{"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/38","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":38,"pages_in_order":139,"rows_per_page":100,"rows":[3701,3800],"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/37","next":"/method/diffusion/papers/39","papers":[{"paper":null,"slug":"self-guidance-boosting-flow-and-diffusion","title":"Self-Guidance: Boosting Flow and Diffusion Generation on Their Own","date":"2024-12-08","arxiv_id":"2412.05827","n_code_links":0,"syntology":null},{"paper":"/paper/topocellgen-generating-histopathology-cell","slug":"topocellgen-generating-histopathology-cell","title":"TopoCellGen: Generating Histopathology Cell Topology with a Diffusion Model","date":"2024-12-08","arxiv_id":"2412.06011","n_code_links":1,"syntology":{"ran":6,"of":6,"n_ran_checked":3,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["melon-xu/topocellgen"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"track4gen-teaching-video-diffusion-models-to","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","date":"2024-12-08","arxiv_id":"2412.06016","n_code_links":0,"syntology":null},{"paper":"/paper/dif4ff-leveraging-multimodal-diffusion-models","slug":"dif4ff-leveraging-multimodal-diffusion-models","title":"Dif4FF: Leveraging Multimodal Diffusion Models and Graph Neural Networks for Accurate New Fashion Product Performance Forecasting","date":"2024-12-07","arxiv_id":"2412.05566","n_code_links":1,"syntology":null},{"paper":null,"slug":"dm-sbl-channel-estimation-under-structured","title":"DM-SBL: Channel Estimation under Structured Interference","date":"2024-12-07","arxiv_id":"2412.05582","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-we-need-to-design-specific-diffusion","title":"Do We Need to Design Specific Diffusion Models for Different Tasks? Try ONE-PIC","date":"2024-12-07","arxiv_id":"2412.05619","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-continuous-video-flow-model-for","title":"Efficient Continuous Video Flow Model for Video Prediction","date":"2024-12-07","arxiv_id":"2412.05633","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-sample-generation-of-diffusion","title":"Enhancing Sample Generation of Diffusion Models using Noise Level Correction","date":"2024-12-07","arxiv_id":"2412.05488","n_code_links":0,"syntology":null},{"paper":"/paper/remix-dit-mixing-diffusion-transformers-for","slug":"remix-dit-mixing-diffusion-transformers-for","title":"Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising","date":"2024-12-07","arxiv_id":"2412.05628","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":5,"n_instrument":7,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 4 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","official":{"repos":["vainf/remix-dit"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"text-to-3d-gaussian-splatting-with-physics","title":"Text-to-3D Gaussian Splatting with Physics-Grounded Motion Generation","date":"2024-12-07","arxiv_id":"2412.05560","n_code_links":0,"syntology":null},{"paper":null,"slug":"7-tesla-multimodal-mri-dataset-of-ex-vivo","title":"7 Tesla multimodal MRI dataset of ex-vivo human brain","date":"2024-12-06","arxiv_id":"2412.17816","n_code_links":0,"syntology":null},{"paper":null,"slug":"birth-and-death-of-a-rose","title":"Birth and Death of a Rose","date":"2024-12-06","arxiv_id":"2412.05278","n_code_links":0,"syntology":null},{"paper":null,"slug":"dawn-si-data-aware-and-noise-informed","title":"DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems","date":"2024-12-06","arxiv_id":"2412.04766","n_code_links":0,"syntology":null},{"paper":null,"slug":"diff4steer-steerable-diffusion-prior-for","title":"Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance","date":"2024-12-06","arxiv_id":"2412.04746","n_code_links":0,"syntology":null},{"paper":null,"slug":"dnf-unconditional-4d-generation-with","title":"DNF: Unconditional 4D Generation with Dictionary-based Neural Fields","date":"2024-12-06","arxiv_id":"2412.05161","n_code_links":0,"syntology":null},{"paper":"/paper/extrapolated-urban-view-synthesis-benchmark","slug":"extrapolated-urban-view-synthesis-benchmark","title":"Extrapolated