{"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":"/method/diffusion/papers/67","list_of":"/method/diffusion","method":"Diffusion","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":67,"pages_in_order":139,"rows_per_page":100,"rows":[6601,6700],"of":13848,"counts":{"archive_papers_tagged":13848,"with_a_code_link":5365,"where_syntology_ran_a_sample":2249,"not_listed_spam_title":0,"listed":13848,"listed_where_code_ran":2249,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1969,"every_run_a_failure_of_syntologys_instrument":280,"listed_with_a_run_with_no_instrument_failure":1969,"listed_every_run_a_failure_of_syntologys_instrument":280,"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":"/method/diffusion","prev":"/method/diffusion/papers/66","next":"/method/diffusion/papers/68","papers":[{"paper":null,"slug":"orientdream-streamlining-text-to-3d","title":"OrientDream: Streamlining Text-to-3D Generation with Explicit Orientation Control","date":"2024-06-14","arxiv_id":"2406.10000","n_code_links":0,"syntology":null},{"paper":"/paper/pid-prompt-independent-data-protection","slug":"pid-prompt-independent-data-protection","title":"PID: Prompt-Independent Data Protection Against Latent Diffusion Models","date":"2024-06-14","arxiv_id":"2406.15305","n_code_links":1,"syntology":{"ran":10,"of":17,"n_ran_checked":5,"n_instrument":5,"unverified":7,"pointer_only":17,"phrase":"10 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; 5 where Syntology's instrument failed) · 7 unverified","official":{"repos":["PKU-ML/Diffusion-PID-Protection"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"satdiffmoe-a-mixture-of-estimation-method-for","title":"SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models","date":"2024-06-14","arxiv_id":"2406.10225","n_code_links":0,"syntology":null},{"paper":"/paper/sigdiffusions-score-based-diffusion-models","slug":"sigdiffusions-score-based-diffusion-models","title":"SigDiffusions: Score-Based Diffusion Models for Long Time Series via Log-Signature Embeddings","date":"2024-06-14","arxiv_id":"2406.10354","n_code_links":1,"syntology":{"ran":28,"of":41,"n_ran_checked":25,"n_instrument":3,"unverified":13,"pointer_only":11,"phrase":"28 ran (of which 5 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 1 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 13 unverified","official":{"repos":["Barb0ra/SigDiffusions"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":5,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["found_in_text","official"]}}},{"paper":null,"slug":"training-free-camera-control-for-video","title":"Training-free Camera Control for Video Generation","date":"2024-06-14","arxiv_id":"2406.10126","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-monocular-depth-estimation-based","title":"Unsupervised Monocular Depth Estimation Based on Hierarchical Feature-Guided Diffusion","date":"2024-06-14","arxiv_id":"2406.09782","n_code_links":0,"syntology":null},{"paper":null,"slug":"videogui-a-benchmark-for-gui-automation-from","title":"VideoGUI: A Benchmark for GUI Automation from Instructional Videos","date":"2024-06-14","arxiv_id":"2406.10227","n_code_links":0,"syntology":null},{"paper":"/paper/advancing-graph-generation-through-beta","slug":"advancing-graph-generation-through-beta","title":"Advancing Graph Generation through Beta Diffusion","date":"2024-06-13","arxiv_id":"2406.09357","n_code_links":1,"syntology":null},{"paper":"/paper/alleviating-distortion-in-image-generation","slug":"alleviating-distortion-in-image-generation","title":"Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models and Time-Dependent Layer Normalization","date":"2024-06-13","arxiv_id":"2406.09416","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":11,"n_instrument":2,"unverified":3,"pointer_only":6,"phrase":"13 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; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["qihao067/DiMR"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"an-image-is-worth-more-than-16x16-patches","title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels","date":"2024-06-13","arxiv_id":"2406.09415","n_code_links":0,"syntology":null},{"paper":"/paper/batch-instructed-gradient-for-prompt","slug":"batch-instructed-gradient-for-prompt","title":"Batch-Instructed Gradient for Prompt Evolution:Systematic Prompt Optimization for Enhanced Text-to-Image Synthesis","date":"2024-06-13","arxiv_id":"2406.08713","n_code_links":1,"syntology":null},{"paper":null,"slug":"between-randomness-and-arbitrariness-some","title":"Between