{"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/text-to-image-generation-1/papers/ran/1","list_of":"/task/text-to-image-generation-1","task":"Text to 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":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":2,"rows_per_page":100,"rows":[1,100],"of":198,"counts":{"archive_papers_tagged":969,"with_a_code_link":461,"where_syntology_ran_a_sample":198,"not_listed_spam_title":0,"listed":969,"listed_where_code_ran":198,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":171,"every_run_a_failure_of_syntologys_instrument":27,"listed_with_a_run_with_no_instrument_failure":171,"listed_every_run_a_failure_of_syntologys_instrument":27,"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/text-to-image-generation-1/papers/ran/1","prev":null,"next":"/task/text-to-image-generation-1/papers/ran/2","papers":[{"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/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/hidream-i1-a-high-efficient-image-generative","slug":"hidream-i1-a-high-efficient-image-generative","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","date":"2025-05-28","arxiv_id":"2505.22705","repositories_listed":2,"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":0,"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/hidream-i1-a-high-efficient-image-generative#ran","syntology_url":"https://syntology.ai/paper/2505.22705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22705"}},"official":{"repos":["hidream-ai/hidream-e1","hidream-ai/hidream-i1"],"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/imgedit-a-unified-image-editing-dataset-and","slug":"imgedit-a-unified-image-editing-dataset-and","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","date":"2025-05-26","arxiv_id":"2505.20275","repositories_listed":2,"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/imgedit-a-unified-image-editing-dataset-and#ran","syntology_url":"https://syntology.ai/paper/2505.20275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20275"}},"official":{"repos":["pku-yuangroup/imgedit"],"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/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/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/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"]}}},{"url":"/paper/t2i-r1-reinforcing-image-generation-with","slug":"t2i-r1-reinforcing-image-generation-with","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","date":"2025-05-01","arxiv_id":"2505.00703","repositories_listed":2,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/t2i-r1-reinforcing-image-generation-with#ran","syntology_url":"https://syntology.ai/paper/2505.00703","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.00703"}},"official":{"repos":["caraj7/t2i-r1"],"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/lumina-image-2-0-a-unified-and-efficient","slug":"lumina-image-2-0-a-unified-and-efficient","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework","date":"2025-03-27","arxiv_id":"2503.21758","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lumina-image-2-0-a-unified-and-efficient#ran","syntology_url":"https://syntology.ai/paper/2503.21758","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21758"}},"official":{"repos":["alpha-vllm/lumina-image-2.0"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/halton-scheduler-for-masked-generative-image","slug":"halton-scheduler-for-masked-generative-image","title":"Halton Scheduler For Masked Generative Image Transformer","date":"2025-03-21","arxiv_id":"2503.17076","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/halton-scheduler-for-masked-generative-image#ran","syntology_url":"https://syntology.ai/paper/2503.17076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.17076"}},"official":{"repos":["valeoai/halton-maskgit"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/reflect-dit-inference-time-scaling-for-text-1","slug":"reflect-dit-inference-time-scaling-for-text-1","title":"Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection","date":"2025-03-15","arxiv_id":"2503.12271","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"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) · 2 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/reflect-dit-inference-time-scaling-for-text-1#ran","syntology_url":"https://syntology.ai/paper/2503.12271","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12271"}},"official":null}},{"url":"/paper/towards-better-alignment-training-diffusion","slug":"towards-better-alignment-training-diffusion","title":"Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards","date":"2025-03-14","arxiv_id":"2503.11240","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-better-alignment-training-diffusion#ran","syntology_url":"https://syntology.ai/paper/2503.11240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.11240"}},"official":{"repos":["hu-zijing/b2-diffurl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/got-unleashing-reasoning-capability-of","slug":"got-unleashing-reasoning-capability-of","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","date":"2025-03-13","arxiv_id":"2503.10639","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/got-unleashing-reasoning-capability-of#ran","syntology_url":"https://syntology.ai/paper/2503.10639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10639"}},"official":{"repos":["rongyaofang/got"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neighboring-autoregressive-modeling-for","slug":"neighboring-autoregressive-modeling-for","title":"Neighboring Autoregressive Modeling for Efficient Visual Generation","date":"2025-03-12","arxiv_id":"2503.10696","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 2 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) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/neighboring-autoregressive-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2503.10696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10696"}},"official":{"repos":["thisisbillhe/nar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/aligning-text-to-image-in-diffusion-models-is","slug":"aligning-text-to-image-in-diffusion-models-is","title":"Aligning