{"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/11","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":11,"pages_in_order":67,"rows_per_page":100,"rows":[1001,1100],"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/10","next":"/task/image-generation/papers/12","papers":[{"url":"/paper/tinyfusion-diffusion-transformers-learned","slug":"tinyfusion-diffusion-transformers-learned","title":"TinyFusion: Diffusion Transformers Learned Shallow","date":"2024-12-02","arxiv_id":"2412.01199","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/tinyfusion-diffusion-transformers-learned#ran","syntology_url":"https://syntology.ai/paper/2412.01199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.01199"}},"official":{"repos":["vainf/tinyfusion"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/x-prompt-towards-universal-in-context-image","slug":"x-prompt-towards-universal-in-context-image","title":"X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models","date":"2024-12-02","arxiv_id":"2412.01824","repositories_listed":1,"syntology":null},{"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/energy-based-prior-latent-space-diffusion","slug":"energy-based-prior-latent-space-diffusion","title":"Energy-Based Prior Latent Space Diffusion model for Reconstruction of Lumbar Vertebrae from Thick Slice MRI","date":"2024-11-30","arxiv_id":"2412.00511","repositories_listed":1,"syntology":null},{"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/texgaussian-generating-high-quality-pbr","slug":"texgaussian-generating-high-quality-pbr","title":"TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting","date":"2024-11-29","arxiv_id":"2411.19654","repositories_listed":1,"syntology":null},{"url":"/paper/uniform-attention-maps-boosting-image","slug":"uniform-attention-maps-boosting-image","title":"Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing","date":"2024-11-29","arxiv_id":"2411.19652","repositories_listed":1,"syntology":null},{"url":"/paper/amo-sampler-enhancing-text-rendering-with","slug":"amo-sampler-enhancing-text-rendering-with","title":"AMO Sampler: Enhancing Text Rendering with Overshooting","date":"2024-11-28","arxiv_id":"2411.19415","repositories_listed":1,"syntology":null},{"url":"/paper/gate-opening-a-comprehensive-benchmark-for","slug":"gate-opening-a-comprehensive-benchmark-for","title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","date":"2024-11-27","arxiv_id":"2411.18499","repositories_listed":1,"syntology":null},{"url":"/paper/tryoffdiff-virtual-try-off-via-high-fidelity","slug":"tryoffdiff-virtual-try-off-via-high-fidelity","title":"TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models","date":"2024-11-27","arxiv_id":"2411.18350","repositories_listed":1,"syntology":null},{"url":"/paper/accelerating-vision-diffusion-transformers","slug":"accelerating-vision-diffusion-transformers","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","date":"2024-11-26","arxiv_id":"2411.17616","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/accelerating-vision-diffusion-transformers#ran","syntology_url":"https://syntology.ai/paper/2411.17616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17616"}},"official":{"repos":["opensparsellms/skip-dit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/collaborative-decoding-makes-visual-auto","slug":"collaborative-decoding-makes-visual-auto","title":"Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient","date":"2024-11-26","arxiv_id":"2411.17787","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/collaborative-decoding-makes-visual-auto#ran","syntology_url":"https://syntology.ai/paper/2411.17787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17787"}},"official":{"repos":["czg1225/code"],"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/cwdm-conditional-wavelet-diffusion-models-for","slug":"cwdm-conditional-wavelet-diffusion-models-for","title":"cWDM: Conditional Wavelet Diffusion Models for Cross-Modality 3D Medical Image Synthesis","date":"2024-11-26","arxiv_id":"2411.17203","repositories_listed":1,"syntology":null},{"url":"/paper/litevar-compressing-visual-autoregressive","slug":"litevar-compressing-visual-autoregressive","title":"LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization","date":"2024-11-26","arxiv_id":"2411.17178","repositories_listed":1,"syntology":null},{"url":"/paper/image-generation-diversity-issues-and-how-to","slug":"image-generation-diversity-issues-and-how-to","title":"Image Generation Diversity Issues and How to Tame Them","date":"2024-11-25","arxiv_id":"2411.16171","repositories_listed":1,"syntology":null},{"url":"/paper/one-diffusion-to-generate-them-all","slug":"one-diffusion-to-generate-them-all","title":"One