README.md

awesome-diffusion-iclr-2025

List of diffusion related active submissions on OpenReview for ICLR 2025.

Content

• 3D Diffusion
• Personalized T2I
• Super-Resolution
• Concept Eraser
• Adversarial Diffusion
• Video Generation
• Distilled Learning

3D Diffusion

• Bootstrap3D: Improving Multi-view Diffusion Model with Synthetic Data [PDF]
• InfiniteMesh: View Interpolation using Multi-view Diffusion for 3D Mesh Reconstruction [PDF]
• Consistency Diffusion Models for Singel-Image 3D Reconstruction with priors [PDF]
• Wavelet Latent Diffusion (WaLa): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings [PDF]
• 3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation [PDF]
• Generalizable Monocular 3D Human Rendering via Direct Gaussian Attribute Diffusion [PDF]
• HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model [PDF]
• ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors [PDF]
• HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models [PDF]
• NEXT-MOL: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation [PDF]
• SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation [PDF]
• PSHead: 3D Head Reconstruction from a Single Image with Diffusion Prior and Self-Enhancement [PDF]
• MVLight: Relightable Text-to-3D Generation via Light-conditioned Multi-View Diffusion [PDF]
• Build your own cell: Diffusion Models for Multichannel 3D Microscopy Image Generation [PDF]
• Atlas Gaussians Diffusion for 3D Generation [PDF]
• Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models [PDF]
• DSPart: A Large-scale Diffusion-generated Synthetic Dataset with Annotations from 3D Parts [PDF]
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control [PDF]
• Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion [PDF]
• Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion [PDF]
• Boost 3D Reconstruction using Diffusion-based Intrinsic Estimation [PDF]
• 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion [PDF]
• 3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance [PDF]
• Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation [PDF]
• ZERO-1-to-G: Taming Pretrained 2D Diffusion Models for Direct 3D Generation [PDF]
• GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation [PDF]
• VFDiff: SE(3)-Equivariant Vector Field Guided Diffusion Model for Target-Aware Molecule Generation in 3D [PDF]
• LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion [PDF]
• X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models [PDF]
• A3D: Does Diffusion Dream about 3D Alignment? [PDF]
• Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation [PDF]
• GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting [PDF]
• EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing [PDF]
• Diffusion priors for Bayesian 3D reconstruction from incomplete measurements [PDF]
• DC3DO: Diffusion Classifier for 3D Objects [PDF]
• GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation [PDF]
• Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion [PDF]
• LISA: UNLEASHING 2D DIFFUSION FOR 3D GENERATION VIA LIGHTWEIGHT IMAGE SPLATS ADAPTATION [PDF]

Video Generation

• Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos [PDF]
• Self-Conditioned Diffusion Model for Consistent Human Image and Video Synthesis [PDF]
• ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning [PDF]
• Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention [PDF]
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control [PDF]
• Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion [PDF]
• ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation [PDF]
• FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality [PDF]
• FreeTraj: Tuning-Free Trajectory Control via Noise Guided Video Diffusion [PDF]
• MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling [PDF]
• Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [PDF]
• VideoPanda: Video Panoramic Diffusion With Multi-view Attention [PDF]
• Promptus: Representing Real-World Video as Stable Diffusion Prompts for Video Streaming [PDF]
• MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion [PDF]
• Boosting Camera Motion Control for Video Diffusion Transformers [PDF]
• UniVAE: A Unified Frame-Enriched Video VAE for Latent Video Diffusion Models [PDF]
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [PDF]
• TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation [PDF]
• HERO: Harnessing Temporal Modeling for Diffusion-Based Video Outpainting [PDF]
• ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler [PDF]
• Training-free Long Video Generation with Chain of Diffusion Model Experts [PDF]
• VideoDiT: Bridging Image Diffusion Transformers for Streamlined Video Generation [PDF]
• Video Diffusion Models Learn the Structure of the Dynamic World [PDF]
• VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide [PDF]
• Camera Pose Estimation Emerging In Video Diffusion Transformer [PDF]
• Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models [PDF]
• Improved Video VAE for Latent Video Diffusion Model [PDF]
• Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile [PDF]
• Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation [PDF]
• Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models [PDF]
• Zero-shot Novel View Synthesis via Adaptive Modulating Video Diffusion Process [PDF]
• A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation [PDF]
• VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking [PDF]
• State & Image Guidance: Teaching Old Text-to-Video Diffusion Models New Tricks [PDF]
• Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach [PDF]
• ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation [PDF]
• Progressive Autoregressive Video Diffusion Models [PDF]
• DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation [PDF]
• MarDini: Masked Autoregressive Diffusion for Video Generation at Scale [PDF]
• The Blessing of Smooth Initialization for Video Diffusion Models [PDF]
• ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model [PDF]
• Semantically Consistent Video Inpainting with Conditional Diffusion Models [PDF]
• Emerging Tracking from Video Diffusion [PDF]
• Solving Video Inverse Problems Using Image Diffusion Models [PDF]
• VADER: Video Diffusion Alignment via Reward Gradients [PDF]
• CamI2V: Camera-Controlled Image-to-Video Diffusion Model [PDF]
• AVID: Adapting Video Diffusion Models to World Models [PDF]
• Investigating Memorization in Video Diffusion Models [PDF]
• DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models [PDF]
• IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis [PDF]
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer [PDF]
• Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos [PDF]
• Self-Conditioned Diffusion Model for Consistent Human Image and Video Synthesis [PDF]
• ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning [PDF]
• Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention [PDF]
• Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models [PDF]
• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control [PDF]
• Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion [PDF]
• ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation [PDF]

