{"total":88,"rows":[{"id":"2406.02507","title":"Guiding a Diffusion Model with a Bad Version of Itself","created":"2024-06-04","cited_by_count":299,"area":"diffusion"},{"id":"2411.09502","title":"Golden Noise for Diffusion Models: A Learning Framework","created":"2024-11-14","cited_by_count":92,"area":"diffusion"},{"id":"2405.18407","title":"Phased Consistency Models","created":"2024-05-28","cited_by_count":85,"area":"diffusion"},{"id":"2408.00760","title":"Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention","created":"2024-08-01","cited_by_count":59,"area":"diffusion"},{"id":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"area":"diffusion"},{"id":"2407.02687","title":"No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models","created":"2024-07-02","cited_by_count":53,"area":"diffusion"},{"id":"2412.03895","title":"A Noise is Worth Diffusion Guidance","created":"2024-12-05","cited_by_count":49,"area":"diffusion"},{"id":"2508.12880","title":"Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models","created":"2025-08-18","cited_by_count":36,"area":"diffusion"},{"id":"2408.16333","title":"Self-Improving Diffusion Models with Synthetic Data","created":"2024-08-29","cited_by_count":35,"area":"diffusion"},{"id":"2411.18664","title":"Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling","created":"2024-11-27","cited_by_count":34,"area":"diffusion"},{"id":"2506.17220","title":"Emergent Temporal Correspondences from Video Diffusion Transformers","created":"2025-06-20","cited_by_count":31,"area":"diffusion"},{"id":"2509.18096","title":"Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers","created":"2025-09-22","cited_by_count":24,"area":"diffusion"},{"id":"2412.05827","title":"Self-Guidance: Boosting Flow and Diffusion Generation on Their Own","created":"2024-12-08","cited_by_count":23,"area":"diffusion"},{"id":"2505.11245","title":"Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models","created":"2025-05-16","cited_by_count":23,"area":"diffusion"},{"id":"2511.05563","title":"Lookahead Unmasking Elicits Accurate Decoding in Diffusion Language Models","created":"2025-11-04","cited_by_count":17,"area":"diffusion"},{"id":"2503.18137","title":"TCFG: Tangential Damping Classifier-free Guidance","created":"2025-03-23","cited_by_count":15,"area":"diffusion"},{"id":"2506.10036","title":"Token Perturbation Guidance for Diffusion Models","created":"2025-06-10","cited_by_count":15,"area":"diffusion"},{"id":"2505.21179","title":"Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models","created":"2025-05-27","cited_by_count":13,"area":"diffusion"},{"id":"2502.20126","title":"FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute","created":"2025-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2601.00090","title":"It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models","created":"2025-12-31","cited_by_count":11,"area":"diffusion"},{"id":"2512.03045","title":"CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2411.15393","title":"Gradient-Free Classifier Guidance for Diffusion Model Sampling","created":"2024-11-23","cited_by_count":8,"area":"diffusion"},{"id":"2503.20240","title":"Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models","created":"2025-03-26","cited_by_count":8,"area":"diffusion"},{"id":"2503.07677","title":"PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity","created":"2025-03-10","cited_by_count":7,"area":"diffusion"},{"id":"2504.12027","title":"Understanding Attention Mechanism in Video Diffusion Models","created":"2025-04-16","cited_by_count":7,"area":"diffusion"},{"id":"2508.00319","title":"Steering Guidance for Personalized Text-to-Image Diffusion Models","created":"2025-08-01","cited_by_count":7,"area":"diffusion"},{"id":"2510.11538","title":"Massive Activations are the Key to Local Detail Synthesis in Diffusion Transformers","created":"2025-10-13","cited_by_count":7,"area":"diffusion"},{"id":"2406.16695","title":"Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling","created":"2024-06-24","cited_by_count":6,"area":"diffusion"},{"id":"2409.07451","title":"FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising Process","created":"2024-09-11","cited_by_count":6,"area":"diffusion"},{"id":"2506.10978","title":"Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models","created":"2025-06-12","cited_by_count":6,"area":"diffusion"},{"id":"2602.18022","title":"Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers","created":"2026-02-20","cited_by_count":6,"area":"diffusion"},{"id":"2411.01212","title":"Infinite-Resolution