Diffusion to Generate Them All","date":"2024-11-25","arxiv_id":"2411.16318","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 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; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/one-diffusion-to-generate-them-all#ran","syntology_url":"https://syntology.ai/paper/2411.16318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16318"}},"official":{"repos":["lehduong/onediffusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/semantic-image-synthesis-of-anime-characters","slug":"semantic-image-synthesis-of-anime-characters","title":"semantic image synthesis of anime characters based on conditional generative adversarial networks","date":"2024-11-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/zoomldm-latent-diffusion-model-for-multi","slug":"zoomldm-latent-diffusion-model-for-multi","title":"ZoomLDM: Latent Diffusion Model for multi-scale image generation","date":"2024-11-25","arxiv_id":"2411.16969","repositories_listed":1,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":13,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":11,"n_pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 2 violated, 11 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/zoomldm-latent-diffusion-model-for-multi#ran","syntology_url":"https://syntology.ai/paper/2411.16969","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16969"}},"official":{"repos":["cvlab-stonybrook/ZoomLDM"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/panollama-generating-endless-and-coherent","slug":"panollama-generating-endless-and-coherent","title":"PanoLlama: Generating Endless and Coherent Panoramas with Next-Token-Prediction LLMs","date":"2024-11-24","arxiv_id":"2411.15867","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/panollama-generating-endless-and-coherent#ran","syntology_url":"https://syntology.ai/paper/2411.15867","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15867"}},"official":{"repos":["0606zt/panollama"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/automatic-evaluation-for-text-to-image","slug":"automatic-evaluation-for-text-to-image","title":"Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark","date":"2024-11-23","arxiv_id":"2411.15488","repositories_listed":1,"syntology":null},{"url":"/paper/large-scale-text-to-image-model-with","slug":"large-scale-text-to-image-model-with","title":"Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator","date":"2024-11-23","arxiv_id":"2411.15466","repositories_listed":1,"syntology":null},{"url":"/paper/munba-machine-unlearning-via-nash-bargaining","slug":"munba-machine-unlearning-via-nash-bargaining","title":"MUNBa: Machine Unlearning via Nash Bargaining","date":"2024-11-23","arxiv_id":"2411.15537","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/munba-machine-unlearning-via-nash-bargaining#ran","syntology_url":"https://syntology.ai/paper/2411.15537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15537"}},"official":{"repos":["JingWu321/MUNBa"],"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","unlocated"]}}},{"url":"/paper/what-makes-a-scene-scene-graph-based","slug":"what-makes-a-scene-scene-graph-based","title":"What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation","date":"2024-11-23","arxiv_id":"2411.15435","repositories_listed":1,"syntology":null},{"url":"/paper/anytext2-visual-text-generation-and-editing","slug":"anytext2-visual-text-generation-and-editing","title":"AnyText2: Visual Text Generation and Editing With Customizable Attributes","date":"2024-11-22","arxiv_id":"2411.15245","repositories_listed":1,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":17,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":17,"n_pointer_only":1,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/anytext2-visual-text-generation-and-editing#ran","syntology_url":"https://syntology.ai/paper/2411.15245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15245"}},"official":{"repos":["tyxsspa/anytext2"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":17,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cross-group-attention-and-group-wise-rolling","slug":"cross-group-attention-and-group-wise-rolling","title":"Learning Modality-Aware Representations: Adaptive Group-wise Interaction Network for Multimodal MRI Synthesis","date":"2024-11-22","arxiv_id":"2411.14684","repositories_listed":1,"syntology":null},{"url":"/paper/dealing-with-synthetic-data-contamination-in","slug":"dealing-with-synthetic-data-contamination-in","title":"Dealing with Synthetic Data Contamination in Online Continual