Personalized T2I

• MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models [PDF]
• DreamMakeup: Face Makeup Customization using Latent Diffusion Models [PDF]
• Revealing the Unseen: Guiding Personalized Diffusion Models to Expose Training Data [PDF]
• Rethinking and Defending Protective Perturbation in Personalized Diffusion Models [PDF]
• FedBiP: Heterogeneous One-Shot Federated Learning with Personalized Latent Diffusion Models [PDF]
• Object Fusion via Diffusion Time-step for Customized Image Editing with Single Example [PDF]
• Receptor-Specific Diffusion Model: Towards Generating Protein-Protein Structures with Customized Perturbing and Sampling [PDF]
• Learning to Customize Text-to-Image Diffusion In Diverse Context [PDF]
• TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation [PDF]
• LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models [PDF]

Super-Resolution

• One Step Diffusion-based Super-Resolution with Time-Aware Distillation [PDF]
• FedSR: Frequency-Aware Enhancement for Diffusion-based Image Super-Resolution [PDF]
• Image Super-Resolution with Text Prompt Diffusion [PDF]

Concept Eraser

• Optimal Targets for Concept Erasure in Diffusion Models and Where To Find Them [PDF]
• Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate [PDF]
• Prompt-Agnostic Erasure for Diffusion Models Using Task Vectors [PDF]
• EraseDiff: Erasing Data Influence in Diffusion Models [PDF]
• Erasing Combination from Text-to-Image Diffusion Model [PDF]

Adversarial Diffusion

• Diffusion Guided Adversarial State Perturbations in Reinforcement Learning [PDF]
• AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models [PDF]
• Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting [PDF]
• How and how well do diffusion models improve adversarial robustness? [PDF]
• Improved Diffusion-based Generative Model with Better Adversarial Robustness [PDF]
• Breaking Free: Hacking Diffusion Models for Generating Adversarial Examples and Bypassing Safety Guardrails [PDF]
• AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation [PDF]
• Adversarial Guided Diffusion Models for Adversarial Purification [PDF]
• Adversarial Diffusion Bridge Model for Reliable Adversarial Purification [PDF]
• Sample-specific Noise Injection for Diffusion-based Adversarial Purification [PDF]
• Rethinking Adversarial Attacks as Protection Against Diffusion-based Mimicry [PDF]
• Efficient Adversarial Detection and Purification with Diffusion Models [PDF]
• Adversarial-Guided Diffusion for Robust and High-Fidelity Multimodal LLM Attacks [PDF]

Distilled Learning

• CONCORD: -informed Diffusion for Dataset Distillation [PDF]
• Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models [PDF]
• Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution [PDF]
• Skip the Steps: Data-Free Consistency Distillation for Diffusion-based Samplers [PDF]
• Secure Diffusion Model Unlocked: Efficient Inference via Score Distillation [PDF]
• Influence-Guided Diffusion for Dataset Distillation [PDF]
• Amortized Posterior Sampling with Diffusion Prior Distillation [PDF]
• InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation [PDF]
• Fast Multi-Mode Adaptive Generative Distillation for Continually Learning Diffusion Models [PDF]
• MGD3: Mode-Guided Dataset Distillation using Diffusion Models [PDF]
• One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation [PDF]
• Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation [PDF]
• DDIL: Improved Diffusion Distillation with Imitation Learning [PDF]
• Multi-Student Diffusion Distillation for Better One-Step Generators [PDF]

---

• Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models [PDF]

• AQUATIC-Diff: Additive Quantization for Truly Tiny Compressed Diffusion Models [PDF]

