{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-generation/papers/8","list_of":"/task/image-generation","task":"Image Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":8,"pages_in_order":67,"rows_per_page":100,"rows":[701,800],"of":6689,"counts":{"archive_papers_tagged":6689,"with_a_code_link":3102,"where_syntology_ran_a_sample":1223,"not_listed_spam_title":0,"listed":6689,"listed_where_code_ran":1223,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1063,"every_run_a_failure_of_syntologys_instrument":160,"listed_with_a_run_with_no_instrument_failure":1063,"listed_every_run_a_failure_of_syntologys_instrument":160,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-generation","prev":"/task/image-generation/papers/7","next":"/task/image-generation/papers/9","papers":[{"url":"/paper/blip3-o-a-family-of-fully-open-unified","slug":"blip3-o-a-family-of-fully-open-unified","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","date":"2025-05-14","arxiv_id":"2505.09568","repositories_listed":1,"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":4,"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/blip3-o-a-family-of-fully-open-unified#ran","syntology_url":"https://syntology.ai/paper/2505.09568","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.09568"}},"official":{"repos":["jiuhaichen/blip3o"],"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/train-a-multi-task-diffusion-policy-on","slug":"train-a-multi-task-diffusion-policy-on","title":"Mini Diffuser: Fast Multi-task Diffusion Policy Training Using Two-level Mini-batches","date":"2025-05-14","arxiv_id":"2505.09430","repositories_listed":1,"syntology":null},{"url":"/paper/skeleton-guided-diffusion-model-for-accurate","slug":"skeleton-guided-diffusion-model-for-accurate","title":"Skeleton-Guided Diffusion Model for Accurate Foot X-ray Synthesis in Hallux Valgus Diagnosis","date":"2025-05-13","arxiv_id":"2505.08247","repositories_listed":1,"syntology":null},{"url":"/paper/metrics-that-matter-evaluating-image-quality","slug":"metrics-that-matter-evaluating-image-quality","title":"Metrics that matter: Evaluating image quality metrics for medical image generation","date":"2025-05-12","arxiv_id":"2505.07175","repositories_listed":1,"syntology":null},{"url":"/paper/towards-sfw-sampling-for-diffusion-models-via","slug":"towards-sfw-sampling-for-diffusion-models-via","title":"Towards SFW sampling for diffusion models via external conditioning","date":"2025-05-12","arxiv_id":"2505.08817","repositories_listed":1,"syntology":null},{"url":"/paper/unified-continuous-generative-models","slug":"unified-continuous-generative-models","title":"Unified Continuous Generative Models","date":"2025-05-12","arxiv_id":"2505.07447","repositories_listed":1,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":10,"n_instrument":9,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":6,"n_pointer_only":4,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 1 violated, 6 with no contract checked; 9 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unified-continuous-generative-models#ran","syntology_url":"https://syntology.ai/paper/2505.07447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07447"}},"official":{"repos":["LINs-Lab/UCGM"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/hcma-hierarchical-cross-model-alignment-for","slug":"hcma-hierarchical-cross-model-alignment-for","title":"HCMA: Hierarchical Cross-model Alignment for Grounded Text-to-Image Generation","date":"2025-05-10","arxiv_id":"2505.06512","repositories_listed":1,"syntology":null},{"url":"/paper/learning-graph-representation-of-agent","slug":"learning-graph-representation-of-agent","title":"Learning Graph Representation of Agent Diffusers","date":"2025-05-10","arxiv_id":"2505.06761","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-diffusion-transformer-via","slug":"accelerating-diffusion-transformer-via","title":"Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition","date":"2025-05-09","arxiv_id":"2505.05829","repositories_listed":1,"syntology":null},{"url":"/paper/noise-consistent-siamese-diffusion-for","slug":"noise-consistent-siamese-diffusion-for","title":"Noise-Consistent Siamese-Diffusion for Medical Image Synthesis and Segmentation","date":"2025-05-09","arxiv_id":"2505.06068","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"10 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/noise-consistent-siamese-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2505.06068","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.06068"}},"official":{"repos":["qiukunpeng/siamese-diffusion"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-preliminary-study-for-gpt-4o-on-image","slug":"a-preliminary-study-for-gpt-4o-on-image","title":"A Preliminary Study for GPT-4o on Image