Text to Image in Diffusion Models is Easier Than You Think","date":"2025-03-11","arxiv_id":"2503.08250","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aligning-text-to-image-in-diffusion-models-is#ran","syntology_url":"https://syntology.ai/paper/2503.08250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08250"}},"official":{"repos":["softrepa/SoftREPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lightgen-efficient-image-generation-through","slug":"lightgen-efficient-image-generation-through","title":"LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization","date":"2025-03-11","arxiv_id":"2503.08619","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lightgen-efficient-image-generation-through#ran","syntology_url":"https://syntology.ai/paper/2503.08619","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08619"}},"official":{"repos":["xianfengwu01/lightgen"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/wise-a-world-knowledge-informed-semantic","slug":"wise-a-world-knowledge-informed-semantic","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","date":"2025-03-10","arxiv_id":"2503.07265","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/wise-a-world-knowledge-informed-semantic#ran","syntology_url":"https://syntology.ai/paper/2503.07265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07265"}},"official":{"repos":["pku-yuangroup/wise"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-few-step-diffusion-models-by","slug":"learning-few-step-diffusion-models-by","title":"Learning Few-Step Diffusion Models by Trajectory Distribution Matching","date":"2025-03-09","arxiv_id":"2503.06674","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/learning-few-step-diffusion-models-by#ran","syntology_url":"https://syntology.ai/paper/2503.06674","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06674"}},"official":{"repos":["Luo-Yihong/TDM"],"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/x2i-seamless-integration-of-multimodal","slug":"x2i-seamless-integration-of-multimodal","title":"X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation","date":"2025-03-08","arxiv_id":"2503.06134","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/x2i-seamless-integration-of-multimodal#ran","syntology_url":"https://syntology.ai/paper/2503.06134","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06134"}},"official":{"repos":["oppo-mente-lab/x2i"],"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/chats-combining-human-aligned-optimization","slug":"chats-combining-human-aligned-optimization","title":"CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation","date":"2025-02-18","arxiv_id":"2502.12579","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":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) · 0 unverified","sample_list":"/paper/chats-combining-human-aligned-optimization#ran","syntology_url":"https://syntology.ai/paper/2502.12579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.12579"}},"official":{"repos":["AIDC-AI/CHATS"],"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/reg-rectified-gradient-guidance-for","slug":"reg-rectified-gradient-guidance-for","title":"REG: Rectified Gradient Guidance for Conditional Diffusion Models","date":"2025-01-31","arxiv_id":"2501.18865","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/reg-rectified-gradient-guidance-for#ran","syntology_url":"https://syntology.ai/paper/2501.18865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.18865"}},"official":null}},{"url":"/paper/dual-diffusion-for-unified-image-generation","slug":"dual-diffusion-for-unified-image-generation","title":"Dual Diffusion for Unified Image Generation and Understanding","date":"2024-12-31","arxiv_id":"2501.00289","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dual-diffusion-for-unified-image-generation#ran","syntology_url":"https://syntology.ai/paper/2501.00289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00289"}},"official":null}},{"url":"/paper/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","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/open-sora-democratizing-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2412.20404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20404"}},"official":{"repos":["hpcaitech/open-sora"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/autoregressive-video-generation-without","slug":"autoregressive-video-generation-without","title":"Autoregressive Video Generation without Vector Quantization","date":"2024-12-18","arxiv_id":"2412.14169","repositories_listed":1,"syntology":{"n":26,"n_ran":19,"n_constructed":18,"n_ran_checked":19,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 18 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/autoregressive-video-generation-without#ran","syntology_url":"https://syntology.ai/paper/2412.14169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14169"}},"official":{"repos":["baaivision/nova"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":18,"n_ran_no_instrument_failure":19,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/fast-prompt-alignment-for-text-to-image","slug":"fast-prompt-alignment-for-text-to-image","title":"Fast Prompt Alignment for Text-to-Image Generation","date":"2024-12-11","arxiv_id":"2412.08639","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/fast-prompt-alignment-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2412.08639","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08639"}},"official":{"repos":["tiktok/fast_prompt_alignment"],"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/flexdit-dynamic-token-density-control-for","slug":"flexdit-dynamic-token-density-control-for","title":"FlexDiT: Dynamic Token Density Control for Diffusion Transformer","date":"2024-12-08","arxiv_id":"2412.06028","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 4 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) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/flexdit-dynamic-token-density-control-for#ran","syntology_url":"https://syntology.ai/paper/2412.06028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06028"}},"official":{"repos":["changsn/FlexDiT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/playable-game-generation","slug":"playable-game-generation","title":"Playable