Urban View Synthesis Benchmark","date":"2024-12-06","arxiv_id":"2412.05256","n_code_links":1,"syntology":null},{"paper":null,"slug":"maximizing-alignment-with-minimal-feedback","title":"Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment","date":"2024-12-06","arxiv_id":"2412.04835","n_code_links":0,"syntology":null},{"paper":null,"slug":"megatron-evasive-clean-label-backdoor-attacks","title":"Megatron: Evasive Clean-Label Backdoor Attacks against Vision Transformer","date":"2024-12-06","arxiv_id":"2412.04776","n_code_links":0,"syntology":null},{"paper":null,"slug":"mind-the-time-temporally-controlled-multi","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","date":"2024-12-06","arxiv_id":"2412.05263","n_code_links":0,"syntology":null},{"paper":null,"slug":"motionflow-attention-driven-motion-transfer","title":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","date":"2024-12-06","arxiv_id":"2412.05275","n_code_links":0,"syntology":null},{"paper":null,"slug":"motionshop-zero-shot-motion-transfer-in-video","title":"MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance","date":"2024-12-06","arxiv_id":"2412.05355","n_code_links":0,"syntology":null},{"paper":"/paper/multi-armed-bandit-approach-for-optimizing","slug":"multi-armed-bandit-approach-for-optimizing","title":"Multi-Armed Bandit Approach for Optimizing Training on Synthetic Data","date":"2024-12-06","arxiv_id":"2412.05466","n_code_links":1,"syntology":null},{"paper":null,"slug":"noise-matters-diffusion-model-based-urban","title":"Noise Matters: Diffusion Model-based Urban Mobility Generation with Collaborative Noise Priors","date":"2024-12-06","arxiv_id":"2412.05000","n_code_links":0,"syntology":null},{"paper":null,"slug":"parametric-controlnet-multimodal-control-in","title":"Parametric-ControlNet: Multimodal Control in Foundation Models for Precise Engineering Design Synthesis","date":"2024-12-06","arxiv_id":"2412.04707","n_code_links":0,"syntology":null},{"paper":null,"slug":"perturb-and-revise-flexible-3d-editing-with","title":"Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories","date":"2024-12-06","arxiv_id":"2412.05279","n_code_links":0,"syntology":null},{"paper":null,"slug":"ref-ldm-a-latent-diffusion-model-for","title":"ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration","date":"2024-12-06","arxiv_id":"2412.05043","n_code_links":0,"syntology":null},{"paper":"/paper/sleepermark-towards-robust-watermark-against","slug":"sleepermark-towards-robust-watermark-against","title":"SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models","date":"2024-12-06","arxiv_id":"2412.04852","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-silent-prompt-initial-noise-as-implicit","title":"The Silent Prompt: Initial Noise as Implicit Guidance for Goal-Driven Image Generation","date":"2024-12-06","arxiv_id":"2412.05101","n_code_links":0,"syntology":null},{"paper":null,"slug":"unimic-towards-universal-multi-modality","title":"UniMIC: Towards Universal Multi-modality Perceptual Image Compression","date":"2024-12-06","arxiv_id":"2412.04912","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-segmentation-by-diffusing","title":"Unsupervised Segmentation by Diffusing, Walking and Cutting","date":"2024-12-06","arxiv_id":"2412.04678","n_code_links":0,"syntology":null},{"paper":"/paper/wavelet-diffusion-neural-operator","slug":"wavelet-diffusion-neural-operator","title":"Wavelet Diffusion Neural Operator","date":"2024-12-06","arxiv_id":"2412.04833","n_code_links":1,"syntology":{"ran":11,"of":13,"n_ran_checked":10,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["AI4Science-WestlakeU/wdno"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"4real-video-learning-generalizable-photo","title":"4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion","date":"2024-12-05","arxiv_id":"2412.04462","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-data-driven-framework-for-discovering","title":"A Data-Driven Framework for Discovering Fractional Differential Equations in Complex