Restoration","date":"2025-05-08","arxiv_id":"2505.05621","repositories_listed":1,"syntology":null},{"url":"/paper/instancegen-image-generation-with-instance","slug":"instancegen-image-generation-with-instance","title":"InstanceGen: Image Generation with Instance-level Instructions","date":"2025-05-08","arxiv_id":"2505.05678","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/instancegen-image-generation-with-instance#ran","syntology_url":"https://syntology.ai/paper/2505.05678","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.05678"}},"official":{"repos":["tsunghan-wu/SLD"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/prompt-to-polyp-clinically-aware-medical","slug":"prompt-to-polyp-clinically-aware-medical","title":"Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models","date":"2025-05-08","arxiv_id":"2505.05573","repositories_listed":1,"syntology":null},{"url":"/paper/mamba-diffusion-model-with-learnable-wavelet","slug":"mamba-diffusion-model-with-learnable-wavelet","title":"Mamba-Diffusion Model with Learnable Wavelet for Controllable Symbolic Music Generation","date":"2025-05-06","arxiv_id":"2505.03314","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-benchmarking-and-recommendation-of","slug":"multimodal-benchmarking-and-recommendation-of","title":"Multimodal Benchmarking and Recommendation of Text-to-Image Generation Models","date":"2025-05-06","arxiv_id":"2505.04650","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-person-image-synthesis-using-a-flow","slug":"real-time-person-image-synthesis-using-a-flow","title":"Real-Time Person Image Synthesis Using a Flow Matching Model","date":"2025-05-06","arxiv_id":"2505.03562","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-chain-of-thought-reward","slug":"unified-multimodal-chain-of-thought-reward","title":"Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning","date":"2025-05-06","arxiv_id":"2505.03318","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":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) · 1 unverified","sample_list":"/paper/unified-multimodal-chain-of-thought-reward#ran","syntology_url":"https://syntology.ai/paper/2505.03318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.03318"}},"official":null}},{"url":"/paper/ming-lite-uni-advancements-in-unified","slug":"ming-lite-uni-advancements-in-unified","title":"Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction","date":"2025-05-05","arxiv_id":"2505.02471","repositories_listed":1,"syntology":null},{"url":"/paper/no-other-representation-component-is-needed","slug":"no-other-representation-component-is-needed","title":"No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves","date":"2025-05-05","arxiv_id":"2505.02831","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"7 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; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/no-other-representation-component-is-needed#ran","syntology_url":"https://syntology.ai/paper/2505.02831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.02831"}},"official":{"repos":["vvvvvjdy/sra"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-dataset-copyright-evasion-attack","slug":"towards-dataset-copyright-evasion-attack","title":"Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models","date":"2025-05-05","arxiv_id":"2505.02824","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-understanding-and","slug":"unified-multimodal-understanding-and","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","date":"2025-05-05","arxiv_id":"2505.02567","repositories_listed":1,"syntology":null},{"url":"/paper/regression-is-all-you-need-for-medical-image","slug":"regression-is-all-you-need-for-medical-image","title":"Regression is all you need for medical image translation","date":"2025-05-04","arxiv_id":"2505.02048","repositories_listed":1,"syntology":null},{"url":"/paper/nexus-gen-a-unified-model-for-image","slug":"nexus-gen-a-unified-model-for-image","title":"Nexus-Gen: A Unified Model for Image Understanding, Generation, and Editing","date":"2025-04-30","arxiv_id":"2504.21356","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/nexus-gen-a-unified-model-for-image#ran","syntology_url":"https://syntology.ai/paper/2504.21356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21356"}},"official":{"repos":["modelscope/nexus-gen"],"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/pixelhacker-image-inpainting-with-structural-1","slug":"pixelhacker-image-inpainting-with-structural-1","title":"PixelHacker: Image Inpainting with Structural and Semantic Consistency","date":"2025-04-29","arxiv_id":"2504.20438","repositories_listed":1,"syntology":null},{"url":"/paper/generative-ai-for-character-animation-a","slug":"generative-ai-for-character-animation-a","title":"Generative AI for Character Animation: A Comprehensive Survey of Techniques, Applications, and