Game Generation","date":"2024-12-01","arxiv_id":"2412.00887","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"8 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/playable-game-generation#ran","syntology_url":"https://syntology.ai/paper/2412.00887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00887"}},"official":{"repos":["greatx3/playable-game-generation"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/jetformer-an-autoregressive-generative-model","slug":"jetformer-an-autoregressive-generative-model","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","date":"2024-11-29","arxiv_id":"2411.19722","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/jetformer-an-autoregressive-generative-model#ran","syntology_url":"https://syntology.ai/paper/2411.19722","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19722"}},"official":{"repos":["google-research/big_vision"],"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/region-aware-text-to-image-generation-via","slug":"region-aware-text-to-image-generation-via","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","date":"2024-11-10","arxiv_id":"2411.06558","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":1,"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/region-aware-text-to-image-generation-via#ran","syntology_url":"https://syntology.ai/paper/2411.06558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06558"}},"official":{"repos":["nju-pcalab/rag-diffusion"],"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/training-free-regional-prompting-for","slug":"training-free-regional-prompting-for","title":"Training-free Regional Prompting for Diffusion Transformers","date":"2024-11-04","arxiv_id":"2411.02395","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/training-free-regional-prompting-for#ran","syntology_url":"https://syntology.ai/paper/2411.02395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02395"}},"official":{"repos":["instantX-research/Regional-Prompting-FLUX"],"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/mmm-rs-a-multi-modal-multi-gsd-multi-scene","slug":"mmm-rs-a-multi-modal-multi-gsd-multi-scene","title":"MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation","date":"2024-10-26","arxiv_id":"2410.22362","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":5,"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/mmm-rs-a-multi-modal-multi-gsd-multi-scene#ran","syntology_url":"https://syntology.ai/paper/2410.22362","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22362"}},"official":{"repos":["ljl5261/mmm-rs"],"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/bigr-harnessing-binary-latent-codes-for-image","slug":"bigr-harnessing-binary-latent-codes-for-image","title":"BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities","date":"2024-10-18","arxiv_id":"2410.14672","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":5,"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/bigr-harnessing-binary-latent-codes-for-image#ran","syntology_url":"https://syntology.ai/paper/2410.14672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14672"}},"official":{"repos":["haoosz/BiGR"],"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/puma-empowering-unified-mllm-with-multi","slug":"puma-empowering-unified-mllm-with-multi","title":"PUMA: Empowering Unified MLLM with Multi-granular Visual Generation","date":"2024-10-17","arxiv_id":"2410.13861","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/puma-empowering-unified-mllm-with-multi#ran","syntology_url":"https://syntology.ai/paper/2410.13861","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13861"}},"official":{"repos":["rongyaofang/puma"],"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/intermediate-representations-for-enhanced","slug":"intermediate-representations-for-enhanced","title":"Generating Intermediate Representations for Compositional Text-To-Image Generation","date":"2024-10-13","arxiv_id":"2410.09792","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/intermediate-representations-for-enhanced#ran","syntology_url":"https://syntology.ai/paper/2410.09792","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09792"}},"official":{"repos":["rang1991/public-intermediate-semantics-for-generation"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tulip-token-length-upgraded-clip","slug":"tulip-token-length-upgraded-clip","title":"TULIP: Token-length Upgraded CLIP","date":"2024-10-13","arxiv_id":"2410.10034","repositories_listed":1,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":7,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/tulip-token-length-upgraded-clip#ran","syntology_url":"https://syntology.ai/paper/2410.10034","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10034"}},"official":{"repos":["ivonajdenkoska/tulip"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/minorityprompt-text-to-minority-image","slug":"minorityprompt-text-to-minority-image","title":"Minority-Focused Text-to-Image Generation via Prompt Optimization","date":"2024-10-10","arxiv_id":"2410.07838","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/minorityprompt-text-to-minority-image#ran","syntology_url":"https://syntology.ai/paper/2410.07838","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07838"}},"official":{"repos":["anonymous5293/minorityprompt"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/itercomp-iterative-composition-aware-feedback","slug":"itercomp-iterative-composition-aware-feedback","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","date":"2024-10-09","arxiv_id":"2410.07171","repositories_listed":2,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/itercomp-iterative-composition-aware-feedback#ran","syntology_url":"https://syntology.ai/paper/2410.07171","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07171"}},"official":{"repos":["yangling0818/itercomp"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/training-free-diffusion-model-alignment-with","slug":"training-free-diffusion-model-alignment-with","title":"Training-free