Learning","date":"2024-11-21","arxiv_id":"2411.13852","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/dealing-with-synthetic-data-contamination-in#ran","syntology_url":"https://syntology.ai/paper/2411.13852","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13852"}},"official":{"repos":["maorong-wang/esrm"],"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/detecting-human-artifacts-from-text-to-image","slug":"detecting-human-artifacts-from-text-to-image","title":"Detecting Human Artifacts from Text-to-Image Models","date":"2024-11-21","arxiv_id":"2411.13842","repositories_listed":1,"syntology":null},{"url":"/paper/mmgenbench-evaluating-the-limits-of-lmms-from","slug":"mmgenbench-evaluating-the-limits-of-lmms-from","title":"MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective","date":"2024-11-21","arxiv_id":"2411.14062","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-low-light-image-enhancement-via","slug":"zero-shot-low-light-image-enhancement-via","title":"Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion","date":"2024-11-21","arxiv_id":"2411.13961","repositories_listed":1,"syntology":null},{"url":"/paper/raw-diffusion-rgb-guided-diffusion-models-for","slug":"raw-diffusion-rgb-guided-diffusion-models-for","title":"RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generation","date":"2024-11-20","arxiv_id":"2411.13150","repositories_listed":1,"syntology":null},{"url":"/paper/vbench-comprehensive-and-versatile-benchmark","slug":"vbench-comprehensive-and-versatile-benchmark","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","date":"2024-11-20","arxiv_id":"2411.13503","repositories_listed":1,"syntology":null},{"url":"/paper/from-text-to-pose-to-image-improving","slug":"from-text-to-pose-to-image-improving","title":"From Text to Pose to Image: Improving Diffusion Model Control and Quality","date":"2024-11-19","arxiv_id":"2411.12872","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":3,"n_ran_checked":7,"n_instrument":1,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"8 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/from-text-to-pose-to-image-improving#ran","syntology_url":"https://syntology.ai/paper/2411.12872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12872"}},"official":{"repos":["clement-bonnet/text-to-pose"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":3,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/hypergan-clip-a-unified-framework-for-domain","slug":"hypergan-clip-a-unified-framework-for-domain","title":"HyperGAN-CLIP: A Unified Framework for Domain Adaptation, Image Synthesis and Manipulation","date":"2024-11-19","arxiv_id":"2411.12832","repositories_listed":1,"syntology":null},{"url":"/paper/stylecodes-encoding-stylistic-information-for","slug":"stylecodes-encoding-stylistic-information-for","title":"Stylecodes: Encoding Stylistic Information For Image Generation","date":"2024-11-19","arxiv_id":"2411.12811","repositories_listed":1,"syntology":null},{"url":"/paper/cascaded-diffusion-models-for-2d-and-3d","slug":"cascaded-diffusion-models-for-2d-and-3d","title":"Cascaded Diffusion Models for 2D and 3D Microscopy Image Synthesis to Enhance Cell Segmentation","date":"2024-11-18","arxiv_id":"2411.11515","repositories_listed":1,"syntology":null},{"url":"/paper/continuous-speculative-decoding-for","slug":"continuous-speculative-decoding-for","title":"Continuous Speculative Decoding for Autoregressive Image Generation","date":"2024-11-18","arxiv_id":"2411.11925","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":6,"n_instrument":6,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/continuous-speculative-decoding-for#ran","syntology_url":"https://syntology.ai/paper/2411.11925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11925"}},"official":{"repos":["markxcloud/cspd"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/zoomed-in-diffused-out-towards-local","slug":"zoomed-in-diffused-out-towards-local","title":"Zoomed In, Diffused Out: Towards Local Degradation-Aware Multi-Diffusion for Extreme Image Super-Resolution","date":"2024-11-18","arxiv_id":"2411.12072","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"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) · 1 unverified","sample_list":"/paper/zoomed-in-diffused-out-towards-local#ran","syntology_url":"https://syntology.ai/paper/2411.12072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.12072"}},"official":{"repos":["Brian-Moser/zido"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/time-step-generating-a-universal-synthesized","slug":"time-step-generating-a-universal-synthesized","title":"Time Step Generating: A Universal Synthesized Deepfake Image