null},{"url":"/paper/reasongen-r1-cot-for-autoregressive-image","slug":"reasongen-r1-cot-for-autoregressive-image","title":"ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL","date":"2025-05-30","arxiv_id":"2505.24875","repositories_listed":1,"syntology":{"n":13,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"7 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; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/reasongen-r1-cot-for-autoregressive-image#ran","syntology_url":"https://syntology.ai/paper/2505.24875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.24875"}},"official":null}},{"url":"/paper/unleashing-high-quality-image-generation-in","slug":"unleashing-high-quality-image-generation-in","title":"Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevin","date":"2025-05-30","arxiv_id":"2505.24222","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-sampling-path-tells-more-an","slug":"diffusion-sampling-path-tells-more-an","title":"Diffusion Sampling Path Tells More: An Efficient Plug-and-Play Strategy for Sample Filtering","date":"2025-05-29","arxiv_id":"2505.23343","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-inversion-turns-clip-into-a-decoder","slug":"implicit-inversion-turns-clip-into-a-decoder","title":"Implicit Inversion turns CLIP into a Decoder","date":"2025-05-29","arxiv_id":"2505.23161","repositories_listed":1,"syntology":null},{"url":"/paper/muddit-liberating-generation-beyond-text-to","slug":"muddit-liberating-generation-beyond-text-to","title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","date":"2025-05-29","arxiv_id":"2505.23606","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/muddit-liberating-generation-beyond-text-to#ran","syntology_url":"https://syntology.ai/paper/2505.23606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23606"}},"official":{"repos":["m-e-agi-lab/muddit"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/viton-drr-details-retention-virtual-try-on","slug":"viton-drr-details-retention-virtual-try-on","title":"VITON-DRR: Details Retention Virtual Try-on via Non-rigid Registration","date":"2025-05-29","arxiv_id":"2505.23439","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-rag-sub-dimensional-retrieval","slug":"cross-modal-rag-sub-dimensional-retrieval","title":"Cross-modal RAG: Sub-dimensional Retrieval-Augmented Text-to-Image Generation","date":"2025-05-28","arxiv_id":"2505.21956","repositories_listed":1,"syntology":null},{"url":"/paper/detailflow-1d-coarse-to-fine-autoregressive","slug":"detailflow-1d-coarse-to-fine-autoregressive","title":"DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction","date":"2025-05-27","arxiv_id":"2505.21473","repositories_listed":1,"syntology":null},{"url":"/paper/disa-diffusion-step-annealing-in","slug":"disa-diffusion-step-annealing-in","title":"DiSA: Diffusion Step Annealing in Autoregressive Image Generation","date":"2025-05-26","arxiv_id":"2505.20297","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-masked-autoregressive-models","slug":"hierarchical-masked-autoregressive-models","title":"Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots","date":"2025-05-26","arxiv_id":"2505.20288","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-llm-guided-semantic-correction-in","slug":"multimodal-llm-guided-semantic-correction-in","title":"Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion","date":"2025-05-26","arxiv_id":"2505.20053","repositories_listed":1,"syntology":null},{"url":"/paper/meditok-a-unified-tokenizer-for-medical-image","slug":"meditok-a-unified-tokenizer-for-medical-image","title":"MedITok: A Unified Tokenizer for Medical Image Synthesis and Interpretation","date":"2025-05-25","arxiv_id":"2505.19225","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meditok-a-unified-tokenizer-for-medical-image#ran","syntology_url":"https://syntology.ai/paper/2505.19225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19225"}},"official":{"repos":["masaaki-75/meditok"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/raise-realness-assessment-for-image-synthesis","slug":"raise-realness-assessment-for-image-synthesis","title":"RAISE: Realness Assessment for Image Synthesis and Evaluation","date":"2025-05-25","arxiv_id":"2505.19233","repositories_listed":1,"syntology":null},{"url":"/paper/strict-stress-test-of-rendering-images","slug":"strict-stress-test-of-rendering-images","title":"STRICT: Stress Test of Rendering Images Containing Text","date":"2025-05-25","arxiv_id":"2505.18985","repositories_listed":1,"syntology":null},{"url":"/paper/align-beyond-prompts-evaluating-world","slug":"align-beyond-prompts-evaluating-world","title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","date":"2025-05-24","arxiv_id":"2505.18730","repositories_listed":1,"syntology":null},{"url":"/paper/omnigenbench-a-benchmark-for-omnipotent","slug":"omnigenbench-a-benchmark-for-omnipotent","title":"OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks","date":"2025-05-24","arxiv_id":"2505.18775","repositories_listed":1,"syntology":null},{"url":"/paper/test-time-scaling-of-diffusion-models-via","slug":"test-time-scaling-of-diffusion-models-via","title":"Test-Time Scaling of Diffusion Models via Noise Trajectory