Diffusion Model Alignment with Sampling Demons","date":"2024-10-08","arxiv_id":"2410.05760","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/training-free-diffusion-model-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2410.05760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05760"}},"official":{"repos":["aiiu-lab/DemonSampling"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerating-auto-regressive-text-to-image","slug":"accelerating-auto-regressive-text-to-image","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","date":"2024-10-02","arxiv_id":"2410.01699","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_constructed":1,"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 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/accelerating-auto-regressive-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2410.01699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01699"}},"official":{"repos":["tyshiwo1/Accelerating-T2I-AR-with-SJD"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/resolving-multi-condition-confusion-for","slug":"resolving-multi-condition-confusion-for","title":"Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation","date":"2024-09-26","arxiv_id":"2409.17920","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/resolving-multi-condition-confusion-for#ran","syntology_url":"https://syntology.ai/paper/2409.17920","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17920"}},"official":{"repos":["hqhqaq/mip-adapter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/flowturbo-towards-real-time-flow-based-image","slug":"flowturbo-towards-real-time-flow-based-image","title":"FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner","date":"2024-09-26","arxiv_id":"2409.18128","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/flowturbo-towards-real-time-flow-based-image#ran","syntology_url":"https://syntology.ai/paper/2409.18128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18128"}},"official":{"repos":["shiml20/flowturbo"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/pixwizard-versatile-image-to-image-visual","slug":"pixwizard-versatile-image-to-image-visual","title":"PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions","date":"2024-09-23","arxiv_id":"2409.15278","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":9,"n_pointer_only":1,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 2 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pixwizard-versatile-image-to-image-visual#ran","syntology_url":"https://syntology.ai/paper/2409.15278","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.15278"}},"official":{"repos":["afeng-x/pixwizard"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/omnigen-unified-image-generation","slug":"omnigen-unified-image-generation","title":"OmniGen: Unified Image Generation","date":"2024-09-17","arxiv_id":"2409.11340","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omnigen-unified-image-generation#ran","syntology_url":"https://syntology.ai/paper/2409.11340","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11340"}},"official":{"repos":["vectorspacelab/omnigen"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/styletokenizer-defining-image-style-by-a","slug":"styletokenizer-defining-image-style-by-a","title":"StyleTokenizer: Defining Image Style by a Single Instance for Controlling Diffusion Models","date":"2024-09-04","arxiv_id":"2409.02543","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/styletokenizer-defining-image-style-by-a#ran","syntology_url":"https://syntology.ai/paper/2409.02543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02543"}},"official":{"repos":["alipay/style-tokenizer"],"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/prompt-agnostic-adversarial-perturbation-for","slug":"prompt-agnostic-adversarial-perturbation-for","title":"Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models","date":"2024-08-20","arxiv_id":"2408.10571","repositories_listed":2,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/prompt-agnostic-adversarial-perturbation-for#ran","syntology_url":"https://syntology.ai/paper/2408.10571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.10571"}},"official":{"repos":["vancyland/prompt-agnostic-adversarial-perturbation-for-customized-diffusion-models.github.io","vancyland/vancyland.github.io-project-PAP"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/megafusion-extend-diffusion-models-towards","slug":"megafusion-extend-diffusion-models-towards","title":"MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning","date":"2024-08-20","arxiv_id":"2408.11001","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"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) · 1 unverified","sample_list":"/paper/megafusion-extend-diffusion-models-towards#ran","syntology_url":"https://syntology.ai/paper/2408.11001","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.11001"}},"official":{"repos":["haoningwu3639/MegaFusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/2408-02657","slug":"2408-02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","date":"2024-08-05","arxiv_id":"2408.02657","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"7 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2408-02657#ran","syntology_url":"https://syntology.ai/paper/2408.02657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.02657"}},"official":{"repos":["alpha-vllm/lumina-mgpt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/subject-driven-text-to-image-generation-via-1","slug":"subject-driven-text-to-image-generation-via-1","title":"Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning","date":"2024-07-16","arxiv_id":"2407.12164","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/subject-driven-text-to-image-generation-via-1#ran","syntology_url":"https://syntology.ai/paper/2407.12164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12164"}},"official":{"repos":["andrew-miao/RPO"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"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/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/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/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/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/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/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/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/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/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/long-and-short-guidance-in-score-identity","slug":"long-and-short-guidance-in-score-identity","title":"Long