Systems","date":"2024-12-05","arxiv_id":"2412.03970","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-noise-is-worth-diffusion-guidance","title":"A Noise is Worth Diffusion Guidance","date":"2024-12-05","arxiv_id":"2412.03895","n_code_links":0,"syntology":null},{"paper":null,"slug":"actfusion-a-unified-diffusion-model-for","title":"ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation","date":"2024-12-05","arxiv_id":"2412.04353","n_code_links":0,"syntology":null},{"paper":null,"slug":"anydressing-customizable-multi-garment","title":"AnyDressing: Customizable Multi-Garment Virtual Dressing via Latent Diffusion Models","date":"2024-12-05","arxiv_id":"2412.04146","n_code_links":0,"syntology":null},{"paper":"/paper/compositional-generative-multiphysics-and","slug":"compositional-generative-multiphysics-and","title":"M2PDE: Compositional Generative Multiphysics and Multi-component PDE Simulation","date":"2024-12-05","arxiv_id":"2412.04134","n_code_links":2,"syntology":null},{"paper":null,"slug":"creatilayout-siamese-multimodal-diffusion","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","date":"2024-12-05","arxiv_id":"2412.03859","n_code_links":0,"syntology":null},{"paper":null,"slug":"dicode-diffusion-compressed-deep-tokens-for","title":"DiCoDe: Diffusion-Compressed Deep Tokens for Autoregressive Video Generation with Language Models","date":"2024-12-05","arxiv_id":"2412.04446","n_code_links":0,"syntology":null},{"paper":"/paper/diffsign-ai-assisted-generation-of","slug":"diffsign-ai-assisted-generation-of","title":"DiffSign: AI-Assisted Generation of Customizable Sign Language Videos With Enhanced Realism","date":"2024-12-05","arxiv_id":"2412.03878","n_code_links":1,"syntology":null},{"paper":"/paper/divot-diffusion-powers-video-tokenizer-for","slug":"divot-diffusion-powers-video-tokenizer-for","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","date":"2024-12-05","arxiv_id":"2412.04432","n_code_links":1,"syntology":null},{"paper":null,"slug":"editscout-locating-forged-regions-from","title":"EditScout: Locating Forged Regions from Diffusion-based Edited Images with Multimodal LLM","date":"2024-12-05","arxiv_id":"2412.03809","n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-and-accelerating-diffusion-based","title":"Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization","date":"2024-12-05","arxiv_id":"2412.03941","n_code_links":0,"syntology":null},{"paper":null,"slug":"four-plane-factorized-video-autoencoders","title":"Four-Plane Factorized Video Autoencoders","date":"2024-12-05","arxiv_id":"2412.04452","n_code_links":0,"syntology":null},{"paper":"/paper/hidden-in-the-noise-two-stage-robust","slug":"hidden-in-the-noise-two-stage-robust","title":"Hidden in the Noise: Two-Stage Robust Watermarking for Images","date":"2024-12-05","arxiv_id":"2412.04653","n_code_links":1,"syntology":{"ran":12,"of":16,"n_ran_checked":9,"n_instrument":3,"unverified":4,"pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["Kasraarabi/Hidden-in-the-Noise"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"how-well-behaved-is-finite-dimensional","title":"How well behaved is finite dimensional Diffusion Maps?","date":"2024-12-05","arxiv_id":"2412.03992","n_code_links":0,"syntology":null},{"paper":null,"slug":"if-mdm-implicit-face-motion-diffusion-model","title":"IF-MDM: Implicit Face Motion Diffusion Model for High-Fidelity Realtime Talking Head Generation","date":"2024-12-05","arxiv_id":"2412.04000","n_code_links":0,"syntology":null},{"paper":"/paper/infinity-scaling-bitwise-autoregressive","slug":"infinity-scaling-bitwise-autoregressive","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","date":"2024-12-05","arxiv_id":"2412.04431","n_code_links":2,"syntology":{"ran":14,"of":19,"n_ran_checked":5,"n_instrument":9,"unverified":5,"pointer_only":4,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 5 unverified","official":{"repos":["FoundationVision/Infinity"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"instructional-video-generation","title":"Instructional Video Generation","date":"2024-12-05","arxiv_id":"2412.04189","n_code_links":0,"syntology":null},{"paper":null,"slug":"layerfusion-harmonized-multi-layer-text-to","title":"LayerFusion: Harmonized Multi-Layer Text-to-Image Generation with Generative Priors","date":"2024-12-05","arxiv_id":"2412.04460","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-artistic-signatures-symmetry","title":"Learning Artistic Signatures: Symmetry Discovery and Style Transfer","date":"2024-12-05","arxiv_id":"2412.04441","n_code_links":0,"syntology":null},{"paper":null,"slug":"likelihood-scheduled-score-based-generative","title":"Likelihood-Scheduled Score-Based Generative Modeling for Fully 3D PET Image Reconstruction","date":"2024-12-05","arxiv_id":"2412.04339","n_code_links":0,"syntology":null},{"paper":null,"slug":"lmdm-latent-molecular-diffusion-model-for-3d","title":"LMDM:Latent Molecular Diffusion Model For 3D Molecule Generation","date":"2024-12-05","arxiv_id":"2412.04242","n_code_links":0,"syntology":null},{"paper":null,"slug":"local-curvature-smoothing-with-stein-s","title":"Local Curvature Smoothing with Stein's Identity for Efficient Score Matching","date":"2024-12-05","arxiv_id":"2412.03962","n_code_links":0,"syntology":null},{"paper":null,"slug":"memo-memory-guided-diffusion-for-expressive","title":"MEMO: Memory-Guided Diffusion for Expressive Talking Video Generation","date":"2024-12-05","arxiv_id":"2412.04448","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-subject-image-synthesis-as-a-generative","title":"Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction","date":"2024-12-05","arxiv_id":"2412.04324","n_code_links":0,"syntology":null},{"paper":null,"slug":"paintscene4d-consistent-4d-scene-generation","title":"PaintScene4D: Consistent 4D Scene Generation from Text Prompts","date":"2024-12-05","arxiv_id":"2412.04471","n_code_links":0,"syntology":null},{"paper":null,"slug":"pathwise-optimization-for-bridge-type","title":"Pathwise optimization for bridge-type estimators and its applications","date":"2024-12-05","arxiv_id":"2412.04047","n_code_links":0,"syntology":null},{"paper":"/paper/reversible-molecular-simulation-for-training","slug":"reversible-molecular-simulation-for-training","title":"Reversible molecular simulation for training classical and machine learning force fields","date":"2024-12-05","arxiv_id":"2412.04374","n_code_links":1,"syntology":null},{"paper":null,"slug":"rmd-a-simple-baseline-for-more-general-human","title":"RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse","date":"2024-12-05","arxiv_id":"2412.04343","n_code_links":0,"syntology":null},{"paper":"/paper/safeguarding-text-to-image-generation-via","slug":"safeguarding-text-to-image-generation-via","title":"Safeguarding Text-to-Image Generation via Inference-Time Prompt-Noise Optimization","date":"2024-12-05","arxiv_id":"2412.03876","n_code_links":1,"syntology":null},{"paper":null,"slug":"scenediffuser-efficient-and-controllable","title":"SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout","date":"2024-12-05","arxiv_id":"2412.12129","n_code_links":0,"syntology":null},{"paper":"/paper/structure-aware-stylized-image-synthesis-for","slug":"structure-aware-stylized-image-synthesis-for","title":"Structure-Aware Stylized Image Synthesis for Robust Medical Image Segmentation","date":"2024-12-05","arxiv_id":"2412.04296","n_code_links":1,"syntology":null},{"paper":null,"slug":"turbo3d-ultra-fast-text-to-3d-generation","title":"Turbo3D: Ultra-fast Text-to-3D Generation","date":"2024-12-05","arxiv_id":"2412.04470","n_code_links":0,"syntology":null},{"paper":null,"slug":"understanding-memorization-in-generative","title":"Understanding Memorization in Generative Models via Sharpness in Probability Landscapes","date":"2024-12-05","arxiv_id":"2412.04140","n_code_links":0,"syntology":null},{"paper":null,"slug":"align3r-aligned-monocular-depth-estimation","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","date":"2024-12-04","arxiv_id":"2412.03079","n_code_links":0,"syntology":null},{"paper":null,"slug":"appearance-matching-adapter-for-exemplar","title":"Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis","date":"2024-12-04","arxiv_id":"2412.03150","n_code_links":0,"syntology":null},{"paper":null,"slug":"black-box-forgery-attacks-on-semantic","title":"Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models","date":"2024-12-04","arxiv_id":"2412.03283","n_code_links":0,"syntology":null},{"paper":"/paper/cleandift-diffusion-features-without-noise","slug":"cleandift-diffusion-features-without-noise","title":"CleanDIFT: Diffusion Features without Noise","date":"2024-12-04","arxiv_id":"2412.03439","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"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","official":{"repos":["CompVis/cleandift"],"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"]}}},{"paper":null,"slug":"diffstyletts-diffusion-based-hierarchical","title":"DiffStyleTTS: Diffusion-based Hierarchical Prosody Modeling for Text-to-Speech with Diverse and Controllable Styles","date":"2024-12-04","arxiv_id":"2412.03388","n_code_links":0,"syntology":null},{"paper":null,"slug":"diffupt-class-imbalance-mitigation-for","title":"DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model Pretraining","date":"2024-12-04","arxiv_id":"2412.03629","n_code_links":0,"syntology":null},{"paper":"/paper/diffusion-in-zero-shot-learning-for","slug":"diffusion-in-zero-shot-learning-for","title":"Diffusion in Zero-Shot Learning for Environmental Audio","date":"2024-12-04","arxiv_id":"2412.03771","n_code_links":1,"syntology":null},{"paper":null,"slug":"diffusion-vla-scaling-robot-foundation-models","title":"Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning","date":"2024-12-04","arxiv_id":"2412.03293","n_code_links":0,"syntology":null},{"paper":null,"slug":"dive-taming-dino-for-subject-driven-video","title":"DIVE: Taming DINO for Subject-Driven Video Editing","date":"2024-12-04","arxiv_id":"2412.03347","n_code_links":0,"syntology":null},{"paper":null,"slug":"dynamiccontrol-adaptive-condition-selection","title":"DynamicControl: Adaptive Condition Selection for Improved Text-to-Image Generation","date":"2024-12-04","arxiv_id":"2412.03255","n_code_links":0,"syntology":null},{"paper":null,"slug":"flow-matching-with-general-discrete-paths-a","title":"Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective","date":"2024-12-04","arxiv_id":"2412.03487","n_code_links":0,"syntology":null},{"paper":"/paper/frequency-guided-diffusion-model-with","slug":"frequency-guided-diffusion-model-with","title":"Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection","date":"2024-12-04","arxiv_id":"2412.03044","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalized-diffusion-model-with-adjusted","title":"Generalized Diffusion Model with Adjusted Offset Noise","date":"2024-12-04","arxiv_id":"2412.03134","n_code_links":0,"syntology":null},{"paper":null,"slug":"geometry-guided-cross-view-diffusion-for-one","title":"Geometry-guided Cross-view Diffusion for One-to-many Cross-view Image Synthesis","date":"2024-12-04","arxiv_id":"2412.03315","n_code_links":0,"syntology":null},{"paper":null,"slug":"human-multi-view-synthesis-from-a-single-view","title":"Human Multi-View Synthesis from a Single-View Model:Transferred Body and Face Representations","date":"2024-12-04","arxiv_id":"2412.03011","n_code_links":0,"syntology":null},{"paper":null,"slug":"implicit-priors-editing-in-stable-diffusion","title":"Implicit Priors Editing in Stable Diffusion via Targeted Token Adjustment","date":"2024-12-04","arxiv_id":"2412.03400","n_code_links":0,"syntology":null},{"paper":null,"slug":"materialpicker-multi-modal-material","title":"MaterialPicker: Multi-Modal Material Generation with Diffusion Transformers","date":"2024-12-04","arxiv_id":"2412.03225","n_code_links":0,"syntology":null},{"paper":"/paper/midi-multi-instance-diffusion-for-single","slug":"midi-multi-instance-diffusion-for-single","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","date":"2024-12-04","arxiv_id":"2412.03558","n_code_links":0,"syntology":null},{"paper":null,"slug":"mimir-improving-video-diffusion-models-for","title":"Mimir: Improving Video Diffusion Models for Precise Text Understanding","date":"2024-12-04","arxiv_id":"2412.03085","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-view-image-diffusion-via-coordinate","title":"Multi-view