Detector","date":"2024-11-17","arxiv_id":"2411.11016","repositories_listed":1,"syntology":null},{"url":"/paper/m-var-decoupled-scale-wise-autoregressive","slug":"m-var-decoupled-scale-wise-autoregressive","title":"M-VAR: Decoupled Scale-wise Autoregressive Modeling for High-Quality Image Generation","date":"2024-11-15","arxiv_id":"2411.10433","repositories_listed":1,"syntology":{"n":13,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"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) · 5 unverified","sample_list":"/paper/m-var-decoupled-scale-wise-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2411.10433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10433"}},"official":{"repos":["oliverrensu/mvar"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/smoothcache-a-universal-inference","slug":"smoothcache-a-universal-inference","title":"SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers","date":"2024-11-15","arxiv_id":"2411.10510","repositories_listed":1,"syntology":null},{"url":"/paper/physics-informed-distillation-for-diffusion","slug":"physics-informed-distillation-for-diffusion","title":"Physics Informed Distillation for Diffusion Models","date":"2024-11-13","arxiv_id":"2411.08378","repositories_listed":1,"syntology":{"n":24,"n_ran":14,"n_constructed":0,"n_ran_checked":9,"n_instrument":5,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":7,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/physics-informed-distillation-for-diffusion#ran","syntology_url":"https://syntology.ai/paper/2411.08378","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.08378"}},"official":{"repos":["pantheon5100/pid_diffusion"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":10,"ran_from_kinds":["official"]}}},{"url":"/paper/tipo-text-to-image-with-text-presampling-for","slug":"tipo-text-to-image-with-text-presampling-for","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","date":"2024-11-12","arxiv_id":"2411.08127","repositories_listed":1,"syntology":null},{"url":"/paper/enat-rethinking-spatial-temporal-interactions","slug":"enat-rethinking-spatial-temporal-interactions","title":"ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis","date":"2024-11-11","arxiv_id":"2411.06959","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":16,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/enat-rethinking-spatial-temporal-interactions#ran","syntology_url":"https://syntology.ai/paper/2411.06959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.06959"}},"official":{"repos":["leaplabthu/enat"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/more-expressive-attention-with-negative","slug":"more-expressive-attention-with-negative","title":"More Expressive Attention with Negative Weights","date":"2024-11-11","arxiv_id":"2411.07176","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/more-expressive-attention-with-negative#ran","syntology_url":"https://syntology.ai/paper/2411.07176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07176"}},"official":{"repos":["trestad/cogattn"],"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/token-merging-for-training-free-semantic","slug":"token-merging-for-training-free-semantic","title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","date":"2024-11-11","arxiv_id":"2411.07132","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/token-merging-for-training-free-semantic#ran","syntology_url":"https://syntology.ai/paper/2411.07132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.07132"}},"official":{"repos":["hutaihang/tome"],"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/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/autoregressive-models-in-vision-a-survey","slug":"autoregressive-models-in-vision-a-survey","title":"Autoregressive Models in Vision: A Survey","date":"2024-11-08","arxiv_id":"2411.05902","repositories_listed":1,"syntology":null},{"url":"/paper/bendvlm-test-time-debiasing-of-vision","slug":"bendvlm-test-time-debiasing-of-vision","title":"BendVLM: Test-Time Debiasing of Vision-Language Embeddings","date":"2024-11-07","arxiv_id":"2411.04420","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bendvlm-test-time-debiasing-of-vision#ran","syntology_url":"https://syntology.ai/paper/2411.04420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04420"}},"official":{"repos":["waltergerych/bend_vlm"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/domaingallery-few-shot-domain-driven-image","slug":"domaingallery-few-shot-domain-driven-image","title":"DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning","date":"2024-11-07","arxiv_id":"2411.04571","repositories_listed":1,"syntology":null},{"url":"/paper/image-understanding-makes-for-a-good","slug":"image-understanding-makes-for-a-good","title":"Image