and Short Guidance in Score identity Distillation for One-Step Text-to-Image Generation","date":"2024-06-03","arxiv_id":"2406.01561","repositories_listed":2,"syntology":{"n":24,"n_ran":19,"n_constructed":0,"n_ran_checked":13,"n_instrument":6,"n_unverified":5,"n_honours":3,"n_violates":0,"n_no_contract":10,"n_pointer_only":7,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/long-and-short-guidance-in-score-identity#ran","syntology_url":"https://syntology.ai/paper/2406.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.01561"}},"official":{"repos":["mingyuanzhou/sid-lsg"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":5,"ran_from_kinds":["community","official"]}}},{"url":"/paper/diffusion-features-to-bridge-domain-gap-for","slug":"diffusion-features-to-bridge-domain-gap-for","title":"Diffusion Features to Bridge Domain Gap for Semantic Segmentation","date":"2024-06-02","arxiv_id":"2406.00777","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/diffusion-features-to-bridge-domain-gap-for#ran","syntology_url":"https://syntology.ai/paper/2406.00777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.00777"}},"official":{"repos":["Yux1angJi/DIFF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/amortizing-intractable-inference-in-diffusion","slug":"amortizing-intractable-inference-in-diffusion","title":"Amortizing intractable inference in diffusion models for vision, language, and control","date":"2024-05-31","arxiv_id":"2405.20971","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/amortizing-intractable-inference-in-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.20971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20971"}},"official":{"repos":["gfnorg/diffusion-finetuning"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/defensive-unlearning-with-adversarial","slug":"defensive-unlearning-with-adversarial","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","date":"2024-05-24","arxiv_id":"2405.15234","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/defensive-unlearning-with-adversarial#ran","syntology_url":"https://syntology.ai/paper/2405.15234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15234"}},"official":{"repos":["optml-group/advunlearn"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/curriculum-direct-preference-optimization-for","slug":"curriculum-direct-preference-optimization-for","title":"Curriculum Direct Preference Optimization for Diffusion and Consistency Models","date":"2024-05-22","arxiv_id":"2405.13637","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":8,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/curriculum-direct-preference-optimization-for#ran","syntology_url":"https://syntology.ai/paper/2405.13637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13637"}},"official":{"repos":["croitorualin/curriculum-dpo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/imageinwords-unlocking-hyper-detailed-image","slug":"imageinwords-unlocking-hyper-detailed-image","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","date":"2024-05-05","arxiv_id":"2405.02793","repositories_listed":2,"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/imageinwords-unlocking-hyper-detailed-image#ran","syntology_url":"https://syntology.ai/paper/2405.02793","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.02793"}},"official":{"repos":["google/imageinwords"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/pulid-pure-and-lightning-id-customization-via","slug":"pulid-pure-and-lightning-id-customization-via","title":"PuLID: Pure and Lightning ID Customization via Contrastive Alignment","date":"2024-04-24","arxiv_id":"2404.16022","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":4,"n_pointer_only":4,"phrase":"12 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; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pulid-pure-and-lightning-id-customization-via#ran","syntology_url":"https://syntology.ai/paper/2404.16022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.16022"}},"official":{"repos":["tothebeginning/pulid"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["community","official"]}}},{"url":"/paper/latent-guard-a-safety-framework-for-text-to","slug":"latent-guard-a-safety-framework-for-text-to","title":"Latent Guard: a Safety Framework for Text-to-image Generation","date":"2024-04-11","arxiv_id":"2404.08031","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":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) · 0 unverified","sample_list":"/paper/latent-guard-a-safety-framework-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2404.08031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.08031"}},"official":{"repos":["rt219/latentguard"],"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/dynamic-prompt-optimizing-for-text-to-image","slug":"dynamic-prompt-optimizing-for-text-to-image","title":"Dynamic Prompt Optimizing for Text-to-Image Generation","date":"2024-04-05","arxiv_id":"2404.04095","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/dynamic-prompt-optimizing-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2404.04095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.04095"}},"official":{"repos":["mowenyii/pae"],"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/comat-aligning-text-to-image-diffusion-model","slug":"comat-aligning-text-to-image-diffusion-model","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","date":"2024-04-04","arxiv_id":"2404.03653","repositories_listed":2,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"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) · 