{"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/20","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":20,"pages_in_order":139,"rows_per_page":100,"rows":[1901,2000],"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/19","next":"/method/diffusion/papers/21","papers":[{"paper":"/paper/perceive-understand-and-restore-real-world","slug":"perceive-understand-and-restore-real-world","title":"Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models","date":"2025-03-14","arxiv_id":"2503.11073","n_code_links":1,"syntology":null},{"paper":null,"slug":"psf-4d-a-progressive-sampling-framework-for","title":"PSF-4D: A Progressive Sampling Framework for View Consistent 4D Editing","date":"2025-03-14","arxiv_id":"2503.11044","n_code_links":0,"syntology":null},{"paper":null,"slug":"safe-var-safe-visual-autoregressive-model-for","title":"Safe-VAR: Safe Visual Autoregressive Model for Text-to-Image Generative Watermarking","date":"2025-03-14","arxiv_id":"2503.11324","n_code_links":0,"syntology":null},{"paper":null,"slug":"taste-rob-advancing-video-generation-of-task","title":"TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation","date":"2025-03-14","arxiv_id":"2503.11423","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-correct-usage-of-cryptography-in","title":"Towards A Correct Usage of Cryptography in Semantic Watermarks for Diffusion Models","date":"2025-03-14","arxiv_id":"2503.11404","n_code_links":0,"syntology":null},{"paper":"/paper/towards-better-alignment-training-diffusion","slug":"towards-better-alignment-training-diffusion","title":"Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards","date":"2025-03-14","arxiv_id":"2503.11240","n_code_links":1,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["hu-zijing/b2-diffurl"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"understanding-flatness-in-generative-models","title":"Understanding Flatness in Generative Models: Its Role and Benefits","date":"2025-03-14","arxiv_id":"2503.11078","n_code_links":0,"syntology":null},{"paper":"/paper/advpaint-protecting-images-from-inpainting","slug":"advpaint-protecting-images-from-inpainting","title":"AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption","date":"2025-03-13","arxiv_id":"2503.10081","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["joonsungjeon/advpaint"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"audiox-diffusion-transformer-for-anything-to","title":"AudioX: Diffusion Transformer for Anything-to-Audio Generation","date":"2025-03-13","arxiv_id":"2503.10522","n_code_links":0,"syntology":null},{"paper":null,"slug":"cameractrl-ii-dynamic-scene-exploration-via","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models","date":"2025-03-13","arxiv_id":"2503.10592","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-wise-noise-scheduled-diffusion-for","title":"Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes","date":"2025-03-13","arxiv_id":"2503.09993","n_code_links":0,"syntology":null},{"paper":null,"slug":"cinema-coherent-multi-subject-video","title":"CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance","date":"2025-03-13","arxiv_id":"2503.10391","n_code_links":0,"syntology":null},{"paper":null,"slug":"codiphy-a-general-framework-for-applying","title":"CoDiPhy: A General Framework for Applying Denoising Diffusion Models to the Physical Layer of Wireless Communication Systems","date":"2025-03-13","arxiv_id":"2503.10297","n_code_links":0,"syntology":null},{"paper":null,"slug":"consislora-enhancing-content-and-style","title":"ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer","date":"2025-03-13","arxiv_id":"2503.10614","n_code_links":0,"syntology":null},{"paper":null,"slug":"cosh-dit-co-speech-gesture-video-synthesis","title":"Cosh-DiT: Co-Speech Gesture Video Synthesis via Hybrid Audio-Visual Diffusion Transformers","date":"2025-03-13","arxiv_id":"2503.09942","n_code_links":0,"syntology":null},{"paper":"/paper/costa-ast-cost-sensitive-toolpath-agent-for","slug":"costa-ast-cost-sensitive-toolpath-agent-for","title":"CoSTA$\\ast$: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing","date":"2025-03-13","arxiv_id":"2503.10613","n_code_links":1,"syntology":null},{"paper":"/paper/costodet-ddpm-collaborative-training-of","slug":"costodet-ddpm-collaborative-training-of","title":"CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognition","date":"2025-03-13","arxiv_id":"2503.10216","n_code_links":1,"syntology":null},{"paper":null,"slug":"data-augmentation-using-diffusion-models-to","title":"Data