Future Directions","date":"2025-04-27","arxiv_id":"2504.19056","repositories_listed":1,"syntology":null},{"url":"/paper/freegraftor-training-free-cross-image-feature","slug":"freegraftor-training-free-cross-image-feature","title":"FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation","date":"2025-04-22","arxiv_id":"2504.15958","repositories_listed":1,"syntology":null},{"url":"/paper/cross-attention-for-state-based-model-rwkv-7","slug":"cross-attention-for-state-based-model-rwkv-7","title":"Cross-attention for State-based model RWKV-7","date":"2025-04-19","arxiv_id":"2504.14260","repositories_listed":1,"syntology":null},{"url":"/paper/supresdiffgan-a-new-approach-for-the-super","slug":"supresdiffgan-a-new-approach-for-the-super","title":"SupResDiffGAN a new approach for the Super-Resolution task","date":"2025-04-18","arxiv_id":"2504.13622","repositories_listed":1,"syntology":null},{"url":"/paper/u-shape-mamba-state-space-model-for-faster","slug":"u-shape-mamba-state-space-model-for-faster","title":"U-Shape Mamba: State Space Model for faster diffusion","date":"2025-04-18","arxiv_id":"2504.13499","repositories_listed":1,"syntology":null},{"url":"/paper/artistauditor-auditing-artist-style-pirate-in","slug":"artistauditor-auditing-artist-style-pirate-in","title":"ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models","date":"2025-04-17","arxiv_id":"2504.13061","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-person-to-person-virtual-try-on","slug":"enhancing-person-to-person-virtual-try-on","title":"Enhancing Person-to-Person Virtual Try-On with Multi-Garment Virtual Try-Off","date":"2025-04-17","arxiv_id":"2504.13078","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-text-to-image-generation-with","slug":"personalized-text-to-image-generation-with","title":"Personalized Text-to-Image Generation with Auto-Regressive Models","date":"2025-04-17","arxiv_id":"2504.13162","repositories_listed":1,"syntology":null},{"url":"/paper/smartfreeedit-mask-free-spatial-aware-image","slug":"smartfreeedit-mask-free-spatial-aware-image","title":"SmartFreeEdit: Mask-Free Spatial-Aware Image Editing with Complex Instruction Understanding","date":"2025-04-17","arxiv_id":"2504.12704","repositories_listed":1,"syntology":null},{"url":"/paper/dmm-building-a-versatile-image-generation","slug":"dmm-building-a-versatile-image-generation","title":"DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging","date":"2025-04-16","arxiv_id":"2504.12364","repositories_listed":1,"syntology":null},{"url":"/paper/instantcharacter-personalize-any-characters","slug":"instantcharacter-personalize-any-characters","title":"InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework","date":"2025-04-16","arxiv_id":"2504.12395","repositories_listed":1,"syntology":null},{"url":"/paper/novel-view-x-ray-projection-synthesis-through","slug":"novel-view-x-ray-projection-synthesis-through","title":"Novel-view X-ray Projection Synthesis through Geometry-Integrated Deep Learning","date":"2025-04-16","arxiv_id":"2504.11953","repositories_listed":1,"syntology":null},{"url":"/paper/towards-safe-synthetic-image-generation-on","slug":"towards-safe-synthetic-image-generation-on","title":"Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset","date":"2025-04-16","arxiv_id":"2504.11707","repositories_listed":1,"syntology":null},{"url":"/paper/aligning-generative-denoising-with","slug":"aligning-generative-denoising-with","title":"Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception","date":"2025-04-15","arxiv_id":"2504.11457","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/aligning-generative-denoising-with#ran","syntology_url":"https://syntology.ai/paper/2504.11457","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11457"}},"official":{"repos":["ziqipang/addp"],"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/repa-e-unlocking-vae-for-end-to-end-tuning-of","slug":"repa-e-unlocking-vae-for-end-to-end-tuning-of","title":"REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers","date":"2025-04-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/anchor-token-matching-implicit-structure","slug":"anchor-token-matching-implicit-structure","title":"Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing","date":"2025-04-14","arxiv_id":"2504.10434","repositories_listed":1,"syntology":null},{"url":"/paper/geouni-a-unified-model-for-generating","slug":"geouni-a-unified-model-for-generating","title":"GeoUni: A Unified Model for Generating Geometry Diagrams, Problems and Problem Solutions","date":"2025-04-14","arxiv_id":"2504.10146","repositories_listed":1,"syntology":null},{"url":"/paper/flux-already-knows-activating-subject-driven","slug":"flux-already-knows-activating-subject-driven","title":"Flux Already Knows -- Activating Subject-Driven Image Generation without