4 unverified","sample_list":"/paper/comat-aligning-text-to-image-diffusion-model#ran","syntology_url":"https://syntology.ai/paper/2404.03653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03653"}},"official":{"repos":["caraj7/comat"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/instantstyle-free-lunch-towards-style","slug":"instantstyle-free-lunch-towards-style","title":"InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation","date":"2024-04-03","arxiv_id":"2404.02733","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":6,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/instantstyle-free-lunch-towards-style#ran","syntology_url":"https://syntology.ai/paper/2404.02733","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02733"}},"official":{"repos":["instantstyle/instantstyle"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/be-yourself-bounded-attention-for-multi","slug":"be-yourself-bounded-attention-for-multi","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","date":"2024-03-25","arxiv_id":"2403.16990","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/be-yourself-bounded-attention-for-multi#ran","syntology_url":"https://syntology.ai/paper/2403.16990","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.16990"}},"official":null}},{"url":"/paper/flashface-human-image-personalization-with","slug":"flashface-human-image-personalization-with","title":"FlashFace: Human Image Personalization with High-fidelity Identity Preservation","date":"2024-03-25","arxiv_id":"2403.17008","repositories_listed":1,"syntology":{"n":13,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 8 unverified","sample_list":"/paper/flashface-human-image-personalization-with#ran","syntology_url":"https://syntology.ai/paper/2403.17008","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17008"}},"official":null}},{"url":"/paper/long-clip-unlocking-the-long-text-capability","slug":"long-clip-unlocking-the-long-text-capability","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","date":"2024-03-22","arxiv_id":"2403.15378","repositories_listed":1,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/long-clip-unlocking-the-long-text-capability#ran","syntology_url":"https://syntology.ai/paper/2403.15378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.15378"}},"official":{"repos":["beichenzbc/long-clip"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/open-vocabulary-attention-maps-with-token","slug":"open-vocabulary-attention-maps-with-token","title":"Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models","date":"2024-03-21","arxiv_id":"2403.14291","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-vocabulary-attention-maps-with-token#ran","syntology_url":"https://syntology.ai/paper/2403.14291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14291"}},"official":{"repos":["vpulab/ovam"],"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/you-only-sample-once-taming-one-step-text-to","slug":"you-only-sample-once-taming-one-step-text-to","title":"You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs","date":"2024-03-19","arxiv_id":"2403.12931","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/you-only-sample-once-taming-one-step-text-to#ran","syntology_url":"https://syntology.ai/paper/2403.12931","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12931"}},"official":{"repos":["luo-yihong/yoso"],"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"]}}},{"url":"/paper/fouriscale-a-frequency-perspective-on","slug":"fouriscale-a-frequency-perspective-on","title":"FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis","date":"2024-03-19","arxiv_id":"2403.12963","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":0,"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/fouriscale-a-frequency-perspective-on#ran","syntology_url":"https://syntology.ai/paper/2403.12963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.12963"}},"official":{"repos":["leonhlj/fouriscale"],"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/omg-occlusion-friendly-personalized-multi","slug":"omg-occlusion-friendly-personalized-multi","title":"OMG: Occlusion-friendly Personalized Multi-concept Generation in Diffusion Models","date":"2024-03-16","arxiv_id":"2403.10983","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"6 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; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/omg-occlusion-friendly-personalized-multi#ran","syntology_url":"https://syntology.ai/paper/2403.10983","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10983"}},"official":{"repos":["kongzhecn/omg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/stable-makeup-when-real-world-makeup-transfer","slug":"stable-makeup-when-real-world-makeup-transfer","title":"Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model","date":"2024-03-12","arxiv_id":"2403.07764","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":1,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stable-makeup-when-real-world-makeup-transfer#ran","syntology_url":"https://syntology.ai/paper/2403.07764","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07764"}},"official":{"repos":["Xiaojiu-z/Stable-Makeup"],"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"]}}},{"url":"/paper/bridging-different-language-models-and","slug":"bridging-different-language-models-and","title":"Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation","date":"2024-03-12","arxiv_id":"2403.07860","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bridging-different-language-models-and#ran","syntology_url":"https://syntology.ai/paper/2403.07860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07860"}},"official":{"repos":["shihaozhaozsh/lavi-bridge"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cogview3-finer-and-faster-text-to-image","slug":"cogview3-finer-and-faster-text-to-image","title":"CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion","date":"2024-03-08","arxiv_id":"2403.05121","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/cogview3-finer-and-faster-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