• Diffusion-PINN Sampler [PDF]

• Offline Reinforcement Learning with Closed-loop Policy Evaluation and Diffusion World-Model Adaptation [PDF]

• SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation [PDF]

• Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data [PDF]

• From Abstract Noise to Architectural Form: Designing Diffusion Models for Efficient Floor Plan Generation [PDF]

• KnobGen: Controlling the Sophistication of Artwork in Sketch-Based Diffusion Models [PDF]

• Diffusion Bridge Implicit Models [PDF]

• Precise Parameter Localization for Textual Generation in Diffusion Models [PDF]

• Improved Sampling Algorithms for Lévy-Itô Diffusion Models [PDF]

• Improving Diffusion-based Data Augmentation with Inversion Circle Interpolation [PDF]

• Dreamguider: Improved Training free Diffusion-based Conditional Generation [PDF]

• TabDiff: a Multi-Modal Diffusion Model for Tabular Data Generation [PDF]

• Fast constrained sampling in pre-trained diffusion models [PDF]

• Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models [PDF]

• A Study of Posterior Stability for Time-Series Latent Diffusion [PDF]

• Diffusion Actor-Critic: Formulating Constrained Policy Iteration as Diffusion Noise Regression for Offline Reinforcement Learning [PDF]

• Improved Video VAE for Latent Video Diffusion Model [PDF]

• Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling [PDF]

• ParaSolver: A Hierarchical Parallel Integral Solver for Diffusion Models [PDF]

• Pose-guided Motion Diffusion Model for Text-to-motion Generation [PDF]

• Energy-Based ual Diffusion Model [PDF]

• Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task [PDF]

• Discrete Diffusion Schrödinger Bridge Matching for Graph Transformation [PDF]

• DiffPath: Generating Road Network based Path with Latent Diffusion Model [PDF]

• PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion [PDF]

• Training-Free Diffusion Model Alignment with Sampling Demons [PDF]

• Diffusion Modulation via Environment Mechanism Modeling for Planning [PDF]

• Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models [PDF]

• Instant Policy: In-Context Imitation Learning via Graph Diffusion [PDF]

• Denoising Diffusion Causal Discovery [PDF]

• StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces [PDF]

• Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling [PDF]

• The Deficit of New Information in Diffusion Models: A Focus on Diverse Samples [PDF]

• Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis [PDF]

• Latent Diffusion with LLMs for Reasoning [PDF]

• The Geometry of Phase Transitions in Diffusion Models: Tubular Neighbourhoods and Singularities [PDF]

• Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better [PDF]

• Warm Diffusion: Recipe for Blur-Noise Mixture Diffusion Models [PDF]

• How Discrete and Continuous Diffusion Meet: Comprehensive Analysis of Discrete Diffusion Models via a Stochastic Integral Framework [PDF]

• Discrete Inversion: A Controllable Latent Space for Multinomial Diffusion and Masked Generative Models [PDF]

• Temporal Environment-Aware Image Generation via Latent Diffusion [PDF]

• Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements [PDF]

• Data Unlearning in Diffusion Models [PDF]

• Single-Step Diffusion Model-Based Generative Model Inversion Attacks [PDF]

• Efficient-vDiT: Efficient Video Diffusion Transformers With Attention Tile [PDF]

• Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation [PDF]

• Implicit Search via Discrete Diffusion: A Study on Chess [PDF]

• Diffusion Process with Implicit Latents via Energy Models [PDF]

• DiffuSolve: Diffusion-Based Solver for Non-Convex Trajectory Optimization [PDF]

• Semantic-Aware Diffusion Model for Sequential Recommendation [PDF]

• A Unified Framework for Hierarchical Diffusion via Simplicial Complexes [PDF]

• FullDiffusion: Diffusion Models Without Time Truncation [PDF]

• Can Diffusion Models Disentangle? A Theoretical Perspective [PDF]

• Δ-DiT: Accelerating Diffusion Transformers without training via Denoising Property Alignment [PDF]

• Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models [PDF]

• Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior [PDF]

• Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costs [PDF]

• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation [PDF]

• LDMol: Text-to-Molecule Diffusion Model with Structurally Informative Latent Space [PDF]

• DiffVAS: Diffusion-Guided Visual Active Search in Partially Observable Environments [PDF]

• Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models [PDF]

• Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion [PDF]

• Diff-Prompt: Diffusion-driven Prompt Generator with Mask Supervision [PDF]

• Multidimensional Trajectory Optimization for Flow and Diffusion [PDF]

• Zero-Order Diffusion Guidance for Inverse Problems [PDF]

