{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/code/tokenize-prompt","entry":"tokenize_prompt","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":23,"n_papers_ran":15,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":12,"n_samples_ran":7,"n_samples_fingerprinted":0,"n_places":23,"n_places_pointer_only":12,"by_status":{"ran_honours":2,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":4,"unverified":5},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2609.01148","paper":"/paper/arxiv-2609-01148","title":"Dotting the Eye: An Intent-Driven Image Retouching Agent for Visual Focus Enhancement","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"DragonisCV/EyeControl","path":"src/pipelines/text_encoder.py","file_url":"https://github.com/DragonisCV/EyeControl/blob/HEAD/src/pipelines/text_encoder.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"eb4f8a321d97a458","mcp_get_code":{"code_sha256":"eb4f8a321d97a458"}},{"arxiv_id":"2607.19510","paper":"/paper/arxiv-2607-19510","title":"Total Variation Distance Estimation in Autoregressive Models","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"XunZhiyang/llm-tv-estimation","path":"experiments/fig1/cache_build.py","file_url":"https://github.com/XunZhiyang/llm-tv-estimation/blob/HEAD/experiments/fig1/cache_build.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8765d8d06d025758","mcp_get_code":{"code_sha256":"8765d8d06d025758"}},{"arxiv_id":"2509.25940","paper":"/paper/arxiv-2509-25940","title":"Steer Away From Mode Collisions: Improving Composition In Diffusion Models","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"debottam-dutta7/co3","path":"composers/utils/ptp_utils.py","file_url":"https://github.com/debottam-dutta7/co3/blob/HEAD/composers/utils/ptp_utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d3d9b5fd6b42f66c","mcp_get_code":{"code_sha256":"d3d9b5fd6b42f66c"}},{"arxiv_id":"2507.05964","paper":"/paper/t-lora-single-image-diffusion-model","title":"T-LoRA: Single Image Diffusion Model Customization Without Overfitting","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"controlgenai/t-lora","path":"flux/model/encode.py","file_url":"https://github.com/controlgenai/t-lora/blob/HEAD/flux/model/encode.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb4f8a321d97a458","mcp_get_code":{"code_sha256":"eb4f8a321d97a458"}},{"arxiv_id":"2501.01633","paper":"/paper/ace-anti-editing-concept-erasure-in-text-to","title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models","date":"2025-01-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"120l020904/ace","path":"src/train_ace.py","file_url":"https://github.com/120l020904/ace/blob/HEAD/src/train_ace.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a67a2074238bd9ef","mcp_get_code":{"code_sha256":"a67a2074238bd9ef"}},{"arxiv_id":"2412.20413","paper":"/paper/eraseanything-enabling-concept-erasure-in","title":"EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers","date":"2024-12-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tomguluson92/eraseanything","path":"prompt_process.py","file_url":"https://github.com/tomguluson92/eraseanything/blob/HEAD/prompt_process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"442d96197841458f","mcp_get_code":{"code_sha256":"442d96197841458f"}},{"arxiv_id":"2412.16112","paper":"/paper/clear-conv-like-linearization-revs-pre","title":"CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up","date":"2024-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huage001/clear","path":"cache_prompt_embeds.py","file_url":"https://github.com/huage001/clear/blob/HEAD/cache_prompt_embeds.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"eb4f8a321d97a458","mcp_get_code":{"code_sha256":"eb4f8a321d97a458"}},{"arxiv_id":"2411.16443","paper":"/paper/splatflow-multi-view-rectified-flow-model-for","title":"SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gohyojun15/SplatFlow","path":"model/multiview_rf/text_embedding.py","file_url":"https://github.com/gohyojun15/SplatFlow/blob/HEAD/model/multiview_rf/text_embedding.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"02aa413663394d0c","mcp_get_code":{"code_sha256":"02aa413663394d0c"}},{"arxiv_id":"2410.05591","paper":"/paper/tweediemix-improving-multi-concept-fusion-for","title":"TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation","date":"2024-10-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kwongihyun/tweediemix","path":"fusion_generation/fusion_sampling.py","file_url":"https://github.com/kwongihyun/tweediemix/blob/HEAD/fusion_generation/fusion_sampling.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d3d9b5fd6b42f66c","mcp_get_code":{"code_sha256":"d3d9b5fd6b42f66c"}},{"arxiv_id":"2409.08248","paper":"/paper/textboost-towards-one-shot-personalization-of","title":"TextBoost: Towards One-Shot Personalization of Text-to-Image Models via Fine-tuning Text Encoder","date":"2024-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nahyeonkaty/textboost","path":"src/textboost/datasets.py","file_url":"https://github.com/nahyeonkaty/textboost/blob/HEAD/src/textboost/datasets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"424823a175dc433e","mcp_get_code":{"code_sha256":"424823a175dc433e"}},{"arxiv_id":"2407.10910","paper":"/paper/datadream-few-shot-guided-dataset-generation","title":"DataDream: Few-shot Guided Dataset Generation","date":"2024-07-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"explainableml/datadream","path":"DataDream/datadream.py","file_url":"https://github.com/explainableml/datadream/blob/HEAD/DataDream/datadream.