augmentation using diffusion models to enhance inverse Ising inference","date":"2025-03-13","arxiv_id":"2503.10154","n_code_links":0,"syntology":null},{"paper":null,"slug":"distilling-diversity-and-control-in-diffusion","title":"Distilling Diversity and Control in Diffusion Models","date":"2025-03-13","arxiv_id":"2503.10637","n_code_links":0,"syntology":null},{"paper":null,"slug":"dit-air-revisiting-the-efficiency-of","title":"DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation","date":"2025-03-13","arxiv_id":"2503.10618","n_code_links":0,"syntology":null},{"paper":null,"slug":"dreaminsert-zero-shot-image-to-video-object","title":"DreamInsert: Zero-Shot Image-to-Video Object Insertion from A Single Image","date":"2025-03-13","arxiv_id":"2503.10342","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-facial-privacy-protection-via","slug":"enhancing-facial-privacy-protection-via","title":"Enhancing Facial Privacy Protection via Weakening Diffusion Purification","date":"2025-03-13","arxiv_id":"2503.10350","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-diffusion-generative-models-via","title":"Fine-Tuning Diffusion Generative Models via Rich Preference Optimization","date":"2025-03-13","arxiv_id":"2503.11720","n_code_links":0,"syntology":null},{"paper":"/paper/got-unleashing-reasoning-capability-of","slug":"got-unleashing-reasoning-capability-of","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","date":"2025-03-13","arxiv_id":"2503.10639","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":0,"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) · 1 unverified","official":{"repos":["rongyaofang/got"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"hybridvla-collaborative-diffusion-and","title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","date":"2025-03-13","arxiv_id":"2503.10631","n_code_links":0,"syntology":null},{"paper":"/paper/improving-diffusion-based-inverse-algorithms","slug":"improving-diffusion-based-inverse-algorithms","title":"Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolation","date":"2025-03-13","arxiv_id":"2503.10103","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":{"repos":["weigerzan/lle_inverse_problem"],"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":"investigating-and-improving-counter","title":"Investigating and Improving Counter-Stereotypical Action Relation in Text-to-Image Diffusion Models","date":"2025-03-13","arxiv_id":"2503.10037","n_code_links":0,"syntology":null},{"paper":null,"slug":"long-context-tuning-for-video-generation","title":"Long Context Tuning for Video Generation","date":"2025-03-13","arxiv_id":"2503.10589","n_code_links":0,"syntology":null},{"paper":"/paper/moedit-on-learning-quantity-perception-for","slug":"moedit-on-learning-quantity-perception-for","title":"MoEdit: On Learning Quantity Perception for Multi-object Image Editing","date":"2025-03-13","arxiv_id":"2503.10112","n_code_links":1,"syntology":null},{"paper":null,"slug":"mudg-taming-multi-modal-diffusion-with","title":"MuDG: Taming Multi-modal Diffusion with Gaussian Splatting for Urban Scene Reconstruction","date":"2025-03-13","arxiv_id":"2503.10604","n_code_links":0,"syntology":null},{"paper":null,"slug":"nil-no-data-imitation-learning-by-leveraging","title":"NIL: No-data Imitation Learning by Leveraging Pre-trained Video Diffusion Models","date":"2025-03-13","arxiv_id":"2503.10626","n_code_links":0,"syntology":null},{"paper":null,"slug":"panogen-domain-adapted-text-guided-panoramic","title":"PanoGen++: Domain-Adapted Text-Guided Panoramic Environment Generation for Vision-and-Language Navigation","date":"2025-03-13","arxiv_id":"2503.09938","n_code_links":0,"syntology":null},{"paper":null,"slug":"probability-flow-ode-in-infinite-dimensional","title":"Probability-Flow ODE in Infinite-Dimensional Function