Understanding Makes for A Good Tokenizer for Image Generation","date":"2024-11-07","arxiv_id":"2411.04406","repositories_listed":1,"syntology":null},{"url":"/paper/mixture-of-transformers-a-sparse-and-scalable","slug":"mixture-of-transformers-a-sparse-and-scalable","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","date":"2024-11-07","arxiv_id":"2411.04996","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":0,"n_no_contract":10,"n_pointer_only":2,"phrase":"12 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mixture-of-transformers-a-sparse-and-scalable#ran","syntology_url":"https://syntology.ai/paper/2411.04996","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04996"}},"official":null}},{"url":"/paper/precision-or-recall-an-analysis-of-image","slug":"precision-or-recall-an-analysis-of-image","title":"Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model","date":"2024-11-07","arxiv_id":"2411.05079","repositories_listed":1,"syntology":null},{"url":"/paper/taming-rectified-flow-for-inversion-and","slug":"taming-rectified-flow-for-inversion-and","title":"Taming Rectified Flow for Inversion and Editing","date":"2024-11-07","arxiv_id":"2411.04746","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"phrase":"3 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; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/taming-rectified-flow-for-inversion-and#ran","syntology_url":"https://syntology.ai/paper/2411.04746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04746"}},"official":{"repos":["wangjiangshan0725/rf-solver-edit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/dimsum-diffusion-mamba-a-scalable-and-unified","slug":"dimsum-diffusion-mamba-a-scalable-and-unified","title":"DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generation","date":"2024-11-06","arxiv_id":"2411.04168","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/dimsum-diffusion-mamba-a-scalable-and-unified#ran","syntology_url":"https://syntology.ai/paper/2411.04168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04168"}},"official":{"repos":["vinairesearch/dimsum"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/textual-aesthetics-in-large-language-models","slug":"textual-aesthetics-in-large-language-models","title":"Textual Aesthetics in Large Language Models","date":"2024-11-05","arxiv_id":"2411.02930","repositories_listed":1,"syntology":null},{"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/towards-small-object-editing-a-benchmark","slug":"towards-small-object-editing-a-benchmark","title":"Towards Small Object Editing: A Benchmark Dataset and A Training-Free Approach","date":"2024-11-03","arxiv_id":"2411.01545","repositories_listed":1,"syntology":null},{"url":"/paper/randomized-autoregressive-visual-generation","slug":"randomized-autoregressive-visual-generation","title":"Randomized Autoregressive Visual Generation","date":"2024-11-01","arxiv_id":"2411.00776","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/randomized-autoregressive-visual-generation#ran","syntology_url":"https://syntology.ai/paper/2411.00776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.00776"}},"official":{"repos":["bytedance/1d-tokenizer"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/diffpad-denoising-diffusion-based-adversarial","slug":"diffpad-denoising-diffusion-based-adversarial","title":"DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination","date":"2024-10-31","arxiv_id":"2410.24006","repositories_listed":1,"syntology":null},{"url":"/paper/edt-an-efficient-diffusion-transformer","slug":"edt-an-efficient-diffusion-transformer","title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","date":"2024-10-31","arxiv_id":"2410.23788","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":7,"n_ran_checked":9,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":2,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/edt-an-efficient-diffusion-transformer#ran","syntology_url":"https://syntology.ai/paper/2410.23788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.23788"}},"official":{"repos":["xinwangchen/edt"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":7,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/in-context-lora-for-diffusion-transformers","slug":"in-context-lora-for-diffusion-transformers","title":"In-Context LoRA for Diffusion Transformers","date":"2024-10-31","arxiv_id":"2410.23775","repositories_listed":1,"syntology":null},{"url":"/paper/identifying-drift-diffusion-and-causal","slug":"identifying-drift-diffusion-and-causal","title":"Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots","date":"2024-10-30","arxiv_id":"2410.22729","repositories_listed":1,"syntology":null},{"url":"/paper/latent-diffusion-implicit-amplification","slug":"latent-diffusion-implicit-amplification","title":"Latent