2403.05121","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05121"}},"official":null}},{"url":"/paper/ella-equip-diffusion-models-with-llm-for","slug":"ella-equip-diffusion-models-with-llm-for","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","date":"2024-03-08","arxiv_id":"2403.05135","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ella-equip-diffusion-models-with-llm-for#ran","syntology_url":"https://syntology.ai/paper/2403.05135","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05135"}},"official":null}},{"url":"/paper/pixart-s-weak-to-strong-training-of-diffusion","slug":"pixart-s-weak-to-strong-training-of-diffusion","title":"PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","date":"2024-03-07","arxiv_id":"2403.04692","repositories_listed":2,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":6,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/pixart-s-weak-to-strong-training-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2403.04692","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.04692"}},"official":{"repos":["PixArt-alpha/PixArt-sigma"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/noisecollage-a-layout-aware-text-to-image","slug":"noisecollage-a-layout-aware-text-to-image","title":"NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging","date":"2024-03-06","arxiv_id":"2403.03485","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":9,"phrase":"5 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/noisecollage-a-layout-aware-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2403.03485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03485"}},"official":{"repos":["univ-esuty/noisecollage"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-rectified-flow-transformers-for-high","slug":"scaling-rectified-flow-transformers-for-high","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","date":"2024-03-05","arxiv_id":"2403.03206","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scaling-rectified-flow-transformers-for-high#ran","syntology_url":"https://syntology.ai/paper/2403.03206","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03206"}},"official":null}},{"url":"/paper/cross-modal-contextualized-diffusion-models","slug":"cross-modal-contextualized-diffusion-models","title":"Contextualized Diffusion Models for Text-Guided Image and Video Generation","date":"2024-02-26","arxiv_id":"2402.16627","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/cross-modal-contextualized-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2402.16627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16627"}},"official":{"repos":["yangling0818/contextdiff"],"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/realcompo-dynamic-equilibrium-between-realism","slug":"realcompo-dynamic-equilibrium-between-realism","title":"RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models","date":"2024-02-20","arxiv_id":"2402.12908","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"8 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/realcompo-dynamic-equilibrium-between-realism#ran","syntology_url":"https://syntology.ai/paper/2402.12908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12908"}},"official":{"repos":["yangling0818/realcompo"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-style-prompting-with-swapping-self","slug":"visual-style-prompting-with-swapping-self","title":"Visual Style Prompting with Swapping Self-Attention","date":"2024-02-20","arxiv_id":"2402.12974","repositories_listed":1,"syntology":{"n":16,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-style-prompting-with-swapping-self#ran","syntology_url":"https://syntology.ai/paper/2402.12974","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.12974"}},"official":{"repos":["naver-ai/Visual-Style-Prompting"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/unlearncanvas-a-stylized-image-dataset-to","slug":"unlearncanvas-a-stylized-image-dataset-to","title":"UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models","date":"2024-02-19","arxiv_id":"2402.11846","repositories_listed":1,"syntology":{"n":74,"n_ran":55,"n_constructed":0,"n_ran_checked":43,"n_instrument":12,"n_unverified":19,"n_honours":2,"n_violates":1,"n_no_contract":40,"n_pointer_only":40,"phrase":"55 ran (of which 0 constructed an object rather than computing a result; 43 with no instrument failure: 2 honoured, 1 violated, 40 with no contract checked; 12 where Syntology's instrument failed) · 19 unverified","sample_list":"/paper/unlearncanvas-a-stylized-image-dataset-to#ran","syntology_url":"https://syntology.ai/paper/2402.11846","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.11846"}},"official":{"repos":["optml-group/unlearncanvas"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/magic-me-identity-specific-video-customized","slug":"magic-me-identity-specific-video-customized","title":"Magic-Me: Identity-Specific Video Customized Diffusion","date":"2024-02-14","arxiv_id":"2402.09368","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"phrase":"6 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/magic-me-identity-specific-video-customized#ran","syntology_url":"https://syntology.ai/paper/2402.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09368"}},"official":{"repos":["zhen-dong/magic-me"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-continuous-3d-words-for-text-to","slug":"learning-continuous-3d-words-for-text-to","title":"Learning Continuous 3D Words for Text-to-Image Generation","date":"2024-02-13","arxiv_id":"2402.08654","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/learning-continuous-3d-words-for-text-to#ran","syntology_url":"https://syntology.ai/paper/2402.08654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.08654"}},"official":{"repos":["ttchengab/continuous_3d_words_code"],"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/training-free-consistent-text-to-image","slug":"training-free-consistent-text-to-image","title":"Training-Free Consistent Text-to-Image