Training","date":"2025-04-12","arxiv_id":"2504.11478","repositories_listed":1,"syntology":null},{"url":"/paper/gigatok-scaling-visual-tokenizers-to-3","slug":"gigatok-scaling-visual-tokenizers-to-3","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","date":"2025-04-11","arxiv_id":"2504.08736","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":7,"n_ran_checked":7,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":15,"phrase":"10 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gigatok-scaling-visual-tokenizers-to-3#ran","syntology_url":"https://syntology.ai/paper/2504.08736","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08736"}},"official":{"repos":["SilentView/GigaTok"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/latent-diffusion-autoencoders-toward","slug":"latent-diffusion-autoencoders-toward","title":"Latent Diffusion Autoencoders: Toward Efficient and Meaningful Unsupervised Representation Learning in Medical Imaging","date":"2025-04-11","arxiv_id":"2504.08635","repositories_listed":1,"syntology":null},{"url":"/paper/id-booth-identity-consistent-face-generation","slug":"id-booth-identity-consistent-face-generation","title":"ID-Booth: Identity-consistent Face Generation with Diffusion Models","date":"2025-04-10","arxiv_id":"2504.07392","repositories_listed":1,"syntology":null},{"url":"/paper/pixelflow-pixel-space-generative-models-with","slug":"pixelflow-pixel-space-generative-models-with","title":"PixelFlow: Pixel-Space Generative Models with Flow","date":"2025-04-10","arxiv_id":"2504.07963","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":2,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/pixelflow-pixel-space-generative-models-with#ran","syntology_url":"https://syntology.ai/paper/2504.07963","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07963"}},"official":{"repos":["shoufachen/pixelflow"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/a-unified-agentic-framework-for-evaluating","slug":"a-unified-agentic-framework-for-evaluating","title":"A Unified Agentic Framework for Evaluating Conditional Image Generation","date":"2025-04-09","arxiv_id":"2504.07046","repositories_listed":1,"syntology":null},{"url":"/paper/dydit-dynamic-diffusion-transformers-for","slug":"dydit-dynamic-diffusion-transformers-for","title":"DyDiT++: Dynamic Diffusion Transformers for Efficient Visual Generation","date":"2025-04-09","arxiv_id":"2504.06803","repositories_listed":1,"syntology":null},{"url":"/paper/omnicaptioner-one-captioner-to-rule-them-all","slug":"omnicaptioner-one-captioner-to-rule-them-all","title":"OmniCaptioner: One Captioner to Rule Them All","date":"2025-04-09","arxiv_id":"2504.07089","repositories_listed":1,"syntology":null},{"url":"/paper/2504-06232","slug":"2504-06232","title":"HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance","date":"2025-04-08","arxiv_id":"2504.06232","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/2504-06232#ran","syntology_url":"https://syntology.ai/paper/2504.06232","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.06232"}},"official":null}},{"url":"/paper/an-empirical-study-of-gpt-4o-image-generation","slug":"an-empirical-study-of-gpt-4o-image-generation","title":"An Empirical Study of GPT-4o Image Generation Capabilities","date":"2025-04-08","arxiv_id":"2504.05979","repositories_listed":1,"syntology":null},{"url":"/paper/ddt-decoupled-diffusion-transformer-1","slug":"ddt-decoupled-diffusion-transformer-1","title":"DDT: Decoupled Diffusion Transformer","date":"2025-04-08","arxiv_id":"2504.05741","repositories_listed":1,"syntology":null},{"url":"/paper/mind-the-trojan-horse-image-prompt-adapter","slug":"mind-the-trojan-horse-image-prompt-adapter","title":"Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking","date":"2025-04-08","arxiv_id":"2504.05838","repositories_listed":1,"syntology":null},{"url":"/paper/gaussian-mixture-flow-matching-models","slug":"gaussian-mixture-flow-matching-models","title":"Gaussian Mixture Flow Matching Models","date":"2025-04-07","arxiv_id":"2504.05304","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 1 unverified","sample_list":"/paper/gaussian-mixture-flow-matching-models#ran","syntology_url":"https://syntology.ai/paper/2504.05304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05304"}},"official":{"repos":["lakonik/gmflow"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unitoken-harmonizing-multimodal-understanding","slug":"unitoken-harmonizing-multimodal-understanding","title":"UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding","date":"2025-04-06","arxiv_id":"2504.04423","repositories_listed":1,"syntology":null},{"url":"/paper/detection-limits-and-statistical-separability","slug":"detection-limits-and-statistical-separability","title":"Detection Limits and Statistical Separability of Tree Ring Watermarks in Rectified