Search","date":"2025-05-24","arxiv_id":"2506.03164","repositories_listed":1,"syntology":null},{"url":"/paper/co-reinforcement-learning-for-unified","slug":"co-reinforcement-learning-for-unified","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","date":"2025-05-23","arxiv_id":"2505.17534","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":1,"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/co-reinforcement-learning-for-unified#ran","syntology_url":"https://syntology.ai/paper/2505.17534","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17534"}},"official":{"repos":["mm-vl/ulm-r1"],"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","unlocated"]}}},{"url":"/paper/f-ancgan-an-attention-enhanced-cycle","slug":"f-ancgan-an-attention-enhanced-cycle","title":"F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles","date":"2025-05-23","arxiv_id":"2505.18106","repositories_listed":1,"syntology":null},{"url":"/paper/reprompt-reasoning-augmented-reprompting-for","slug":"reprompt-reasoning-augmented-reprompting-for","title":"RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning","date":"2025-05-23","arxiv_id":"2505.17540","repositories_listed":1,"syntology":null},{"url":"/paper/taming-diffusion-for-dataset-distillation","slug":"taming-diffusion-for-dataset-distillation","title":"Taming Diffusion for Dataset Distillation with High Representativeness","date":"2025-05-23","arxiv_id":"2505.18399","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/taming-diffusion-for-dataset-distillation#ran","syntology_url":"https://syntology.ai/paper/2505.18399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18399"}},"official":{"repos":["lin-zhao-resolve/d3hr"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/forward-only-diffusion-probabilistic-models","slug":"forward-only-diffusion-probabilistic-models","title":"Forward-only Diffusion Probabilistic Models","date":"2025-05-22","arxiv_id":"2505.16733","repositories_listed":1,"syntology":null},{"url":"/paper/fpqvar-floating-point-quantization-for-visual","slug":"fpqvar-floating-point-quantization-for-visual","title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","date":"2025-05-22","arxiv_id":"2505.16335","repositories_listed":1,"syntology":null},{"url":"/paper/got-r1-unleashing-reasoning-capability-of","slug":"got-r1-unleashing-reasoning-capability-of","title":"GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning","date":"2025-05-22","arxiv_id":"2505.17022","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":6,"n_ran_checked":7,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 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; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/got-r1-unleashing-reasoning-capability-of#ran","syntology_url":"https://syntology.ai/paper/2505.17022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17022"}},"official":{"repos":["gogoduan/got-r1"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":6,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/incorporating-visual-correspondence-into","slug":"incorporating-visual-correspondence-into","title":"Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On","date":"2025-05-22","arxiv_id":"2505.16977","repositories_listed":1,"syntology":null},{"url":"/paper/angle-domain-guidance-latent-diffusion","slug":"angle-domain-guidance-latent-diffusion","title":"Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation","date":"2025-05-21","arxiv_id":"2506.11039","repositories_listed":1,"syntology":null},{"url":"/paper/mmada-multimodal-large-diffusion-language","slug":"mmada-multimodal-large-diffusion-language","title":"MMaDA: Multimodal Large Diffusion Language Models","date":"2025-05-21","arxiv_id":"2505.15809","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"8 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mmada-multimodal-large-diffusion-language#ran","syntology_url":"https://syntology.ai/paper/2505.15809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15809"}},"official":{"repos":["gen-verse/mmada"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-diffusion-transformers-efficiently","slug":"scaling-diffusion-transformers-efficiently","title":"Scaling Diffusion Transformers Efficiently via $μ$P","date":"2025-05-21","arxiv_id":"2505.15270","repositories_listed":1,"syntology":null},{"url":"/paper/instructing-text-to-image-diffusion-models","slug":"instructing-text-to-image-diffusion-models","title":"Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization","date":"2025-05-20","arxiv_id":"2505.14254","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/instructing-text-to-image-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2505.14254","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14254"}},"official":{"repos":["chang-yuanyuan/caso"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-flow-transformer","slug":"latent-flow-transformer","title":"Latent Flow Transformer","date":"2025-05-20","arxiv_id":"2505.14513","repositories_listed":1,"syntology":null},{"url":"/paper/training-free-watermarking-for-autoregressive","slug":"training-free-watermarking-for-autoregressive","title":"Training-Free Watermarking for Autoregressive Image