Diffusion, Implicit Amplification: Efficient Continuous-Scale Super-Resolution for Remote Sensing Images","date":"2024-10-30","arxiv_id":"2410.22830","repositories_listed":1,"syntology":null},{"url":"/paper/private-synthetic-text-generation-with","slug":"private-synthetic-text-generation-with","title":"Private Synthetic Text Generation with Diffusion Models","date":"2024-10-30","arxiv_id":"2410.22971","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/private-synthetic-text-generation-with#ran","syntology_url":"https://syntology.ai/paper/2410.22971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22971"}},"official":{"repos":["trusthlt/private-synthetic-text-generation"],"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/adapting-diffusion-models-for-improved-prompt","slug":"adapting-diffusion-models-for-improved-prompt","title":"Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis","date":"2024-10-29","arxiv_id":"2410.21638","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"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) · 3 unverified","sample_list":"/paper/adapting-diffusion-models-for-improved-prompt#ran","syntology_url":"https://syntology.ai/paper/2410.21638","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21638"}},"official":{"repos":["DeepakSridhar/fgdm"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/volumetric-conditioning-module-to-control","slug":"volumetric-conditioning-module-to-control","title":"Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images","date":"2024-10-29","arxiv_id":"2410.21826","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"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) · 5 unverified","sample_list":"/paper/volumetric-conditioning-module-to-control#ran","syntology_url":"https://syntology.ai/paper/2410.21826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21826"}},"official":{"repos":["Ahn-Ssu/VCM"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/advi2i-adversarial-image-attack-on-image-to","slug":"advi2i-adversarial-image-attack-on-image-to","title":"AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models","date":"2024-10-28","arxiv_id":"2410.21471","repositories_listed":1,"syntology":null},{"url":"/paper/kandinsky-3-text-to-image-synthesis-for","slug":"kandinsky-3-text-to-image-synthesis-for","title":"Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework","date":"2024-10-28","arxiv_id":"2410.21061","repositories_listed":1,"syntology":null},{"url":"/paper/murine-ai-excels-at-cats-and-cheese","slug":"murine-ai-excels-at-cats-and-cheese","title":"Murine AI excels at cats and cheese: Structural differences between human and mouse neurons and their implementation in generative AIs","date":"2024-10-28","arxiv_id":"2410.20735","repositories_listed":1,"syntology":null},{"url":"/paper/shallow-diffuse-robust-and-invisible","slug":"shallow-diffuse-robust-and-invisible","title":"Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models","date":"2024-10-28","arxiv_id":"2410.21088","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/shallow-diffuse-robust-and-invisible#ran","syntology_url":"https://syntology.ai/paper/2410.21088","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21088"}},"official":{"repos":["liwd190019/shallow-diffuse"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/groundit-grounding-diffusion-transformers-via","slug":"groundit-grounding-diffusion-transformers-via","title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation","date":"2024-10-27","arxiv_id":"2410.20474","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/groundit-grounding-diffusion-transformers-via#ran","syntology_url":"https://syntology.ai/paper/2410.20474","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20474"}},"official":{"repos":["KAIST-Visual-AI-Group/GrounDiT"],"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/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/unified-cross-modal-image-synthesis-with","slug":"unified-cross-modal-image-synthesis-with","title":"Unified Cross-Modal Image Synthesis with Hierarchical Mixture of Product-of-Experts","date":"2024-10-25","arxiv_id":"2410.19378","repositories_listed":1,"syntology":null},{"url":"/paper/frecas-efficient-higher-resolution-image","slug":"frecas-efficient-higher-resolution-image","title":"FreCaS: Efficient Higher-Resolution Image Generation via Frequency-aware Cascaded Sampling","date":"2024-10-24","arxiv_id":"2410.18410","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"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) · 