Flow-based Text-to-Image Generation Models","date":"2025-04-04","arxiv_id":"2504.03850","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-importance-in-diffusion-u-net-for","slug":"dynamic-importance-in-diffusion-u-net-for","title":"Dynamic Importance in Diffusion U-Net for Enhanced Image Synthesis","date":"2025-04-04","arxiv_id":"2504.03471","repositories_listed":1,"syntology":null},{"url":"/paper/gpt-imgeval-a-comprehensive-benchmark-for","slug":"gpt-imgeval-a-comprehensive-benchmark-for","title":"GPT-ImgEval: A Comprehensive Benchmark for Diagnosing GPT4o in Image Generation","date":"2025-04-03","arxiv_id":"2504.02782","repositories_listed":1,"syntology":null},{"url":"/paper/from-easy-to-hard-building-a-shortcut-for","slug":"from-easy-to-hard-building-a-shortcut-for","title":"From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis","date":"2025-04-02","arxiv_id":"2504.01395","repositories_listed":1,"syntology":null},{"url":"/paper/illume-illuminating-unified-mllm-with-dual","slug":"illume-illuminating-unified-mllm-with-dual","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","date":"2025-04-02","arxiv_id":"2504.01934","repositories_listed":1,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":18,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":17,"n_pointer_only":0,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 1 violated, 17 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/illume-illuminating-unified-mllm-with-dual#ran","syntology_url":"https://syntology.ai/paper/2504.01934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.01934"}},"official":null}},{"url":"/paper/less-to-more-generalization-unlocking-more","slug":"less-to-more-generalization-unlocking-more","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","date":"2025-04-02","arxiv_id":"2504.02160","repositories_listed":1,"syntology":{"n":43,"n_ran":13,"n_constructed":0,"n_ran_checked":6,"n_instrument":7,"n_unverified":30,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 30 unverified","sample_list":"/paper/less-to-more-generalization-unlocking-more#ran","syntology_url":"https://syntology.ai/paper/2504.02160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02160"}},"official":{"repos":["bytedance/uno"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":30,"ran_from_kinds":["official"]}}},{"url":"/paper/animegamer-infinite-anime-life-simulation","slug":"animegamer-infinite-anime-life-simulation","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction","date":"2025-04-01","arxiv_id":"2504.01014","repositories_listed":1,"syntology":null},{"url":"/paper/follow-the-flow-on-information-flow-across","slug":"follow-the-flow-on-information-flow-across","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","date":"2025-04-01","arxiv_id":"2504.01137","repositories_listed":1,"syntology":null},{"url":"/paper/mergevq-a-unified-framework-for-visual","slug":"mergevq-a-unified-framework-for-visual","title":"MergeVQ: A Unified Framework for Visual Generation and Representation with Disentangled Token Merging and Quantization","date":"2025-04-01","arxiv_id":"2504.00999","repositories_listed":1,"syntology":null},{"url":"/paper/ai2agent-an-end-to-end-framework-for","slug":"ai2agent-an-end-to-end-framework-for","title":"AI2Agent: An End-to-End Framework for Deploying AI Projects as Autonomous Agents","date":"2025-03-31","arxiv_id":"2503.23948","repositories_listed":1,"syntology":null},{"url":"/paper/textcrafter-accurately-rendering-multiple","slug":"textcrafter-accurately-rendering-multiple","title":"TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes","date":"2025-03-30","arxiv_id":"2503.23461","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-validating-synthetic-1","slug":"an-empirical-study-of-validating-synthetic-1","title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","date":"2025-03-28","arxiv_id":"2503.22171","repositories_listed":1,"syntology":null},{"url":"/paper/multi-objective-quality-diversity-in","slug":"multi-objective-quality-diversity-in","title":"Multi-Objective Quality-Diversity in Unstructured and Unbounded Spaces","date":"2025-03-28","arxiv_id":"2504.03715","repositories_listed":1,"syntology":null},{"url":"/paper/harmonizing-visual-representations-for","slug":"harmonizing-visual-representations-for","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","date":"2025-03-27","arxiv_id":"2503.21979","repositories_listed":1,"syntology":null},{"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/optimal-stepsize-for-diffusion-sampling","slug":"optimal-stepsize-for-diffusion-sampling","title":"Optimal Stepsize for Diffusion Sampling","date":"2025-03-27","arxiv_id":"2503.21774","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-visual-concept-blending-without","slug":"zero-shot-visual-concept-blending-without","title":"Zero-Shot Visual