Image Diffusion via Coordinate Noise and Fourier Attention","date":"2024-12-04","arxiv_id":"2412.03756","n_code_links":0,"syntology":null},{"paper":null,"slug":"multigo-towards-multi-level-geometry-learning","title":"MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction","date":"2024-12-04","arxiv_id":"2412.03103","n_code_links":0,"syntology":null},{"paper":"/paper/mv-adapter-multi-view-consistent-image","slug":"mv-adapter-multi-view-consistent-image","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","date":"2024-12-04","arxiv_id":"2412.03632","n_code_links":1,"syntology":{"ran":6,"of":7,"n_ran_checked":6,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/navigation-world-models","slug":"navigation-world-models","title":"Navigation World Models","date":"2024-12-04","arxiv_id":"2412.03572","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"nvcomposer-boosting-generative-novel-view","title":"NVComposer: Boosting Generative Novel View Synthesis with Multiple Sparse and Unposed Images","date":"2024-12-04","arxiv_id":"2412.03517","n_code_links":0,"syntology":null},{"paper":null,"slug":"panoptic-diffusion-models-co-generation-of","title":"Panoptic Diffusion Models: co-generation of images and segmentation maps","date":"2024-12-04","arxiv_id":"2412.02929","n_code_links":0,"syntology":null},{"paper":null,"slug":"partially-conditioned-patch-parallelism-for","title":"Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference","date":"2024-12-04","arxiv_id":"2412.02962","n_code_links":0,"syntology":null},{"paper":null,"slug":"patient-specific-prediction-of-glioblastoma","title":"Patient-specific prediction of glioblastoma growth via reduced order modeling and neural networks","date":"2024-12-04","arxiv_id":"2412.05330","n_code_links":0,"syntology":null},{"paper":"/paper/pixel-level-and-semantic-level-adjustable","slug":"pixel-level-and-semantic-level-adjustable","title":"Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach","date":"2024-12-04","arxiv_id":"2412.03017","n_code_links":2,"syntology":{"ran":22,"of":24,"n_ran_checked":16,"n_instrument":6,"unverified":2,"pointer_only":17,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 1 violated, 13 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","official":{"repos":["csslc/pisa-sr"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/rfsr-improving-isr-diffusion-models-via","slug":"rfsr-improving-isr-diffusion-models-via","title":"RFSR: Improving ISR Diffusion Models via Reward Feedback Learning","date":"2024-12-04","arxiv_id":"2412.03268","n_code_links":1,"syntology":null},{"paper":null,"slug":"seeing-beyond-views-multi-view-driving-scene","title":"Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention","date":"2024-12-04","arxiv_id":"2412.03520","n_code_links":0,"syntology":null},{"paper":null,"slug":"semantic-segmentation-prior-for-diffusion","title":"Semantic Segmentation Prior for Diffusion-Based Real-World Super-Resolution","date":"2024-12-04","arxiv_id":"2412.02960","n_code_links":0,"syntology":null},{"paper":null,"slug":"singer-vivid-audio-driven-singing-video","title":"SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model","date":"2024-12-04","arxiv_id":"2412.03430","n_code_links":0,"syntology":null},{"paper":null,"slug":"skel3d-skeleton-guided-novel-view-synthesis","title":"Skel3D: Skeleton Guided Novel View Synthesis","date":"2024-12-04","arxiv_id":"2412.03407","n_code_links":0,"syntology":null},{"paper":null,"slug":"sprite-sheet-diffusion-generate-game","title":"Sprite Sheet Diffusion: Generate Game Character for Animation","date":"2024-12-04","arxiv_id":"2412.03685","n_code_links":0,"syntology":null},{"paper":"/paper/tasr-timestep-aware-diffusion-model-for-image","slug":"tasr-timestep-aware-diffusion-model-for-image","title":"TASR: Timestep-Aware Diffusion Model for Image Super-Resolution","date":"2024-12-04","arxiv_id":"2412.03355","n_code_links":1,"syntology":null}],"record_sha256":"ee08f3a2e1e379b3bdbf551812d886deb6a39b7a3ede06bedb636617d35b0047","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}