Randomness and Arbitrariness: Some Lessons for Reliable Machine Learning at Scale","date":"2024-06-13","arxiv_id":"2406.09548","n_code_links":0,"syntology":null},{"paper":"/paper/cleandiffuser-an-easy-to-use-modularized","slug":"cleandiffuser-an-easy-to-use-modularized","title":"CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making","date":"2024-06-13","arxiv_id":"2406.09509","n_code_links":3,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["cleandiffuserteam/cleandiffuser"],"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":["listed","official"]}}},{"paper":"/paper/clipaway-harmonizing-focused-embeddings-for","slug":"clipaway-harmonizing-focused-embeddings-for","title":"CLIPAway: Harmonizing Focused Embeddings for Removing Objects via Diffusion Models","date":"2024-06-13","arxiv_id":"2406.09368","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["YigitEkin/CLIPAway"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"consistdreamer-3d-consistent-2d-diffusion-for-1","title":"ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing","date":"2024-06-13","arxiv_id":"2406.09404","n_code_links":0,"syntology":null},{"paper":"/paper/cove-unleashing-the-diffusion-feature","slug":"cove-unleashing-the-diffusion-feature","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","date":"2024-06-13","arxiv_id":"2406.08850","n_code_links":1,"syntology":null},{"paper":"/paper/depth-anything-v2","slug":"depth-anything-v2","title":"Depth Anything V2","date":"2024-06-13","arxiv_id":"2406.09414","n_code_links":2,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"9 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["DepthAnything/Depth-Anything-V2"],"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":["listed","official"]}}},{"paper":null,"slug":"diffpogan-diffusion-policies-with-generative","title":"DiffPoGAN: Diffusion Policies with Generative Adversarial Networks for Offline Reinforcement Learning","date":"2024-06-13","arxiv_id":"2406.09089","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-gaussian-mixture-audio-denoise","title":"Diffusion Gaussian Mixture Audio Denoise","date":"2024-06-13","arxiv_id":"2406.09154","n_code_links":0,"syntology":null},{"paper":null,"slug":"e-cop-episodic-constrained-optimization-of","title":"e-COP : Episodic Constrained Optimization of Policies","date":"2024-06-13","arxiv_id":"2406.09563","n_code_links":0,"syntology":null},{"paper":"/paper/emma-your-text-to-image-diffusion-model-can","slug":"emma-your-text-to-image-diffusion-model-can","title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","date":"2024-06-13","arxiv_id":"2406.09162","n_code_links":1,"syntology":null},{"paper":null,"slug":"equiprompt-debiasing-diffusion-models-via","title":"FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models","date":"2024-06-13","arxiv_id":"2406.09070","n_code_links":0,"syntology":null},{"paper":null,"slug":"facenhance-facial-expression-enhancing-with","title":"FacEnhance: Facial Expression Enhancing with Recurrent DDPMs","date":"2024-06-13","arxiv_id":"2406.09040","n_code_links":0,"syntology":null},{"paper":null,"slug":"fair-data-generation-via-score-based","title":"FADE: Towards Fairness-aware Augmentation for Domain Generalization via Classifier-Guided Score-based Diffusion Models","date":"2024-06-13","arxiv_id":"2406.09495","n_code_links":0,"syntology":null},{"paper":null,"slug":"foura-fourier-low-rank-adaptation","title":"FouRA: Fourier Low Rank Adaptation","date":"2024-06-13","arxiv_id":"2406.08798","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-inverse-design-of-crystal","title":"Generative Inverse Design of Crystal Structures via Diffusion Models with Transformers","date":"2024-06-13","arxiv_id":"2406.09263","n_code_links":0,"syntology":null},{"paper":"/paper/hallo-hierarchical-audio-driven-visual","slug":"hallo-hierarchical-audio-driven-visual","title":"Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation","date":"2024-06-13","arxiv_id":"2406.08801","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/improving-consistency-models-with-generator","slug":"improving-consistency-models-with-generator","title":"Improving Consistency Models with Generator-Induced Flows","date":"2024-06-13","arxiv_id":"2406.09570","n_code_links":1,"syntology":null},{"paper":null,"slug":"instruct-4d-to-4d-editing-4d-scenes-as-pseudo-1","title":"Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion","date":"2024-06-13","arxiv_id":"2406.09402","n_code_links":0,"syntology":null},{"paper":"/paper/interpreting-the-weight-space-of-customized","slug":"interpreting-the-weight-space-of-customized","title":"Interpreting