• ProtPainter: Draw or Drag Protein via Topology-guided Diffusion [PDF]

• Zero-Shot Video Semantic Segmentation based on Pre-Trained Diffusion Models [PDF]

• Risk-Sensitive Diffusion: Robustly Optimizing Diffusion Models with Noisy Samples [PDF]

• TimeAutoDiff: Generation of Heterogeneous Time Series Data via Latent Diffusion Model [PDF]

• SimDiffPDE: Simple Diffusion Baselines for Solving Partial Differential Equations [PDF]

• Zero-shot Novel View Synthesis via Adaptive Modulating Video Diffusion Process [PDF]

• Provable Causal State Representation under Asynchronous Diffusion Model for POMDPs [PDF]

• SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings [PDF]

• Self-Supervised Diffusion Processes for Electron-Aware Molecular Representation Learning [PDF]

• ProFI-Painter: Text-Guided Prompt-Faithful Image Inpainting with Diffusion Models [PDF]

• What Makes a Good Diffusion Planner for Decision Making? [PDF]

• ContraFusion: Contrastively Improving Compositional Understanding in Diffusion Models via Fine-Grained Negative Images [PDF]

• MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models [PDF]

• De-biasing Diffusion: Data-Free FP8 Quantization of Text-to-Image Models with Billions of Parameters [PDF]

• Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variations [PDF]

• Diffusion On Syntax Trees For Program Synthesis [PDF]

• NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Models [PDF]

• FROM LOW TO HIGH-VALUE DESIGNS: OFFLINE OPTIMIZATION VIA GENERALIZED DIFFUSION [PDF]

• Exploring the Design Space of Diffusion Bridge Models via Stochasticity Control [PDF]

• Highlight Diffusion: Training-Free Attention Guided Acceleration for Text-to-Image Models [PDF]

• Diffusion Pretraining for Gait Recognition in the Wild [PDF]

• StyleMaster: Towards Flexible Stylized Image Generation with Diffusion Models [PDF]

• Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design [PDF]

• SafeDiffuser: Safe Planning with Diffusion Probabilistic Models [PDF]

• Choose Your Anchor Wisely: Effective Unlearning Diffusion Models via Reconditioning [PDF]

• DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing [PDF]

• A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation [PDF]

• Diffusion Attribution Score: Which Training Sample Determines Your Generation? [PDF]

• VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking [PDF]

• Diffusion State-Guided Projected Gradient for Inverse Problems [PDF]

• Synthesizing Realistic fMRI: A Physiological Dynamics-Driven Hierarchical Diffusion Model for Efficient fMRI Acquisition [PDF]

• Generation and Comprehension Hand-in-Hand: Vision-guided Expression Diffusion for Boosting Referring Expression Generation and Comprehension [PDF]

• Prompt Diffusion Robustifies Any-Modality Prompt Learning [PDF]

• Discovery and Expansion of New Domains within Diffusion Models [PDF]

• Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel [PDF]

• Hierarchical Protein Backbone Generation with Latent and Structure Diffusion [PDF]

• Data Exfiltration in Diffusion Models: A Backdoor Attack Approach [PDF]

• I2AM: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps [PDF]

• State & Image Guidance: Teaching Old Text-to-Video Diffusion Models New Tricks [PDF]

• Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias [PDF]

• PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation [PDF]

• TimeStep Master: Asymmetrical Mixture of Timestep LoRA Experts for Versatile and Efficient Diffusion Models in Vision [PDF]

• Anti-Exposure Bias in Diffusion Models via Prompt Learning [PDF]

• GUNet: A Graph Convolutional Network United Diffusion Model for Stable and Diversity Pose Generation [PDF]

• Diffusion-based Prompt Generation for Lifelong Continual Adaptation [PDF]

• LeFusion: Controllable Pathology Synthesis via Lesion-Focused Diffusion Models [PDF]

• Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach [PDF]

• Hierarchical Classification via Diffusion on Manifolds [PDF]

• From Patches to Graphs: Towards Image Diffusion Models with GNNs [PDF]

• ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation [PDF]

• AP-LDM: Attentive and Progressive Latent Diffusion Model for Training-Free High-Resolution Image Generation [PDF]

• AudioMorphix: Training-free audio editing with diffusion probabilistic models [PDF]

• Heavy-Tailed Diffusion Models [PDF]

• Deconstructing Denoising Diffusion Models for Self-Supervised Learning [PDF]

• Improving Discrete Diffusion with Schedule-Conditioning [PDF]

• CatVTON: Concatenation Is All You Need for Virtual Try-On with Diffusion Models [PDF]