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a67a2074238bd9ef","mcp_get_code":{"code_sha256":"a67a2074238bd9ef"}},{"arxiv_id":"2407.05282","paper":"/paper/ultraedit-instruction-based-fine-grained","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","date":"2024-07-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkunlp-icler/ultraedit","path":"traning/train_sd3_pix2pix.py","file_url":"https://github.com/pkunlp-icler/ultraedit/blob/HEAD/traning/train_sd3_pix2pix.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"dce9df5004a68cce","mcp_get_code":{"code_sha256":"dce9df5004a68cce"}},{"arxiv_id":"2407.04604","paper":"/paper/partcraft-crafting-creative-objects-by-parts","title":"PartCraft: Crafting Creative Objects by Parts","date":"2024-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kamwoh/partcraft","path":"src/utils.py","file_url":"https://github.com/kamwoh/partcraft/blob/HEAD/src/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1e3b3a8ae01caf34","mcp_get_code":{"code_sha256":"1e3b3a8ae01caf34"}},{"arxiv_id":"2406.07487","paper":"/paper/glad-towards-better-reconstruction-with","title":"GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection","date":"2024-06-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hyao1/glad","path":"dataset/dataset_multiclass.py","file_url":"https://github.com/hyao1/glad/blob/HEAD/dataset/dataset_multiclass.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a67a2074238bd9ef","mcp_get_code":{"code_sha256":"a67a2074238bd9ef"}},{"arxiv_id":"2404.10177","paper":"/paper/consistent-diffusion-meets-tweedie-training","title":"Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data","date":"2024-03-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"giannisdaras/ambient-tweedie","path":"train_text_to_image_lora_sdxl.py","file_url":"https://github.com/giannisdaras/ambient-tweedie/blob/HEAD/train_text_to_image_lora_sdxl.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"d3d9b5fd6b42f66c","mcp_get_code":{"code_sha256":"d3d9b5fd6b42f66c"}},{"arxiv_id":"2403.06741","paper":"/paper/distribution-aware-data-expansion-with","title":"Distribution-Aware Data Expansion with Diffusion Models","date":"2024-03-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haoweiz23/distdiff","path":"dataloader.py","file_url":"https://github.com/haoweiz23/distdiff/blob/HEAD/dataloader.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a67a2074238bd9ef","mcp_get_code":{"code_sha256":"a67a2074238bd9ef"}},{"arxiv_id":"2401.06442","paper":"/paper/rotationdrag-point-based-image-editing-with","title":"RotationDrag: Point-based Image Editing with Rotated Diffusion Features","date":"2024-01-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tony-lowe/rotationdrag","path":"utils/lora_utils.py","file_url":"https://github.com/tony-lowe/rotationdrag/blob/HEAD/utils/lora_utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a67a2074238bd9ef","mcp_get_code":{"code_sha256":"a67a2074238bd9ef"}},{"arxiv_id":"2305.19256","paper":"/paper/ambient-diffusion-learning-clean","title":"Ambient Diffusion: Learning Clean Distributions from Corrupted Data","date":"2023-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d3d9b5fd6b42f66c","mcp_get_code":{"code_sha256":"d3d9b5fd6b42f66c"}},{"arxiv_id":"2301.00704","paper":"/paper/muse-text-to-image-generation-via-masked","title":"Muse: Text-To-Image Generation via Masked Generative Transformers","date":"2023-01-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"huggingface/amused","path":"training/train_amused.py","file_url":"https://github.com/huggingface/amused/blob/HEAD/training/train_amused.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e63f8661cb0af2c8","mcp_get_code":{"code_sha256":"e63f8661cb0af2c8"}},{"arxiv_id":"Wang_SleeperMark_Towards_Robust_Watermark_against_Fine-Tuning_Text-to-image_Diffusion_Models_CVPR_2025_paper","paper":null,"title":"arXiv:Wang_SleeperMark_Towards_Robust_Watermark_against_Fine-Tuning_Text-to-image_Diffusion_Models_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"taco-group/SleeperMark","path":"Stage2/utils.py","file_url":"https://github.com/taco-group/SleeperMark/blob/HEAD/Stage2/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"a67a2074238bd9ef","mcp_get_code":{"code_sha256":"a67a2074238bd9ef"}},{"arxiv_id":"Huang_ArtEditor_Learning_Customized_Instructional_Image_Editor_from_Few-Shot_Examples_ICCV_2025_paper","paper":null,"title":"arXiv:Huang_ArtEditor_Learning_Customized_Instructional_Image_Editor_from_Few-Shot_Examples_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"showlab/PhotoDoodle","path":"src/prompt_helper.py","file_url":"https://github.com/showlab/PhotoDoodle/blob/HEAD/src/prompt_helper.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"eb4f8a321d97a458","mcp_get_code":{"code_sha256":"eb4f8a321d97a458"}},{"arxiv_id":"Dai_SeaS_Few-shot_Industrial_Anomaly_Image_Generation_with_Separation_and_Sharing_ICCV_2025_paper","paper":null,"title":"arXiv:Dai_SeaS_Few-shot_Industrial_Anomaly_Image_Generation_with_Separation_and_Sharing_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HUST-SLOW/SeaS","path":"datasets/seas_dataset.py","file_url":"https://github.com/HUST-SLOW/SeaS/blob/HEAD/datasets/seas_dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c20dda6f45b3804","mcp_get_code":{"code_sha256":"6c20dda6f45b3804"}},{"arxiv_id":"Chung_Fine-Tuning_Visual_Autogressive_Models_for_Subject-Driven_Generation_ICCV_2025_paper","paper":null,"title":"arXiv:Chung_Fine-Tuning_Visual_Autogressive_Models_for_Subject-Driven_Generation_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"jiwoogit/ARBooth","path":"booth_train_final.py","file_url":"https://github.com/jiwoogit/ARBooth/blob/HEAD/booth_train_final.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"79a21725b79678b0","mcp_get_code":{"code_sha256":"79a21725b79678b0"}}]}