the Weight Space of Customized Diffusion Models","date":"2024-06-13","arxiv_id":"2406.09413","n_code_links":1,"syntology":{"ran":4,"of":8,"n_ran_checked":4,"n_instrument":0,"unverified":4,"pointer_only":8,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["snap-research/weights2weights"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"is-diffusion-model-safe-severe-data-leakage","title":"Is Diffusion Model Safe? Severe Data Leakage via Gradient-Guided Diffusion Model","date":"2024-06-13","arxiv_id":"2406.09484","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-driven-grasp-detection-1","title":"Language-driven Grasp Detection","date":"2024-06-13","arxiv_id":"2406.09489","n_code_links":0,"syntology":null},{"paper":null,"slug":"my-body-my-choice-human-centric-full-body","title":"My Body My Choice: Human-Centric Full-Body Anonymization","date":"2024-06-13","arxiv_id":"2406.09553","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-assets-3d-aware-multi-object-scene","title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","date":"2024-06-13","arxiv_id":"2406.09292","n_code_links":0,"syntology":null},{"paper":"/paper/omnitokenizer-a-joint-image-video-tokenizer","slug":"omnitokenizer-a-joint-image-video-tokenizer","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","date":"2024-06-13","arxiv_id":"2406.09399","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":1,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["foundationvision/omnitokenizer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/openvla-an-open-source-vision-language-action","slug":"openvla-an-open-source-vision-language-action","title":"OpenVLA: An Open-Source Vision-Language-Action Model","date":"2024-06-13","arxiv_id":"2406.09246","n_code_links":3,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"operator-informed-score-matching-for-markov","title":"Operator-informed score matching for Markov diffusion models","date":"2024-06-13","arxiv_id":"2406.09084","n_code_links":0,"syntology":null},{"paper":null,"slug":"preserving-identity-with-variational-score","title":"Preserving Identity with Variational Score for General-purpose 3D Editing","date":"2024-06-13","arxiv_id":"2406.08953","n_code_links":0,"syntology":null},{"paper":null,"slug":"rethinking-score-distillation-as-a-bridge","title":"Rethinking Score Distillation as a Bridge Between Image Distributions","date":"2024-06-13","arxiv_id":"2406.09417","n_code_links":0,"syntology":null},{"paper":"/paper/sagiri-low-dynamic-range-image-enhancement","slug":"sagiri-low-dynamic-range-image-enhancement","title":"Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior","date":"2024-06-13","arxiv_id":"2406.09389","n_code_links":1,"syntology":null},{"paper":null,"slug":"simgen-simulator-conditioned-driving-scene","title":"SimGen: Simulator-conditioned Driving Scene Generation","date":"2024-06-13","arxiv_id":"2406.09386","n_code_links":0,"syntology":null},{"paper":null,"slug":"stablematerials-enhancing-diversity-in","title":"StableMaterials: Enhancing Diversity in Material Generation via Semi-Supervised Learning","date":"2024-06-13","arxiv_id":"2406.09293","n_code_links":0,"syntology":null},{"paper":null,"slug":"step-by-step-diffusion-an-elementary-tutorial","title":"Step-by-Step Diffusion: An Elementary Tutorial","date":"2024-06-13","arxiv_id":"2406.08929","n_code_links":0,"syntology":null},{"paper":null,"slug":"turns-out-i-m-not-real-towards-robust","title":"Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos","date":"2024-06-13","arxiv_id":"2406.09601","n_code_links":0,"syntology":null},{"paper":"/paper/understanding-hallucinations-in-diffusion","slug":"understanding-hallucinations-in-diffusion","title":"Understanding Hallucinations in Diffusion Models through Mode Interpolation","date":"2024-06-13","arxiv_id":"2406.09358","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["locuslab/diffusion-model-hallucination"],"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"]}}},{"paper":null,"slug":"wonderworld-interactive-3d-scene-generation","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","date":"2024-06-13","arxiv_id":"2406.09394","n_code_links":0,"syntology":null},{"paper":null,"slug":"2-5d-multi-view-averaging-diffusion-model-for","title":"2.5D Multi-view Averaging Diffusion Model for 3D Medical Image Translation: Application