• The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise [PDF]

• TF-score: Time-series Forecasting using score-based diffusion model [PDF]

• Continuous Speech Synthesis using per-token Latent Diffusion [PDF]

• Efficient Multi-agent Offline Coordination via Diffusion-based Trajectory Stitching [PDF]

• Understanding and Mitigating Memorization in Diffusion Models for Tabular Data [PDF]

• Morse: Fast Sampling for Accelerating Diffusion Models Universally [PDF]

• MoDiff: a Protein Diffusion Model for Multi-motif Scaffolding Problem [PDF]

• BinaryDM: Accurate Weight Binarization for Efficient Diffusion Models [PDF]

• MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance [PDF]

• Longitudinal Latent Diffusion Models [PDF]

• Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering [PDF]

• Unleashing the Potential of Diffusion Models for Incomplete Data Imputation [PDF]

• Learning Conditionally Independent Marginals Enables Logical Compositions in Conditional Diffusion Models [PDF]

• Targeted Attack Improves Protection against Unauthorized Diffusion Customization [PDF]

• Progressive Autoregressive Video Diffusion Models [PDF]

• Model Collapse in the Chain of Diffusion Finetuning: A Novel Perspective from Quantitative Trait Modeling [PDF]

• Periodic Materials Generation using Text-Guided Joint Diffusion Model [PDF]

• Sparse-to-Sparse Training of Diffusion Models [PDF]

• Seeing the Unseen: How EMoE Unveils Bias in Text-to-Image Diffusion Models [PDF]

• Zero-Shot Image Compression with Diffusion-Based Posterior Sampling [PDF]

• DiTTo-TTS: Diffusion Transformers for Scalable Text-to-Speech without Domain-Specific Factors [PDF]

• HouseCrafter: Lifting Floorplans to 3D Scenes with 2D Diffusion Model [PDF]

• CONCORD: -informed Diffusion for Dataset Distillation [PDF]

• AccCtr: Accelerating Training-Free Control For Text-to-Image Diffusion Models [PDF]

• Fragment-Augmented Diffusion for Molecular Conformation Generation [PDF]

• DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation [PDF]

• Chemistry-Inspired Diffusion with Non-Differentiable Guidance [PDF]

• MarDini: Masked Autoregressive Diffusion for Video Generation at Scale [PDF]

• Diffusion Models Meet Contextual Bandits [PDF]

• Diffusion Models for 4D Novel View Synthesis [PDF]

• Unlocking Guidance for Discrete State-Space Diffusion and Flow Models [PDF]

• Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models [PDF]

• ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors [PDF]

• DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models [PDF]

• EDM2+: Exploring Efficient Diffusion Model Architectures for Visual Generation [PDF]

• Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model [PDF]

• Diffusion Bridge AutoEncoders for Unsupervised Representation Learning [PDF]

• HOI-Diff: Text-Driven Synthesis of 3D Human-Object Interactions using Diffusion Models [PDF]

• OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models [PDF]

• Efficient Scaling of Diffusion Transformers for Text-to-Image Generation [PDF]

• BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers [PDF]

• Accelerated Diffusion using Closed-form Discriminator Guidance [PDF]

• Probing the Latent Hierarchical Structure of Data via Diffusion Models [PDF]

• Latent Weight Diffusion: Generating policies from trajectories [PDF]

• PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction [PDF]

• Towards Building Reliable Conditional Diffusion Models for Protein Generation [PDF]

• The Blessing of Smooth Initialization for Video Diffusion Models [PDF]

• Dual Caption Preference Optimization for Diffusion Models [PDF]

• ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model [PDF]

• Stochastic Diffusion: A Diffusion Based Model for Stochastic Time Series Forecasting [PDF]

• Wavelet Diffusion Neural Operator [PDF]

• SymmCD: Symmetry-Preserving Crystal Generation with Diffusion Models [PDF]

• High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity [PDF]

• Characterizing the Training Dynamics of Private Fine-tuning with Langevin Diffusion [PDF]

• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [PDF]

• Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion [PDF]

• Towards a Theoretical Understanding of Memorization in Diffusion Models [PDF]

• GUIDE: Guidance-based Incremental Learning with Diffusion Models [PDF]

• RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning [PDF]

• CausalDiffusion: Causally Related Time-Series Generation through Diffusion Models [PDF]

• Certified Robustness to Clean-label Poisoning Using Diffusion Denoising [PDF]

• Advancing Graph Generation through Beta Diffusion [PDF]

• LocDiffusion: Identifying Locations on Earth by Diffusing in the Hilbert Space [PDF]