Spaces","date":"2025-03-13","arxiv_id":"2503.10219","n_code_links":0,"syntology":null},{"paper":null,"slug":"proxy-tuning-tailoring-multimodal","title":"Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation","date":"2025-03-13","arxiv_id":"2503.10125","n_code_links":0,"syntology":null},{"paper":"/paper/ri3d-few-shot-gaussian-splatting-with-repair","slug":"ri3d-few-shot-gaussian-splatting-with-repair","title":"RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors","date":"2025-03-13","arxiv_id":"2503.10860","n_code_links":1,"syntology":null},{"paper":null,"slug":"streaming-generation-of-co-speech-gestures","title":"Streaming Generation of Co-Speech Gestures via Accelerated Rolling Diffusion","date":"2025-03-13","arxiv_id":"2503.10488","n_code_links":0,"syntology":null},{"paper":null,"slug":"studying-classifier-free-guidance-from-a","title":"Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective","date":"2025-03-13","arxiv_id":"2503.10638","n_code_links":0,"syntology":null},{"paper":null,"slug":"videomerge-towards-training-free-long-video","title":"VideoMerge: Towards Training-free Long Video Generation","date":"2025-03-13","arxiv_id":"2503.09926","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-diffusion-sampling-via","title":"Accelerating Diffusion Sampling via Exploiting Local Transition Coherence","date":"2025-03-12","arxiv_id":"2503.09675","n_code_links":0,"syntology":null},{"paper":null,"slug":"active-learning-inspired-controlnet-guidance","title":"Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets","date":"2025-03-12","arxiv_id":"2503.09221","n_code_links":0,"syntology":null},{"paper":"/paper/advad-exploring-non-parametric-diffusion-for-1","slug":"advad-exploring-non-parametric-diffusion-for-1","title":"AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks","date":"2025-03-12","arxiv_id":"2503.09124","n_code_links":1,"syntology":null},{"paper":"/paper/alias-free-latent-diffusion-models-improving","slug":"alias-free-latent-diffusion-models-improving","title":"Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space","date":"2025-03-12","arxiv_id":"2503.09419","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["singlezombie/afldm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/block-diffusion-interpolating-between","slug":"block-diffusion-interpolating-between","title":"Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models","date":"2025-03-12","arxiv_id":"2503.09573","n_code_links":2,"syntology":{"ran":14,"of":15,"n_ran_checked":11,"n_instrument":3,"unverified":1,"pointer_only":8,"phrase":"14 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; 3 where Syntology's instrument failed) · 1 unverified","official":{"repos":["kuleshov-group/bd3lms"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"cm-diff-a-single-generative-network-for","title":"CM-Diff: A Single Generative Network for Bidirectional Cross-Modality Translation Diffusion Model Between Infrared and Visible Images","date":"2025-03-12","arxiv_id":"2503.09514","n_code_links":0,"syntology":null},{"paper":null,"slug":"constrained-language-generation-with-discrete","title":"Constrained Language Generation with Discrete Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09790","n_code_links":0,"syntology":null},{"paper":"/paper/context-guided-responsible-data-augmentation","slug":"context-guided-responsible-data-augmentation","title":"Context-guided Responsible Data Augmentation with Diffusion Models","date":"2025-03-12","arxiv_id":"2503.10687","n_code_links":1,"syntology":null},{"paper":"/paper/core-2-collect-reflect-and-refine-to-generate","slug":"core-2-collect-reflect-and-refine-to-generate","title":"CoRe^2: Collect, Reflect and Refine to Generate Better and Faster","date":"2025-03-12","arxiv_id":"2503.09662","n_code_links":1,"syntology":null},{"paper":null,"slug":"diff-cl-a-novel-cross-pseudo-supervision","title":"Diff-CL: A Novel Cross Pseudo-Supervision Method for Semi-supervised Medical Image Segmentation","date":"2025-03-12","arxiv_id":"2503.09408","n_code_links":0,"syntology":null},{"paper":null,"slug":"error-analyses-of-auto-regressive-video","title":"Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework","date":"2025-03-12","arxiv_id":"2503.10704","n_code_links":0,"syntology":null},{"paper":null,"slug":"fcas-fine-grained-cardiac-image-synthesis","title":"FCaS: Fine-grained Cardiac Image Synthesis based on 3D