to Low-count PET Reconstruction with CT-less Attenuation Correction","date":"2024-06-12","arxiv_id":"2406.08374","n_code_links":0,"syntology":null},{"paper":null,"slug":"ablation-based-counterfactuals","title":"Ablation Based Counterfactuals","date":"2024-06-12","arxiv_id":"2406.07908","n_code_links":0,"syntology":null},{"paper":"/paper/cfg-manifold-constrained-classifier-free","slug":"cfg-manifold-constrained-classifier-free","title":"CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08070","n_code_links":1,"syntology":null},{"paper":"/paper/collective-invasion-when-does-domain","slug":"collective-invasion-when-does-domain","title":"Collective Invasion: When does domain curvature matter?","date":"2024-06-12","arxiv_id":"2406.08291","n_code_links":1,"syntology":null},{"paper":"/paper/dataset-enhancement-with-instance-level","slug":"dataset-enhancement-with-instance-level","title":"Dataset Enhancement with Instance-Level Augmentations","date":"2024-06-12","arxiv_id":"2406.08249","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":{"repos":["KupynOrest/instance_augmentation"],"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"]}}},{"paper":null,"slug":"deep-learning-for-quadratic-hedging-in","title":"Deep learning for quadratic hedging in incomplete jump market","date":"2024-06-12","arxiv_id":"2407.13688","n_code_links":0,"syntology":null},{"paper":null,"slug":"diff-a-riff-musical-accompaniment-co-creation","title":"Diff-A-Riff: Musical Accompaniment Co-creation via Latent Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08384","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffpop-plausibility-guided-object-placement","title":"DiffPop: Plausibility-Guided Object Placement Diffusion for Image Composition","date":"2024-06-12","arxiv_id":"2406.07852","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-promoted-hdr-video-reconstruction","title":"Diffusion-Promoted HDR Video Reconstruction","date":"2024-06-12","arxiv_id":"2406.08204","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffusion-soup-model-merging-for-text-to","title":"Diffusion Soup: Model Merging for Text-to-Image Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08431","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-the-impact-of-sequence","title":"Evaluating the Impact of Sequence Combinations on Breast Tumor Segmentation in Multiparametric MRI","date":"2024-06-12","arxiv_id":"2406.07813","n_code_links":0,"syntology":null},{"paper":null,"slug":"fakeinversion-learning-to-detect-images-from-1","title":"FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion","date":"2024-06-12","arxiv_id":"2406.08603","n_code_links":0,"syntology":null},{"paper":"/paper/flexible-music-conditioned-dance-generation","slug":"flexible-music-conditioned-dance-generation","title":"Controllable Dance Generation with Style-Guided Motion Diffusion","date":"2024-06-12","arxiv_id":"2406.07871","n_code_links":1,"syntology":null},{"paper":null,"slug":"fontstudio-shape-adaptive-diffusion-model-for","title":"FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation","date":"2024-06-12","arxiv_id":"2406.08392","n_code_links":0,"syntology":null},{"paper":"/paper/hierarchical-patch-diffusion-models-for-high-1","slug":"hierarchical-patch-diffusion-models-for-high-1","title":"Hierarchical Patch Diffusion Models for High-Resolution Video Generation","date":"2024-06-12","arxiv_id":"2406.07792","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-to-distinguish-ai-generated-images-from","title":"How to Distinguish AI-Generated Images from Authentic Photographs","date":"2024-06-12","arxiv_id":"2406.08651","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-3diffusion-realistic-avatar-creation","title":"Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08475","n_code_links":0,"syntology":null},{"paper":"/paper/lafma-a-latent-flow-matching-model-for-text","slug":"lafma-a-latent-flow-matching-model-for-text","title":"LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation","date":"2024-06-12","arxiv_id":"2406.08203","n_code_links":1,"syntology":null},{"paper":"/paper/mail-improving-imitation-learning-with-mamba","slug":"mail-improving-imitation-learning-with-mamba","title":"MaIL: Improving Imitation Learning with Mamba","date":"2024-06-12","arxiv_id":"2406.08234","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alrhub/mail"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"make-your-actor-talk-generalizable-and-high","title":"Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement","date":"2024-06-12","arxiv_id":"2406.08096","n_code_links":0,"syntology":null},{"paper":null,"slug":"mental-intervention-in-quantum-scattering-of","title":"Mental