{"url":"/dataset/wise","name":"WISE","full_name":null,"description_markdown":"WISE, the first benchmark specifically designed for World Knowledge-Informed Semantic Evaluation. WISE moves beyond simple word-pixel mapping by challenging models with 1000 meticulously crafted prompts across 25 sub-domains in cultural common sense, spatio-temporal understanding, and natural science.","description_withheld":null,"homepage":"https://github.com/PKU-YuanGroup/WISE","introduced_date":"2025-03-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/wise-a-world-knowledge-informed-semantic","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","first_author":"Yuwei Niu","url":null},"license":{"name":"MIT","url":null},"modalities":[],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"task","url":null,"datasets_with_task":"/datasets/task/task"}],"languages":[],"variants":["WISE"],"data_loaders":[],"num_papers_in_archive":22,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-generation-on-wise","task":"Image Generation","dataset_variant":"WISE","rows":14,"metrics":["Overall","Cultural","Time","Space","Biology","Physics","Chemistry"],"first_row_in_archive_order":{"model":"MindOmni\n(w/ cot)","paper":"/paper/mindomni-unleashing-reasoning-generation-in","metrics":{"Biology":"0.76","Chemistry":"0.52","Cultural":"0.75","Overall":"0.71","Physics":"0.72","Space":"0.76","Time":"0.70"},"code_links":[{"title":"easonxiao-888/mindomni","url":"https://github.com/easonxiao-888/mindomni"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/on-wise","task":"","dataset_variant":"WISE","rows":11,"metrics":["Overall","Cultural","Time","Space","Biology","Physics","Chemistry"],"first_row_in_archive_order":{"model":"UniWorld-V1","paper":"/paper/uniworld-v1-high-resolution-semantic-encoders","metrics":{"Biology":"0.45","Chemistry":"0.41","Cultural":"0.53","Overall":"0.55","Physics":"0.59","Space":"0.73","Time":"0.55"},"code_links":[{"title":"PKU-YuanGroup/UniWorld-V1","url":"https://github.com/PKU-YuanGroup/UniWorld-V1"},{"title":"pku-yuangroup/imgedit","url":"https://github.com/pku-yuangroup/imgedit"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/uniworld-v1-high-resolution-semantic-encoders","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","date":"2025-06-03","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":9,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/mindomni-unleashing-reasoning-generation-in","title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","date":"2025-05-19","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/transfer-between-modalities-with-metaqueries","title":"Transfer between Modalities with MetaQueries","date":"2025-04-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/janus-pro-unified-multimodal-understanding","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","date":"2025-01-29","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/janus-decoupling-visual-encoding-for-unified","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","date":"2024-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/emu3-next-token-prediction-is-all-you-need","title":"Emu3: Next-Token Prediction is All You Need","date":"2024-09-27","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":3,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/show-o-one-single-transformer-to-unify","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","date":"2024-08-22","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/scaling-rectified-flow-transformers-for-high","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","date":"2024-03-05","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/playground-v2-5-three-insights-towards","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","date":"2024-02-27","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/pixart-a-fast-training-of-diffusion","title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","date":"2023-09-30","rows_on_this_dataset":2,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/sdxl-improving-latent-diffusion-models-for","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","date":"2023-07-04","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":27,"samples_ran":11,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":68,"samples_ran":35,"samples_unverified":33,"pointer_only_for_licence":13,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}