0 unverified","sample_list":"/paper/frecas-efficient-higher-resolution-image#ran","syntology_url":"https://syntology.ai/paper/2410.18410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18410"}},"official":{"repos":["xtudbxk/frecas"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/stable-consistency-tuning-understanding-and","slug":"stable-consistency-tuning-understanding-and","title":"Stable Consistency Tuning: Understanding and Improving Consistency Models","date":"2024-10-24","arxiv_id":"2410.18958","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-gans-with-mmd-neural-architecture","slug":"enhancing-gans-with-mmd-neural-architecture","title":"Enhancing GANs with MMD Neural Architecture Search, PMish Activation Function, and Adaptive Rank Decomposition","date":"2024-10-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/generation-of-indian-sign-language-letters","slug":"generation-of-indian-sign-language-letters","title":"Generation of Indian Sign Language Letters, Numbers, and Words","date":"2024-10-23","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/longitudinal-causal-image-synthesis","slug":"longitudinal-causal-image-synthesis","title":"Longitudinal Causal Image Synthesis","date":"2024-10-23","arxiv_id":"2410.17691","repositories_listed":1,"syntology":null},{"url":"/paper/medical-imaging-complexity-and-its-effects-on","slug":"medical-imaging-complexity-and-its-effects-on","title":"Medical Imaging Complexity and its Effects on GAN Performance","date":"2024-10-23","arxiv_id":"2410.17959","repositories_listed":1,"syntology":null},{"url":"/paper/altogether-image-captioning-via-re-aligning","slug":"altogether-image-captioning-via-re-aligning","title":"Altogether: Image Captioning via Re-aligning Alt-text","date":"2024-10-22","arxiv_id":"2410.17251","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/altogether-image-captioning-via-re-aligning#ran","syntology_url":"https://syntology.ai/paper/2410.17251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.17251"}},"official":{"repos":["facebookresearch/metaclip"],"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/hierarchical-clustering-for-conditional","slug":"hierarchical-clustering-for-conditional","title":"Hierarchical Clustering for Conditional Diffusion in Image Generation","date":"2024-10-22","arxiv_id":"2410.16910","repositories_listed":1,"syntology":null},{"url":"/paper/idenbat-disentangled-representation-learning","slug":"idenbat-disentangled-representation-learning","title":"IdenBAT: Disentangled Representation Learning for Identity-Preserved Brain Age Transformation","date":"2024-10-22","arxiv_id":"2410.16945","repositories_listed":1,"syntology":null},{"url":"/paper/offline-evaluation-of-set-based-text-to-image","slug":"offline-evaluation-of-set-based-text-to-image","title":"Offline Evaluation of Set-Based Text-to-Image Generation","date":"2024-10-22","arxiv_id":"2410.17331","repositories_listed":1,"syntology":null},{"url":"/paper/elucidating-the-design-space-of-language","slug":"elucidating-the-design-space-of-language","title":"Elucidating the design space of language models for image generation","date":"2024-10-21","arxiv_id":"2410.16257","repositories_listed":1,"syntology":null},{"url":"/paper/seas-few-shot-industrial-anomaly-image","slug":"seas-few-shot-industrial-anomaly-image","title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","date":"2024-10-19","arxiv_id":"2410.14987","repositories_listed":1,"syntology":null},{"url":"/paper/straightness-of-rectified-flow-a-theoretical","slug":"straightness-of-rectified-flow-a-theoretical","title":"On the Wasserstein Convergence and Straightness of Rectified Flow","date":"2024-10-19","arxiv_id":"2410.14949","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":7,"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/straightness-of-rectified-flow-a-theoretical#ran","syntology_url":"https://syntology.ai/paper/2410.14949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14949"}},"official":{"repos":["bansal-vansh/rectified-flow"],"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/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/hico-hierarchical-controllable-diffusion","slug":"hico-hierarchical-controllable-diffusion","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","date":"2024-10-18","arxiv_id":"2410.14324","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"13 