Generation","date":"2025-05-20","arxiv_id":"2505.14673","repositories_listed":1,"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":16,"n_instrument":0,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":14,"n_pointer_only":6,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/training-free-watermarking-for-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2505.14673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14673"}},"official":{"repos":["maifoundations/indexmark"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":16,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/visualquality-r1-reasoning-induced-image","slug":"visualquality-r1-reasoning-induced-image","title":"VisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank","date":"2025-05-20","arxiv_id":"2505.14460","repositories_listed":1,"syntology":{"n":14,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":3,"phrase":"9 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/visualquality-r1-reasoning-induced-image#ran","syntology_url":"https://syntology.ai/paper/2505.14460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.14460"}},"official":{"repos":["tianhewu/visualquality-r1"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerate-tarflow-sampling-with-gs-jacobi","slug":"accelerate-tarflow-sampling-with-gs-jacobi","title":"Accelerate TarFlow Sampling with GS-Jacobi Iteration","date":"2025-05-19","arxiv_id":"2505.12849","repositories_listed":1,"syntology":null},{"url":"/paper/higher-fidelity-perceptual-image-and-video","slug":"higher-fidelity-perceptual-image-and-video","title":"Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model","date":"2025-05-19","arxiv_id":"2505.13152","repositories_listed":1,"syntology":null},{"url":"/paper/improving-compositional-generation-with","slug":"improving-compositional-generation-with","title":"Improving Compositional Generation with Diffusion Models Using Lift Scores","date":"2025-05-19","arxiv_id":"2505.13740","repositories_listed":1,"syntology":null},{"url":"/paper/mindomni-unleashing-reasoning-generation-in","slug":"mindomni-unleashing-reasoning-generation-in","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","date":"2025-05-19","arxiv_id":"2505.13031","repositories_listed":1,"syntology":null},{"url":"/paper/vtbench-evaluating-visual-tokenizers-for","slug":"vtbench-evaluating-visual-tokenizers-for","title":"VTBench: Evaluating Visual Tokenizers for Autoregressive Image Generation","date":"2025-05-19","arxiv_id":"2505.13439","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-sparsity-for-parameter-efficient","slug":"exploring-sparsity-for-parameter-efficient","title":"Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets","date":"2025-05-18","arxiv_id":"2505.12532","repositories_listed":1,"syntology":null},{"url":"/paper/is-artificial-intelligence-generated-image","slug":"is-artificial-intelligence-generated-image","title":"Is Artificial Intelligence Generated Image Detection a Solved Problem?","date":"2025-05-18","arxiv_id":"2505.12335","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-artificial-intelligence-generated-image#ran","syntology_url":"https://syntology.ai/paper/2505.12335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12335"}},"official":{"repos":["horizontel/aigibench"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/fastcar-cache-attentive-replay-for-fast-auto","slug":"fastcar-cache-attentive-replay-for-fast-auto","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","date":"2025-05-17","arxiv_id":"2505.14709","repositories_listed":1,"syntology":null},{"url":"/paper/measurement-score-based-diffusion-model","slug":"measurement-score-based-diffusion-model","title":"Measurement Score-Based Diffusion Model","date":"2025-05-17","arxiv_id":"2505.11853","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11062","slug":"2505-11062","title":"HSRMamba: Efficient Wavelet Stripe State Space Model for Hyperspectral Image Super-Resolution","date":"2025-05-16","arxiv_id":"2505.11062","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11131","slug":"2505-11131","title":"One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework","date":"2025-05-16","arxiv_id":"2505.11131","repositories_listed":1,"syntology":null},{"url":"/paper/2505-11245","slug":"2505-11245","title":"Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models","date":"2025-05-16","arxiv_id":"2505.11245","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/2505-11245#ran","syntology_url":"https://syntology.ai/paper/2505.11245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.11245"}},"official":{"repos":["g-u-n/diffusion-npo"],"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/loft-lora-fused-training-dataset-generation","slug":"loft-lora-fused-training-dataset-generation","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","date":"2025-05-16","arxiv_id":"2505.11703","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-the-deep-fusion-of-large-language","slug":"exploring-the-deep-fusion-of-large-language","title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis","date":"2025-05-15","arxiv_id":"2505.10046","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/exploring-the-deep-fusion-of-large-language#ran","syntology_url":"https://syntology.ai/paper/2505.10046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.10046"}},"official":{"repos":["tang-bd/fuse-dit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}}],"record_sha256":"0bcc7e9b00740fe92b1ad6361cbbe4657af2fbefa420093947fbfff20eeea802","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}