Integral Noise Warping for Diffusion Models","created":"2024-11-02","cited_by_count":5,"area":"diffusion"},{"id":"2503.14505","title":"MusicInfuser: Making Video Diffusion Listen and Dance","created":"2025-03-18","cited_by_count":5,"area":"diffusion"},{"id":"2506.21452","title":"Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency","created":"2025-06-26","cited_by_count":5,"area":"diffusion"},{"id":"2502.08690","title":"Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation","created":"2025-02-12","cited_by_count":4,"area":"diffusion"},{"id":"2502.12579","title":"CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation","created":"2025-02-18","cited_by_count":4,"area":"diffusion"},{"id":"2602.22570","title":"Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation","created":"2026-02-26","cited_by_count":4,"area":"diffusion"},{"id":"2604.26503","title":"Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models","created":"2026-04-29","cited_by_count":4,"area":"diffusion"},{"id":"2510.07546","title":"PickStyle: Video-to-Video Style Transfer with Context-Style Adapters","created":"2025-10-08","cited_by_count":3,"area":"diffusion"},{"id":"2510.14526","title":"Noise Projection: Closing the Prompt-Agnostic Gap Behind Text-to-Image Misalignment in Diffusion Models","created":"2025-10-16","cited_by_count":3,"area":"diffusion"},{"id":"2604.08048","title":"Guiding a Diffusion Model by Swapping Its Tokens","created":"2026-04-09","cited_by_count":3,"area":"diffusion"},{"id":"2605.11494","title":"STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models","created":"2026-05-12","cited_by_count":3,"area":"diffusion"},{"id":"2502.03502","title":"DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior","created":"2025-02-05","cited_by_count":2,"area":"diffusion"},{"id":"2503.02577","title":"SPG: Improving Motion Diffusion by Smooth Perturbation Guidance","created":"2025-03-04","cited_by_count":2,"area":"diffusion"},{"id":"2509.09451","title":"Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation","created":"2025-09-11","cited_by_count":2,"area":"diffusion"},{"id":"2509.13936","title":"Noise-Level Diffusion Guidance: Well Begun is Half Done","created":"2025-09-17","cited_by_count":2,"area":"diffusion"},{"id":"2603.13419","title":"Diffusion Models Memorize in Training -- and Generalize in Inference","created":"2026-03-12","cited_by_count":2,"area":"diffusion"},{"id":"2603.21175","title":"Reward Sharpness-Aware Fine-Tuning for Diffusion Models","created":"2026-03-22","cited_by_count":2,"area":"diffusion"},{"id":"2605.28036","title":"Stay Fair! Ensuring Group Fairness in Diffusion Models Across Guidance Scales","created":"2026-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2606.03119","title":"GuidedBridge: Training-freely Improving Bridge Models with Prior Guidance","created":"2026-06-02","cited_by_count":2,"area":"diffusion"},{"id":"2609.36014","title":"Persistence Forcing: Exploiting Feature Specialization in Pixel-Space Diffusion","created":"2026-09-28","cited_by_count":2,"area":"diffusion"},{"id":"2506.13594","title":"Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching","created":"2025-06-16","cited_by_count":1,"area":"diffusion"},{"id":"2506.21045","title":"Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling","created":"2025-06-26","cited_by_count":1,"area":"diffusion"},{"id":"2509.23708","title":"CrimEdit: Controllable Editing for Counterfactual Object Removal, Insertion, and Movement","created":"2025-09-28","cited_by_count":1,"area":"diffusion"},{"id":"2601.01608","title":"Guiding Token-Sparse Diffusion Models","created":"2026-01-04","cited_by_count":1,"area":"diffusion"},{"id":"2603.14320","title":"Early Failure Detection and Intervention in Video Diffusion Models","created":"2026-03-15","cited_by_count":1,"area":"diffusion"},{"id":"2603.20584","title":"Improving Diffusion Generalization with Weak-to-Strong Segmented Guidance","created":"2026-03-21","cited_by_count":1,"area":"diffusion"},{"id":"2607.17972","title":"DiFA: Inference-Time Forward-Process Alignment for Diffusion Models","created":"2026-07-20","cited_by_count":1,"area":"diffusion"},{"id":"2411.17077","title":"ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts","created":"2024-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2411.17769","title":"Omegance: A Single Parameter for Various Granularities in Diffusion-Based Synthesis","created":"2024-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2505.20935","title":"ISAC: Training-Free Instance-to-Semantic Attention Control for Multi-Instance Generation","created":"2025-05-27","cited_by_count":0,"area":"diffusion"},{"id":"2508.11476","title":"SPG: Style-Prompting Guidance for Style-Specific Content Creation","created":"2025-08-15","cited_by_count":0,"area":"diffusion"},{"id":"2509.06499","title":"TIDE: Achieving Balanced Subject-Driven Image Generation via Target-Instructed Diffusion Enhancement","created":"2025-09-08","cited_by_count":0,"area":"diffusion"},{"id":"2510.04533","title":"TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling","created":"2025-10-06","cited_by_count":0,"area":"diffusion"},{"id":"2510.12954","title":"CADE 2.5 - ZeResFDG: Frequency-Decoupled, Rescaled and Zero-Projected Guidance for SD/SDXL Latent Diffusion Models","created":"2025-10-14","cited_by_count":0,"area":"diffusion"},{"id":"2511.21415","title":"DiverseVAR: Balancing Diversity and Quality of Next-Scale Visual Autoregressive Models","created":"2025-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2511.21863","title":"Saddle-Free Guidance: Improved On-Manifold Sampling without Labels or Additional Training","created":"2025-11-26","cited_by_count":0,"area":"diffusion"},{"id":"2511.22991","title":"Guiding Visual Autoregressive Models through Spectrum Weakening","created":"2025-11-28","cited_by_count":0,"area":"diffusion"},{"id":"2512.13690","title":"DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders","created":"2025-12-15","cited_by_count":0,"area":"diffusion"},{"id":"2512.17303","title":"EMAG: Self-Rectifying Diffusion Sampling with Exponential Moving Average Guidance","created":"2025-12-19","cited_by_count":0,"area":"diffusion"},{"id":"2601.14788","title":"Reconstruction-Anchored Diffusion Model for Text-to-Motion Generation","created":"2026-01-21","cited_by_count":0,"area":"diffusion"},{"id":"2602.09268","title":"Rethinking Global Text Conditioning in Diffusion Transformers","created":"2026-02-09","cited_by_count":0,"area":"diffusion"},{"id":"2603.02531","title":"Geometry-Aware Attention Guidance for Diffusion Models via Modern Hopfield Dynamics","created":"2026-03-03","cited_by_count":0,"area":"diffusion"},{"id":"2603.10780","title":"Guiding Diffusion Models with Semantically Degraded Conditions","created":"2026-03-11","cited_by_count":0,"area":"diffusion"},{"id":"2605.14135","title":"PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting","created":"2026-05-13","cited_by_count":0,"area":"diffusion"},{"id":"2605.17980","title":"Learning to Balance: Decoupled Siamese Diffusion Transformer for Reference-Based Remote Sensing Image Super-Resolution","created":"2026-05-18","cited_by_count":0,"area":"diffusion"},{"id":"2605.31162","title":"Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2607.00647","title":"Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold","created":"2026-07-01","cited_by_count":0,"area":"diffusion"},{"id":"2607.02968","title":"Awakening Diffusion Transformers: Eliciting Stronger Generation and Understanding via Massive Activation Modulation","created":"2026-07-03","cited_by_count":0,"area":"diffusion"},{"id":"2607.03256","title":"A Decomposable Probe for Few-Step Diffusion Models: Prompt, Latent, and Score Selectivity across Backbone Families and Distillation Paradigms","created":"2026-07-03","cited_by_count":0,"area":"diffusion"},{"id":"2607.09753","title":"Unified Backbone Refinement for Diffusion Models via Internal-Latent Analysis","created":"2026-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2608.14172","title":"Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation","created":"2026-08-14","cited_by_count":0,"area":"diffusion"},{"id":"2608.16786","title":"Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models","created":"2026-08-17","cited_by_count":0,"area":"diffusion"},{"id":"2609.34525","title":"SAGE: Subspace Alignment for Classifier-Free Guidance in Mixture-of-Experts Diffusion Models","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.38819","title":"Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.02372","title":"Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion","created":"2026-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2610.13941","title":"Images Talk Back: Guiding MMDiTs by Suppressing Image-to-Text Feedback","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.14136","title":"Correction Training for Diffusion Models","created":"2026-10-09","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}