• Semantically Consistent Video Inpainting with Conditional Diffusion Models [PDF]

• Closed-loop Diffusion Control of Complex Physical Systems [PDF]

• Uncertainty-Aware PPG-2-ECG for Enhanced Cardiovascular Diagnosis using Diffusion Models [PDF]

• Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models [PDF]

• BAYESIAN EXPERIMENTAL DESIGN VIA CONTRASTIVE DIFFUSIONS [PDF]

• DC-DPM: A Divide-and-Conquer Approach for Diffusion Reverse Process [PDF]

• SymDiff: Equivariant Diffusion via Stochastic Symmetrisation [PDF]

• Dark Miner: Defend against unsafe generation for text-to-image diffusion models [PDF]

• Scaling Diffusion Models for Downstream Prediction [PDF]

• DiffDeID: a Multi-conditional Diffusion-based Method for High Fidelity Face De-indentification with Diversity [PDF]

• ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge [PDF]

• EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation [PDF]

• Adding Conditional Control to Diffusion Models with Reinforcement Learning [PDF]

• FairGen: controlling fair generations in diffusion models via adaptive latent guidance [PDF]

• NEXT-MOL: 3D Diffusion Meets 1D Language Modeling for 3D Molecule Generation [PDF]

• Diff-BBO: Diffusion-Based Inverse Modeling for Black-Box Optimization [PDF]

• DreamDistribution: Prompt Distribution Learning for Text-to-Image Diffusion Models [PDF]

• Causally Motivated Diffusion Sampling Frameworks for Harnessing Contextual Bias [PDF]

• How Much is a Noisy Image Worth? Data Scaling Laws for Ambient Diffusion. [PDF]

• Emerging Tracking from Video Diffusion [PDF]

• DiffGS: Repurposing Image Diffusion Models for Scalable Gaussian Splatting Generation [PDF]

• Solving Video Inverse Problems Using Image Diffusion Models [PDF]

• VADER: Video Diffusion Alignment via Reward Gradients [PDF]

• Generalization through variance: how noise shapes inductive biases in diffusion models [PDF]

• Distillation-Free One-Step Diffusion for Real-World Image Super-Resolution [PDF]

• On the onset of memorization to generalization transition in diffusion models [PDF]

• Accelerate High-Quality Diffusion Models with Inner Loop Feedback [PDF]

• Inpainting the Sinogram from Computed Tomography using Latent Diffusion Model and Physics [PDF]

• First-Step Inference in Diffusion Models Learns Image De-whitening [PDF]

• SADE: a Scene-text Autoregressive Diffusion Engine for Character Sequence Recognition [PDF]

• Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models [PDF]

• DLPO: Diffusion Model Loss-Guided Reinforcement Learning for Fine-Tuning Text-to-Speech Diffusion Models [PDF]

• Diffusion Active Learning: Towards Data-Driven Experimental Design in Computed Tomography [PDF]

• HuMouS: Human Motion Synthesis with Fine-Grained Control using Latent Space Manipulation of Cycle-Consistent Diffusion Models [PDF]

• Graffe: Graph Representation Learning Enabled via Diffusion Probabilistic Models [PDF]

• Meta-weighted Diffusion Model for Reliable Online Surgical Phase Recognition [PDF]

• CamI2V: Camera-Controlled Image-to-Video Diffusion Model [PDF]

• No MCMC Teaching For me: Learning Energy-Based Models via Diffusion Synergy [PDF]

• Training-free guidance of diffusion models for generalised inpainting [PDF]

• HDDI: A Historical Data-Based Diffusion Imputation Method for High-Accuracy Recovery in Multivariate Time Series with High Missing Rate and Long-Term Gap [PDF]

• Blind Inversion using Latent Diffusion Priors [PDF]

• On the Relation Between Linear Diffusion and Power Iteration [PDF]

• Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers [PDF]

• T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching [PDF]

• Preference Diffusion for Recommendation [PDF]

• Co-Representation Neural Hypergraph Diffusion for Edge-Dependent Node Classification [PDF]

• Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles [PDF]

• CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion [PDF]

• Singular Subspace Perturbation Bounds via Rectangular Random Matrix Diffusions [PDF]

• Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions [PDF]

• AVID: Adapting Video Diffusion Models to World Models [PDF]

• Signal Dynamics in Diffusion Models: Enhancing Text-to-Image Alignment through Step Selection [PDF]

• Investigating Memorization in Video Diffusion Models [PDF]

• Learned Reference-based Diffusion Sampler for multi-modal distributions [PDF]

• Constant Rate Schedule: Constant-Rate Distributional Change for Efficient Training and Sampling in Diffusion Models [PDF]