Generation","date":"2024-02-05","arxiv_id":"2402.03286","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/training-free-consistent-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2402.03286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03286"}},"official":null}},{"url":"/paper/mastering-text-to-image-diffusion","slug":"mastering-text-to-image-diffusion","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","date":"2024-01-22","arxiv_id":"2401.11708","repositories_listed":1,"syntology":{"n":24,"n_ran":21,"n_constructed":0,"n_ran_checked":12,"n_instrument":9,"n_unverified":3,"n_honours":2,"n_violates":3,"n_no_contract":7,"n_pointer_only":16,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 3 violated, 7 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/mastering-text-to-image-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.11708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11708"}},"official":{"repos":["yangling0818/rpg-diffusionmaster"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/connect-collapse-corrupt-learning-cross-modal","slug":"connect-collapse-corrupt-learning-cross-modal","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","date":"2024-01-16","arxiv_id":"2401.08567","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"5 ran (of which 5 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; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/connect-collapse-corrupt-learning-cross-modal#ran","syntology_url":"https://syntology.ai/paper/2401.08567","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.08567"}},"official":{"repos":["yuhui-zh15/c3"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-initialization-for-personalized-text-to","slug":"cross-initialization-for-personalized-text-to","title":"Cross Initialization for Personalized Text-to-Image Generation","date":"2023-12-26","arxiv_id":"2312.15905","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/cross-initialization-for-personalized-text-to#ran","syntology_url":"https://syntology.ai/paper/2312.15905","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15905"}},"official":{"repos":["lyupang/crossinitialization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/brush-your-text-synthesize-any-scene-text-on","slug":"brush-your-text-synthesize-any-scene-text-on","title":"Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model","date":"2023-12-19","arxiv_id":"2312.12232","repositories_listed":1,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":14,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":19,"phrase":"15 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/brush-your-text-synthesize-any-scene-text-on#ran","syntology_url":"https://syntology.ai/paper/2312.12232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12232"}},"official":{"repos":["ecnuljzhang/brush-your-text"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/scedit-efficient-and-controllable-image","slug":"scedit-efficient-and-controllable-image","title":"SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing","date":"2023-12-18","arxiv_id":"2312.11392","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 1 unverified","sample_list":"/paper/scedit-efficient-and-controllable-image#ran","syntology_url":"https://syntology.ai/paper/2312.11392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.11392"}},"official":{"repos":["modelscope/scepter"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/rich-human-feedback-for-text-to-image","slug":"rich-human-feedback-for-text-to-image","title":"Rich Human Feedback for Text-to-Image Generation","date":"2023-12-15","arxiv_id":"2312.10240","repositories_listed":2,"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/rich-human-feedback-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2312.10240","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10240"}},"official":{"repos":["google-research/google-research"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/semantic-driven-initial-image-construction","slug":"semantic-driven-initial-image-construction","title":"The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization","date":"2023-12-13","arxiv_id":"2312.08872","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":3,"n_no_contract":2,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/semantic-driven-initial-image-construction#ran","syntology_url":"https://syntology.ai/paper/2312.08872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08872"}},"official":{"repos":["UT-Mao/Initial-Noise-Construction"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/correcting-diffusion-generation-through","slug":"correcting-diffusion-generation-through","title":"Correcting Diffusion Generation through Resampling","date":"2023-12-10","arxiv_id":"2312.06038","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/correcting-diffusion-generation-through#ran","syntology_url":"https://syntology.ai/paper/2312.06038","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.06038"}},"official":{"repos":["ucsb-nlp-chang/diffusion_resampling"],"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/photomaker-customizing-realistic-human-photos","slug":"photomaker-customizing-realistic-human-photos","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","date":"2023-12-07","arxiv_id":"2312.04461","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/photomaker-customizing-realistic-human-photos#ran","syntology_url":"https://syntology.ai/paper/2312.04461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04461"}},"official":{"repos":["TencentARC/PhotoMaker"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generating-illustrated-instructions","slug":"generating-illustrated-instructions","title":"Generating Illustrated Instructions","date":"2023-12-07","arxiv_id":"2312.04552","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generating-illustrated-instructions#ran","syntology_url":"https://syntology.ai/paper/2312.04552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04552"}},"official":{"repos":["sachit-menon/generating-illustrated-instructions-reproduction"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}],"record_sha256":"857be1600ee00cf9d51af43c80f886fd97e5d69368a1fe6c6d7221c26810bcef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}