Concept Blending Without Text Guidance","date":"2025-03-27","arxiv_id":"2503.21277","repositories_listed":1,"syntology":null},{"url":"/paper/dissecting-and-mitigating-diffusion-bias-via","slug":"dissecting-and-mitigating-diffusion-bias-via","title":"Dissecting and Mitigating Diffusion Bias via Mechanistic Interpretability","date":"2025-03-26","arxiv_id":"2503.20483","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/dissecting-and-mitigating-diffusion-bias-via#ran","syntology_url":"https://syntology.ai/paper/2503.20483","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20483"}},"official":null}},{"url":"/paper/rectable-fast-modeling-tabular-data-with","slug":"rectable-fast-modeling-tabular-data-with","title":"RecTable: Fast Modeling Tabular Data with Rectified Flow","date":"2025-03-26","arxiv_id":"2503.20731","repositories_listed":1,"syntology":null},{"url":"/paper/unified-multimodal-discrete-diffusion","slug":"unified-multimodal-discrete-diffusion","title":"Unified Multimodal Discrete Diffusion","date":"2025-03-26","arxiv_id":"2503.20853","repositories_listed":1,"syntology":null},{"url":"/paper/learning-hazing-to-dehazing-towards-realistic-1","slug":"learning-hazing-to-dehazing-towards-realistic-1","title":"Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing","date":"2025-03-25","arxiv_id":"2503.19262","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/learning-hazing-to-dehazing-towards-realistic-1#ran","syntology_url":"https://syntology.ai/paper/2503.19262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19262"}},"official":{"repos":["ruiyi-w/learning-hazing-to-dehazing"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scaling-down-text-encoders-of-text-to-image","slug":"scaling-down-text-encoders-of-text-to-image","title":"Scaling Down Text Encoders of Text-to-Image Diffusion Models","date":"2025-03-25","arxiv_id":"2503.19897","repositories_listed":1,"syntology":null},{"url":"/paper/sita-structurally-imperceptible-and","slug":"sita-structurally-imperceptible-and","title":"SITA: Structurally Imperceptible and Transferable Adversarial Attacks for Stylized Image Generation","date":"2025-03-25","arxiv_id":"2503.19791","repositories_listed":1,"syntology":null},{"url":"/paper/diffusion-4k-ultra-high-resolution-image","slug":"diffusion-4k-ultra-high-resolution-image","title":"Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models","date":"2025-03-24","arxiv_id":"2503.18352","repositories_listed":1,"syntology":null},{"url":"/paper/equivariant-image-modeling","slug":"equivariant-image-modeling","title":"Equivariant Image Modeling","date":"2025-03-24","arxiv_id":"2503.18948","repositories_listed":1,"syntology":null},{"url":"/paper/latent-space-super-resolution-for-higher","slug":"latent-space-super-resolution-for-higher","title":"Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models","date":"2025-03-24","arxiv_id":"2503.18446","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":5,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"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) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result","sample_list":"/paper/latent-space-super-resolution-for-higher#ran","syntology_url":"https://syntology.ai/paper/2503.18446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18446"}},"official":{"repos":["3587jjh/lsrna"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/palate-peculiar-application-of-the-law-of","slug":"palate-peculiar-application-of-the-law-of","title":"PALATE: Peculiar Application of the Law of Total Expectation to Enhance the Evaluation of Deep Generative Models","date":"2025-03-24","arxiv_id":"2503.18462","repositories_listed":1,"syntology":null},{"url":"/paper/u-repa-aligning-diffusion-u-nets-to-vits","slug":"u-repa-aligning-diffusion-u-nets-to-vits","title":"U-REPA: Aligning Diffusion U-Nets to ViTs","date":"2025-03-24","arxiv_id":"2503.18414","repositories_listed":1,"syntology":null},{"url":"/paper/decoupling-angles-and-strength-in-low-rank","slug":"decoupling-angles-and-strength-in-low-rank","title":"DeLoRA: Decoupling Angles and Strength in Low-rank Adaptation","date":"2025-03-23","arxiv_id":"2503.18225","repositories_listed":1,"syntology":null},{"url":"/paper/unseen-from-seen-rewriting-observation","slug":"unseen-from-seen-rewriting-observation","title":"Unseen from Seen: Rewriting Observation-Instruction Using Foundation Models for Augmenting Vision-Language Navigation","date":"2025-03-23","arxiv_id":"2503.18065","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-sketch-guided-path-planning","slug":"end-to-end-sketch-guided-path-planning","title":"End-to-end Sketch-Guided Path Planning through Imitation Learning for Autonomous Mobile