Template Conditional Diffusion Model","date":"2025-03-12","arxiv_id":"2503.09560","n_code_links":0,"syntology":null},{"paper":null,"slug":"i2v3d-controllable-image-to-video-generation","title":"I2V3D: Controllable image-to-video generation with 3D guidance","date":"2025-03-12","arxiv_id":"2503.09733","n_code_links":0,"syntology":null},{"paper":null,"slug":"incomplete-multi-view-clustering-via-2","title":"Incomplete Multi-view Clustering via Diffusion Contrastive Generation","date":"2025-03-12","arxiv_id":"2503.09185","n_code_links":0,"syntology":null},{"paper":null,"slug":"inductive-spatio-temporal-kriging-with","title":"Inductive Spatio-Temporal Kriging with Physics-Guided Increment Training Strategy for Air Quality Inference","date":"2025-03-12","arxiv_id":"2503.09646","n_code_links":0,"syntology":null},{"paper":null,"slug":"leveraging-semantic-attribute-binding-for","title":"Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09864","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimax-optimality-of-the-probability-flow","title":"Minimax Optimality of the Probability Flow ODE for Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09583","n_code_links":0,"syntology":null},{"paper":null,"slug":"monte-carlo-diffusion-for-generalizable","title":"Monte Carlo Diffusion for Generalizable Learning-Based RANSAC","date":"2025-03-12","arxiv_id":"2503.09410","n_code_links":0,"syntology":null},{"paper":null,"slug":"nami-efficient-image-generation-via","title":"NAMI: Efficient Image Generation via Progressive Rectified Flow Transformers","date":"2025-03-12","arxiv_id":"2503.09242","n_code_links":0,"syntology":null},{"paper":null,"slug":"other-vehicle-trajectories-are-also-needed-a","title":"Other Vehicle Trajectories Are Also Needed: A Driving World Model Unifies Ego-Other Vehicle Trajectories in Video Latant Space","date":"2025-03-12","arxiv_id":"2503.09215","n_code_links":0,"syntology":null},{"paper":"/paper/percov2-improved-ultra-low-bit-rate","slug":"percov2-improved-ultra-low-bit-rate","title":"PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling","date":"2025-03-12","arxiv_id":"2503.09368","n_code_links":1,"syntology":null},{"paper":null,"slug":"reangle-a-video-4d-video-generation-as-video","title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","date":"2025-03-12","arxiv_id":"2503.09151","n_code_links":0,"syntology":null},{"paper":"/paper/rewardsds-aligning-score-distillation-via","slug":"rewardsds-aligning-score-distillation-via","title":"RewardSDS: Aligning Score Distillation via Reward-Weighted Sampling","date":"2025-03-12","arxiv_id":"2503.09601","n_code_links":1,"syntology":{"ran":5,"of":9,"n_ran_checked":5,"n_instrument":0,"unverified":4,"pointer_only":0,"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) · 4 unverified","official":{"repos":["itaychachy/RewardSDS"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"silent-branding-attack-trigger-free-data","title":"Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09669","n_code_links":0,"syntology":null},{"paper":null,"slug":"solving-bayesian-inverse-problems-with-1","title":"Solving Bayesian inverse problems with diffusion priors and off-policy RL","date":"2025-03-12","arxiv_id":"2503.09746","n_code_links":0,"syntology":null},{"paper":"/paper/sparse-autoencoder-as-a-zero-shot-classifier","slug":"sparse-autoencoder-as-a-zero-shot-classifier","title":"Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models","date":"2025-03-12","arxiv_id":"2503.09446","n_code_links":1,"syntology":null},{"paper":null,"slug":"supercarver-texture-consistent-3d-geometry","title":"SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation","date":"2025-03-12","arxiv_id":"2503.09439","n_code_links":0,"syntology":null},{"paper":null,"slug":"ta-v2a-textually-assisted-video-to-audio","title":"TA-V2A: Textually Assisted Video-to-Audio Generation","date":"2025-03-12","arxiv_id":"2503.10700","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-pitfalls-of-imitation-learning-when","title":"The Pitfalls of Imitation Learning when Actions are Continuous","date":"2025-03-12","arxiv_id":"2503.09722","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-r2d2-deep-neural-network-series-for","title":"The R2D2 Deep Neural Network Series for Scalable