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hico-hierarchical-controllable-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.14324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14324"}},"official":{"repos":["360cvgroup/hico_t2i"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/parallel-backpropagation-for-inverse-of-a","slug":"parallel-backpropagation-for-inverse-of-a","title":"Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows","date":"2024-10-18","arxiv_id":"2410.14634","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-image-generation-with-large","slug":"personalized-image-generation-with-large","title":"Personalized Image Generation with Large Multimodal Models","date":"2024-10-18","arxiv_id":"2410.14170","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/personalized-image-generation-with-large#ran","syntology_url":"https://syntology.ai/paper/2410.14170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14170"}},"official":{"repos":["yiyanxu/pigeon"],"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/arkit-labelmaker-a-new-scale-for-indoor-3d","slug":"arkit-labelmaker-a-new-scale-for-indoor-3d","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","date":"2024-10-17","arxiv_id":"2410.13924","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/arkit-labelmaker-a-new-scale-for-indoor-3d#ran","syntology_url":"https://syntology.ai/paper/2410.13924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13924"}},"official":{"repos":["cvg/labelmaker"],"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/boosting-imperceptibility-of-stable-diffusion","slug":"boosting-imperceptibility-of-stable-diffusion","title":"Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum","date":"2024-10-17","arxiv_id":"2410.13122","repositories_listed":1,"syntology":null},{"url":"/paper/deep-generative-models-unveil-patterns-in","slug":"deep-generative-models-unveil-patterns-in","title":"Deep Generative Models Unveil Patterns in Medical Images Through Vision-Language Conditioning","date":"2024-10-17","arxiv_id":"2410.13823","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/deep-generative-models-unveil-patterns-in#ran","syntology_url":"https://syntology.ai/paper/2410.13823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13823"}},"official":{"repos":["junzhin/dgm-vlc"],"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/diffusion-curriculum-synthetic-to-real","slug":"diffusion-curriculum-synthetic-to-real","title":"Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion","date":"2024-10-17","arxiv_id":"2410.13674","repositories_listed":1,"syntology":null},{"url":"/paper/fitv2-scalable-and-improved-flexible-vision","slug":"fitv2-scalable-and-improved-flexible-vision","title":"FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model","date":"2024-10-17","arxiv_id":"2410.13925","repositories_listed":1,"syntology":null},{"url":"/paper/fluid-scaling-autoregressive-text-to-image","slug":"fluid-scaling-autoregressive-text-to-image","title":"Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens","date":"2024-10-17","arxiv_id":"2410.13863","repositories_listed":1,"syntology":null},{"url":"/paper/loldu-low-rank-adaptation-via-lower-diag","slug":"loldu-low-rank-adaptation-via-lower-diag","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","date":"2024-10-17","arxiv_id":"2410.13618","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":4,"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) · 0 unverified","sample_list":"/paper/loldu-low-rank-adaptation-via-lower-diag#ran","syntology_url":"https://syntology.ai/paper/2410.13618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13618"}},"official":{"repos":["skddj/loldu"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"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/unlocking-the-capabilities-of-masked","slug":"unlocking-the-capabilities-of-masked","title":"Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance","date":"2024-10-17","arxiv_id":"2410.13136","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":3,"n_instrument":8,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"11 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; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/unlocking-the-capabilities-of-masked#ran","syntology_url":"https://syntology.ai/paper/2410.13136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13136"}},"official":{"repos":["jiwanhur/unlockmgm"],"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":["community","official"]}}},{"url":"/paper/3dis-depth-driven-decoupled-instance","slug":"3dis-depth-driven-decoupled-instance","title":"3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation","date":"2024-10-16","arxiv_id":"2410.12669","repositories_listed":1,"syntology":null}],"record_sha256":"16c9d1d503d62c04c8c798a1f2ea34f892e6c8d74f6f70a92b0d28a762e8c343","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}