intervention in quantum scattering of ions without violating conservation laws","date":"2024-06-12","arxiv_id":"2406.08601","n_code_links":0,"syntology":null},{"paper":"/paper/one-step-effective-diffusion-network-for-real","slug":"one-step-effective-diffusion-network-for-real","title":"One-Step Effective Diffusion Network for Real-World Image Super-Resolution","date":"2024-06-12","arxiv_id":"2406.08177","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["cswry/osediff"],"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"]}}},{"paper":"/paper/predicting-cascading-failures-with-a","slug":"predicting-cascading-failures-with-a","title":"Predicting Cascading Failures with a Hyperparametric Diffusion Model","date":"2024-06-12","arxiv_id":"2406.08522","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-consuming-generative-models-with-curated","title":"Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences","date":"2024-06-12","arxiv_id":"2407.09499","n_code_links":0,"syntology":null},{"paper":null,"slug":"vivid-zoo-multi-view-video-generation-with","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","date":"2024-06-12","arxiv_id":"2406.08659","n_code_links":0,"syntology":null},{"paper":"/paper/what-if-we-recaption-billions-of-web-images","slug":"what-if-we-recaption-billions-of-web-images","title":"What If We Recaption Billions of Web Images with LLaMA-3?","date":"2024-06-12","arxiv_id":"2406.08478","n_code_links":0,"syntology":null},{"paper":null,"slug":"wmadapter-adding-watermark-control-to-latent","title":"WMAdapter: Adding WaterMark Control to Latent Diffusion Models","date":"2024-06-12","arxiv_id":"2406.08337","n_code_links":0,"syntology":null},{"paper":null,"slug":"words-worth-a-thousand-pictures-measuring-and","title":"Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation","date":"2024-06-12","arxiv_id":"2406.08482","n_code_links":0,"syntology":null},{"paper":"/paper/an-image-is-worth-32-tokens-for","slug":"an-image-is-worth-32-tokens-for","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","date":"2024-06-11","arxiv_id":"2406.07550","n_code_links":2,"syntology":null},{"paper":"/paper/asyncdiff-parallelizing-diffusion-models-by","slug":"asyncdiff-parallelizing-diffusion-models-by","title":"AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising","date":"2024-06-11","arxiv_id":"2406.06911","n_code_links":2,"syntology":{"ran":5,"of":6,"n_ran_checked":2,"n_instrument":3,"unverified":1,"pointer_only":0,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["czg1225/asyncdiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"av-dit-efficient-audio-visual-diffusion","title":"AV-DiT: Efficient Audio-Visual Diffusion Transformer for Joint Audio and Video Generation","date":"2024-06-11","arxiv_id":"2406.07686","n_code_links":0,"syntology":null},{"paper":null,"slug":"commonsense-t2i-challenge-can-text-to-image","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","date":"2024-06-11","arxiv_id":"2406.07546","n_code_links":0,"syntology":null},{"paper":null,"slug":"ctrl-x-controlling-structure-and-appearance","title":"Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance","date":"2024-06-11","arxiv_id":"2406.07540","n_code_links":0,"syntology":null},{"paper":null,"slug":"cupid-contextual-understanding-of-prompt","title":"CUPID: Contextual Understanding of Prompt-conditioned Image Distributions","date":"2024-06-11","arxiv_id":"2406.07699","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffcom-channel-received-signal-is-a-natural","title":"DiffCom: Channel Received Signal is a Natural Condition to Guide Diffusion Posterior Sampling","date":"2024-06-11","arxiv_id":"2406.07390","n_code_links":0,"syntology":null},{"paper":null,"slug":"dnn-partitioning-task-offloading-and-resource","title":"DNN Partitioning, Task Offloading, and Resource Allocation in Dynamic Vehicular Networks: A Lyapunov-Guided Diffusion-Based Reinforcement Learning Approach","date":"2024-06-11","arxiv_id":"2406.06986","n_code_links":0,"syntology":null},{"paper":"/paper/evolving-from-single-modal-to-multi-modal","slug":"evolving-from-single-modal-to-multi-modal","title":"Evolving from Single-modal to Multi-modal Facial Deepfake Detection: A