Robots","date":"2025-03-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/infiniteyou-flexible-photo-recrafting-while","slug":"infiniteyou-flexible-photo-recrafting-while","title":"InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity","date":"2025-03-20","arxiv_id":"2503.16418","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/infiniteyou-flexible-photo-recrafting-while#ran","syntology_url":"https://syntology.ai/paper/2503.16418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16418"}},"official":{"repos":["bytedance/infiniteyou"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/single-image-iterative-subject-driven","slug":"single-image-iterative-subject-driven","title":"Single Image Iterative Subject-driven Generation and Editing","date":"2025-03-20","arxiv_id":"2503.16025","repositories_listed":1,"syntology":null},{"url":"/paper/tokenize-image-as-a-set","slug":"tokenize-image-as-a-set","title":"Tokenize Image as a Set","date":"2025-03-20","arxiv_id":"2503.16425","repositories_listed":1,"syntology":null},{"url":"/paper/ultra-resolution-adaptation-with-ease","slug":"ultra-resolution-adaptation-with-ease","title":"Ultra-Resolution Adaptation with Ease","date":"2025-03-20","arxiv_id":"2503.16322","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/ultra-resolution-adaptation-with-ease#ran","syntology_url":"https://syntology.ai/paper/2503.16322","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.16322"}},"official":{"repos":["huage001/urae"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/verbdiff-text-only-diffusion-models-with","slug":"verbdiff-text-only-diffusion-models-with","title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","date":"2025-03-20","arxiv_id":"2503.16406","repositories_listed":1,"syntology":null},{"url":"/paper/cam-seg-a-continuous-valued-embedding","slug":"cam-seg-a-continuous-valued-embedding","title":"CAM-Seg: A Continuous-valued Embedding Approach for Semantic Image Generation","date":"2025-03-19","arxiv_id":"2503.15617","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-personalization-of-quantized","slug":"efficient-personalization-of-quantized","title":"Efficient Personalization of Quantized Diffusion Model without Backpropagation","date":"2025-03-19","arxiv_id":"2503.14868","repositories_listed":1,"syntology":null},{"url":"/paper/fp4dit-towards-effective-floating-point","slug":"fp4dit-towards-effective-floating-point","title":"FP4DiT: Towards Effective Floating Point Quantization for Diffusion Transformers","date":"2025-03-19","arxiv_id":"2503.15465","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fp4dit-towards-effective-floating-point#ran","syntology_url":"https://syntology.ai/paper/2503.15465","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.15465"}},"official":{"repos":["cccrrrccc/fp4dit"],"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/multi-focal-conditioned-latent-diffusion-for","slug":"multi-focal-conditioned-latent-diffusion-for","title":"Multi-focal Conditioned Latent Diffusion for Person Image Synthesis","date":"2025-03-19","arxiv_id":"2503.15686","repositories_listed":1,"syntology":null},{"url":"/paper/dpimagebench-a-unified-benchmark-for","slug":"dpimagebench-a-unified-benchmark-for","title":"DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis","date":"2025-03-18","arxiv_id":"2503.14681","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/dpimagebench-a-unified-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2503.14681","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14681"}},"official":{"repos":["2019chengong/dpimagebench"],"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/simworld-a-unified-benchmark-for-simulator","slug":"simworld-a-unified-benchmark-for-simulator","title":"SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model","date":"2025-03-18","arxiv_id":"2503.13952","repositories_listed":1,"syntology":null},{"url":"/paper/genstereo-towards-open-world-generation-of","slug":"genstereo-towards-open-world-generation-of","title":"GenStereo: Towards Open-World Generation of Stereo Images and Unsupervised Matching","date":"2025-03-17","arxiv_id":"2503.12720","repositories_listed":1,"syntology":null},{"url":"/paper/localized-concept-erasure-for-text-to-image","slug":"localized-concept-erasure-for-text-to-image","title":"Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation","date":"2025-03-16","arxiv_id":"2503.12356","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":4,"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/localized-concept-erasure-for-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2503.12356","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.12356"}},"official":{"repos":["Hyun1A/GLoCE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/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}}],"record_sha256":"8a7d90fa1bad4274f5ab05d60d9443f430313d625e88de9febc060d89354c721","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}