Non-Cartesian Magnetic Resonance Imaging","date":"2025-03-12","arxiv_id":"2503.09559","n_code_links":0,"syntology":null},{"paper":null,"slug":"theoretical-guarantees-for-high-order","title":"Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows","date":"2025-03-12","arxiv_id":"2503.09069","n_code_links":0,"syntology":null},{"paper":null,"slug":"tpdiff-temporal-pyramid-video-diffusion-model","title":"TPDiff: Temporal Pyramid Video Diffusion Model","date":"2025-03-12","arxiv_id":"2503.09566","n_code_links":0,"syntology":null},{"paper":"/paper/training-data-provenance-verification-did","slug":"training-data-provenance-verification-did","title":"Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?","date":"2025-03-12","arxiv_id":"2503.09122","n_code_links":1,"syntology":null},{"paper":"/paper/unicombine-unified-multi-conditional","slug":"unicombine-unified-multi-conditional","title":"UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer","date":"2025-03-12","arxiv_id":"2503.09277","n_code_links":0,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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) · 2 unverified","official":null}},{"paper":null,"slug":"adaptive-anomaly-recovery-for","title":"Adaptive Anomaly Recovery for Telemanipulation: A Diffusion Model Approach to Vision-Based Tracking","date":"2025-03-11","arxiv_id":"2503.09632","n_code_links":0,"syntology":null},{"paper":"/paper/aligning-text-to-image-in-diffusion-models-is","slug":"aligning-text-to-image-in-diffusion-models-is","title":"Aligning Text to Image in Diffusion Models is Easier Than You Think","date":"2025-03-11","arxiv_id":"2503.08250","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["softrepa/SoftREPA"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/anymole-any-character-motion-in-betweening","slug":"anymole-any-character-motion-in-betweening","title":"AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models","date":"2025-03-11","arxiv_id":"2503.08417","n_code_links":2,"syntology":null},{"paper":null,"slug":"bokeh-diffusion-defocus-blur-control-in-text","title":"Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models","date":"2025-03-11","arxiv_id":"2503.08434","n_code_links":0,"syntology":null},{"paper":null,"slug":"cdi3d-cross-guided-dense-view-interpolation","title":"CDI3D: Cross-guided Dense-view Interpolation for 3D Reconstruction","date":"2025-03-11","arxiv_id":"2503.08005","n_code_links":0,"syntology":null},{"paper":"/paper/controlling-latent-diffusion-using-latent","slug":"controlling-latent-diffusion-using-latent","title":"Controlling Latent Diffusion Using Latent CLIP","date":"2025-03-11","arxiv_id":"2503.08455","n_code_links":1,"syntology":null},{"paper":null,"slug":"d3po-preference-based-alignment-of-discrete","title":"D3PO: Preference-Based Alignment of Discrete Diffusion Models","date":"2025-03-11","arxiv_id":"2503.08295","n_code_links":0,"syntology":null},{"paper":null,"slug":"fp3-a-3d-foundation-policy-for-robotic","title":"FP3: A 3D Foundation Policy for Robotic Manipulation","date":"2025-03-11","arxiv_id":"2503.08950","n_code_links":0,"syntology":null},{"paper":null,"slug":"garmentcrafter-progressive-novel-view","title":"GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing","date":"2025-03-11","arxiv_id":"2503.08678","n_code_links":0,"syntology":null},{"paper":null,"slug":"generalizable-ai-generated-image-detection","title":"Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum","date":"2025-03-11","arxiv_id":"2503.08484","n_code_links":0,"syntology":null},{"paper":null,"slug":"high-quality-3d-head-reconstruction-from-any","title":"High-Quality 3D Head Reconstruction from Any Single Portrait Image","date":"2025-03-11","arxiv_id":"2503.08516","n_code_links":0,"syntology":null},{"paper":null,"slug":"layton-latent-consistency-tokenizer-for-1024","title":"Layton: Latent Consistency Tokenizer for 1024-pixel Image Reconstruction and Generation by 256 Tokens","date":"2025-03-11","arxiv_id":"2503.08377","n_code_links":0,"syntology":null},{"paper":"/paper/meat-multiview-diffusion-model-for-human","slug":"meat-multiview-diffusion-model-for-human","title":"MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention","date":"2025-03-11","arxiv_id":"2503.08664","n_code_links":1,"syntology":null},{"paper":"/paper/megasr-mining-customized-semantics-and","slug":"megasr-mining-customized-semantics-and","title":"MegaSR: Mining Customized Semantics and Expressive Guidance for Image Super-Resolution","date":"2025-03-11","arxiv_id":"2503.08096","n_code_links":1,"syntology":null},{"paper":null,"slug":"mf-viton-high-fidelity-mask-free-virtual-try","title":"MF-VITON: High-Fidelity Mask-Free Virtual Try-On with Minimal Input","date":"2025-03-11","arxiv_id":"2503.08650","n_code_links":0,"syntology":null},{"paper":null,"slug":"modular-customization-of-diffusion-models-via","title":"Modular Customization of Diffusion Models via Blockwise-Parameterized Low-Rank Adaptation","date":"2025-03-11","arxiv_id":"2503.08575","n_code_links":0,"syntology":null},{"paper":null,"slug":"mvd-hugas-human-gaussians-from-a-single-image","title":"MVD-HuGaS: Human Gaussians from a Single Image via 3D Human Multi-view Diffusion Prior","date":"2025-03-11","arxiv_id":"2503.08218","n_code_links":0,"syntology":null},{"paper":"/paper/nullface-training-free-localized-face","slug":"nullface-training-free-localized-face","title":"NullFace: Training-Free Localized Face Anonymization","date":"2025-03-11","arxiv_id":"2503.08478","n_code_links":1,"syntology":null},{"paper":"/paper/ominicontrol2-efficient-conditioning-for","slug":"ominicontrol2-efficient-conditioning-for","title":"OminiControl2: Efficient Conditioning for Diffusion Transformers","date":"2025-03-11","arxiv_id":"2503.08280","n_code_links":1,"syntology":null},{"paper":null,"slug":"omnipaint-mastering-object-oriented-editing","title":"OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting","date":"2025-03-11","arxiv_id":"2503.08677","n_code_links":0,"syntology":null},{"paper":null,"slug":"partial-differential-equation-system-for","title":"Partial differential equation system for binarization of degraded document images","date":"2025-03-11","arxiv_id":"2503.08017","n_code_links":0,"syntology":null},{"paper":null,"slug":"posterior-mean-denoising-diffusion-model-for","title":"Posterior-Mean Denoising Diffusion Model for Realistic PET Image Reconstruction","date":"2025-03-11","arxiv_id":"2503.08546","n_code_links":0,"syntology":null},{"paper":null,"slug":"preserving-product-fidelity-in-large-scale","title":"Preserving Product Fidelity in Large Scale Image Recontextualization with Diffusion Models","date":"2025-03-11","arxiv_id":"2503.08729","n_code_links":0,"syntology":null},{"paper":"/paper/principal-components-enable-a-new-language-of","slug":"principal-components-enable-a-new-language-of","title":"\"Principal Components\" Enable A New Language of Images","date":"2025-03-11","arxiv_id":"2503.08685","n_code_links":1,"syntology":{"ran":14,"of":17,"n_ran_checked":12,"n_instrument":2,"unverified":3,"pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 3 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["visual-gen/semanticist"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"reconstruct-anything-model-a-lightweight","title":"Reconstruct Anything Model: a lightweight foundation model for computational imaging","date":"2025-03-11","arxiv_id":"2503.08915","n_code_links":0,"syntology":null},{"paper":"/paper/representing-3d-shapes-with-64-latent-vectors","slug":"representing-3d-shapes-with-64-latent-vectors","title":"Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models","date":"2025-03-11","arxiv_id":"2503.08737","n_code_links":0,"syntology":{"ran":4,"of":9,"n_ran_checked":4,"n_instrument":0,"unverified":5,"pointer_only":9,"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) · 5 unverified","official":null}},{"paper":"/paper/rethinking-diffusion-model-in-high-dimension","slug":"rethinking-diffusion-model-in-high-dimension","title":"Rethinking Diffusion Model in High Dimension","date":"2025-03-11","arxiv_id":"2503.08643","n_code_links":1,"syntology":null},{"paper":"/paper/sas-segment-any-3d-scene-with-integrated-2d","slug":"sas-segment-any-3d-scene-with-integrated-2d","title":"SAS: Segment Any 3D Scene with Integrated 2D Priors","date":"2025-03-11","arxiv_id":"2503.08512","n_code_links":1,"syntology":null}],"record_sha256":"55c0ae953f85563708e4398c69caf59dceb93de9f75dcadb9c9702407b9da3a1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}