Survey","date":"2024-06-11","arxiv_id":"2406.06965","n_code_links":2,"syntology":null},{"paper":null,"slug":"eye-for-an-eye-appearance-transfer-with","title":"Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models","date":"2024-06-11","arxiv_id":"2406.07008","n_code_links":0,"syntology":null},{"paper":null,"slug":"flow-map-matching","title":"Flow map matching with stochastic interpolants: A mathematical framework for consistency models","date":"2024-06-11","arxiv_id":"2406.07507","n_code_links":0,"syntology":null},{"paper":null,"slug":"generative-lifting-of-multiview-to-3d-from","title":"Generative Lifting of Multiview to 3D from Unknown Pose: Wrapping NeRF inside Diffusion","date":"2024-06-11","arxiv_id":"2406.06972","n_code_links":0,"syntology":null},{"paper":"/paper/glad-towards-better-reconstruction-with","slug":"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","arxiv_id":"2406.07487","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":10,"n_instrument":3,"unverified":2,"pointer_only":8,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hyao1/glad"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hoi-swap-swapping-objects-in-videos-with-hand","title":"HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness","date":"2024-06-11","arxiv_id":"2406.07754","n_code_links":0,"syntology":null},{"paper":null,"slug":"image-neural-field-diffusion-models","title":"Image Neural Field Diffusion Models","date":"2024-06-11","arxiv_id":"2406.07480","n_code_links":0,"syntology":null},{"paper":null,"slug":"instant-3d-human-avatar-generation-using","title":"Instant 3D Human Avatar Generation using Image Diffusion Models","date":"2024-06-11","arxiv_id":"2406.07516","n_code_links":0,"syntology":null},{"paper":"/paper/is-one-gpu-enough-pushing-image-generation-at","slug":"is-one-gpu-enough-pushing-image-generation-at","title":"Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models","date":"2024-06-11","arxiv_id":"2406.07251","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["thanos-db/pixelsmith"],"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","unlocated"]}}},{"paper":"/paper/motion-consistency-model-accelerating-video","slug":"motion-consistency-model-accelerating-video","title":"Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation","date":"2024-06-11","arxiv_id":"2406.06890","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["yhZhai/mcm"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"neural-gaffer-relighting-any-object-via","title":"Neural Gaffer: Relighting Any Object via Diffusion","date":"2024-06-11","arxiv_id":"2406.07520","n_code_links":0,"syntology":null},{"paper":"/paper/noise-robust-speech-separation-with-fast","slug":"noise-robust-speech-separation-with-fast","title":"Noise-robust Speech Separation with Fast Generative Correction","date":"2024-06-11","arxiv_id":"2406.07461","n_code_links":1,"syntology":null},{"paper":null,"slug":"object-level-scene-deocclusion","title":"Object-level Scene Deocclusion","date":"2024-06-11","arxiv_id":"2406.07706","n_code_links":0,"syntology":null},{"paper":null,"slug":"pre-training-feature-guided-diffusion-model","title":"Pre-training Feature Guided Diffusion Model for Speech Enhancement","date":"2024-06-11","arxiv_id":"2406.07646","n_code_links":0,"syntology":null},{"paper":null,"slug":"recmodiffuse-recurrent-flow-diffusion-for","title":"RecMoDiffuse: Recurrent Flow Diffusion for Human Motion Generation","date":"2024-06-11","arxiv_id":"2406.07169","n_code_links":0,"syntology":null},{"paper":"/paper/simple-and-effective-masked-diffusion","slug":"simple-and-effective-masked-diffusion","title":"Simple and Effective Masked Diffusion Language Models","date":"2024-06-11","arxiv_id":"2406.07524","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["kuleshov-group/mdlm"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"towards-realistic-data-generation-for-real","title":"Towards Realistic Data Generation for Real-World Super-Resolution","date":"2024-06-11","arxiv_id":"2406.07255","n_code_links":0,"syntology":null},{"paper":"/paper/treeffuser-probabilistic-predictions-via","slug":"treeffuser-probabilistic-predictions-via","title":"Treeffuser: Probabilistic Predictions via Conditional Diffusions with Gradient-Boosted Trees","date":"2024-06-11","arxiv_id":"2406.07658","n_code_links":1,"syntology":{"ran":1,"of":5,"n_ran_checked":1,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["blei-lab/treeffuser"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}}],"record_sha256":"5a0d60999a4c47e6f371d07304bb27c812cf77238bcf44d9d9d87330eb30c9f3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}