• From Noise to Factors: Diffusion-based Unsupervised Sequential Disentanglement [PDF]

• Diffusion-Guided Safe Policy Optimization From Cost-Label-Free Offline Dataset [PDF]

• Dynamic Negative Guidance of Diffusion Models [PDF]

• SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generation [PDF]

• Skip the Steps: Data-Free Consistency Distillation for Diffusion-based Samplers [PDF]

• Improving Long-Text Alignment for Text-to-Image Diffusion Models [PDF]

• O(d/T) Convergence Theory for Diffusion Probabilistic Models under Minimal Assumptions [PDF]

• Pixel-Space Post-Training of Latent-Diffusion Models [PDF]

• Spectral Compressive Imaging via Unmixing-driven Subspace Diffusion Refinement [PDF]

• You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs [PDF]

• Distilled Diffusion Language Models [PDF]

• AutoLoRA: AutoGuidance Meets Low-Rank Adaptation for Diffusion Models [PDF]

• Scaling Laws for Diffusion Transformers [PDF]

• Regularization by Texts for Latent Diffusion Inverse Solvers [PDF]

• Latent Abstractions in Generative Diffusion Models [PDF]

• Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data [PDF]

• Diffusion-Nested Auto-Regressive Synthesis of Heterogeneous Tabular Data [PDF]

• Secure Diffusion Model Unlocked: Efficient Inference via Score Distillation [PDF]

• Improving Source Extraction with Diffusion and Consistency Models [PDF]

• FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models [PDF]

• BRIDGE: Bootstrapping Text to Guide Time-Series Generation via Multi-Agent Iterative Optimisation and Diffusion Modelling [PDF]

• DiffMove: Human Trajectory Recovery via Conditional Diffusion Model [PDF]

• An Efficient Framework for Crediting Data Contributors of Diffusion Models [PDF]

• Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models [PDF]

• Scaling Diffusion Language Models via Adaptation from Autoregressive Models [PDF]

• Zigzag Diffusion Sampling: The Path to Success ls Zigzag [PDF]

• Text-to-Model: Text-Conditioned Neural Network Diffusion for Train-Once-for-All Personalization [PDF]

• Diffusion-Based Planning for Autonomous Driving with Flexible Guidance [PDF]

• Diffusion Transformers for Tabular Data Time Series Generation [PDF]

• Understanding Diffusion-based Representation Learning via Low-Dimensional Modeling [PDF]

• DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models [PDF]

• Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction [PDF]

• IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis [PDF]

• One Model to Train Them All: A Unified Diffusion Framework for Multi-Context Neural Population Forecasting [PDF]

• Representative Guidance: Diffusion Model Sampling with Consistency [PDF]

• Rectified Diffusion Guidance for Conditional Generation [PDF]

• D3PM: Diffusion Model Responds to the Duty Call from Causal Discovery [PDF]

• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [PDF]

• A Diffusion-based Generative Approach for Model-free Finite-time Control of Complex Systems [PDF]

• Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation [PDF]

• A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training [PDF]

• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer [PDF]

• CoDiCast: Conditional Diffusion Model for Weather Prediction with Uncertainty Quantification [PDF]

• Think while You Generate: Discrete Diffusion with Planned Denoising [PDF]

• Diffusion Models are Evolutionary Algorithms [PDF]

• Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction [PDF]

• Generating Synthetic Genotypes using Diffusion Models [PDF]

• Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers [PDF]

• Scalable Diffusion for Bio-topological Representation Learning on Brain Graphs [PDF]

• Inference-Time Alignment of Diffusion Models with Direct Noise Optimization [PDF]

• Dual-Model Defense: Safeguarding Diffusion Models from Membership Inference Attacks through Disjoint Data Splitting [PDF]

• PSHead: 3D Head Reconstruction from a Single Image with Diffusion Prior and Self-Enhancement [PDF]

• Diffusion Models Need Visual Priors for Image Generation [PDF]

• DLGrapher: Dual Latent Diffusion for Attributed Graph Generation [PDF]

• MuLan: Multimodal-LLM Agent for Progressive and Interactive Multi-Object Diffusion [PDF]

• Text-to-graph Generation with Conditional Diffusion Models Guided by Graph-aligned LLMs [PDF]

• GRASP: Generating Graphs via Spectral Diffusion [PDF]

• Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups [PDF]

• Adaptive Drag: Semantic-Driven Dragging on Diffusion-Based Image Editing [PDF]

• Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned s [PDF]

• Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control [PDF]

• CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models [PDF]

• Accelerating Diffusion Transformers with Token-wise Feature Caching [PDF]

• PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models [PDF]

• Protecting Minorities in Diffusion Models via Capacity Allocation [PDF]

• Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos [PDF]

• Self-Conditioned Diffusion Model for Consistent Human Image and Video Synthesis [PDF]

• Physics-Informed Diffusion Models [PDF]

• Leveraging Diffusion Transformers for Stock Factor Augmentation in Financial Markets [PDF]

• Compositional Scene Modeling with An Object-Centric Diffusion Transformer [PDF]

• SAN-Diff: Structure-aware noise for super-resolution diffusion model [PDF]

• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding [PDF]

• TIMBA: Time series Imputation with Bi-directional Mamba Blocks and Diffusion models [PDF]

• Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models [PDF]

• Diffusion Implicit Policy for Unpaired Scene-aware Motion Synthesis [PDF]

• Partially Conditioned Patch Parallelism for Accelerated Diffusion Model Inference [PDF]

• Prune: Editing in Diffusion Models via Skilled Neuron Pruning [PDF]

• Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems [PDF]

• Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models [PDF]

• Diffusion on language model encodings for protein sequence generation [PDF]

• Influence-Guided Diffusion for Dataset Distillation [PDF]

• Sparse Repellency for Shielded Generation in Text-to-Image Diffusion Models [PDF]

• SteerDiff: Steering towards Safe Text-To-Image Diffusion Models [PDF]

• TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model [PDF]

• Hiding Images in Diffusion Models by Editing Learned Score Functions [PDF]

• Unified Perspectives on Signal-to-Noise Diffusion Models [PDF]

• MVLight: Relightable Text-to-3D Generation via Light-conditioned Multi-View Diffusion [PDF]

• Progressive Compression with Universally Quantized Diffusion Models [PDF]

• Improving Antibody Design with Force-Guided Sampling in Diffusion Models [PDF]

• GETMusic: Generating Music Tracks with a Unified Representation and Diffusion Framework [PDF]

• Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generation [PDF]

• Beautifying Diffusion Models: Learning Context-Aware Filters for Robust Dense Prediction on Test-Time Corrupted Images [PDF]

• SePPO: Semi-Policy Preference Optimization for Diffusion Alignment [PDF]

• Nested Diffusion Models using Hierarchical Latent Priors [PDF]

• PerLDiff: Controllable Street View Synthesis Using Perspective-Layout Diffusion Model [PDF]

• ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning [PDF]

• MissDiff: Training Diffusion Models on Tabular Data with Missing Values [PDF]

• Build your own cell: Diffusion Models for Multichannel 3D Microscopy Image Generation [PDF]

• Temporal Distribution-aware Quantization for Diffusion Models [PDF]

• DODA: Diffusion for Object-detection Domain Adaptation in Agriculture [PDF]

• DPLM-2: A Multimodal Diffusion Protein Language Model [PDF]

• Imit-Diff: Semantics Guided Diffusion Transformer with Dual Resolution Fusion for Imitation Learning [PDF]

• Diffusion Transformer Policy [PDF]

• DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation [PDF]

• Towards Black-Box Membership Inference Attack for Diffusion Models [PDF]

• Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis [PDF]

• Continuous Ensemble Weather Forecasting with Diffusion models [PDF]

• Mitigating Generative Privacy Risks of Diffusion Models via Mixed Self-Synthesized Data Fine-tuning [PDF]

• Lossy Compression with Pretrained Diffusion Models [PDF]

• On the feature learning in diffusion models [PDF]

• Influence Functions for Scalable Data Attribution in Diffusion Models [PDF]

• Atlas Gaussians Diffusion for 3D Generation [PDF]

• Edge-preserving noise for diffusion models [PDF]

• Diffusion Auto-regressive Transformer for Effective Self-supervised Time Series Forecasting [PDF]

• Less is More: Masking Elements in Image Condition Features Avoids Content Leakages in Style Transfer Diffusion Models [PDF]

• Denoising Task Difficulty-based Curriculum for Training Diffusion Models [PDF]

• Amortized Posterior Sampling with Diffusion Prior Distillation [PDF]

• ID-Booth: Identity-consistent image generation with diffusion models [PDF]

• Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks [PDF]

• Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model [PDF]

• Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning [PDF]

• Diffusion Transportation Cost for Domain Adaptation [PDF]

• SeLoRA: Self-Expanding Low-Rank Adaptation of Latent Diffusion Model for Medical Image Synthesis [PDF]

• Self-Supervised Diffusion MRI Denoising via Iterative and Stable Refinement [PDF]

• Diffusion-based Neural Network Weights Generation [PDF]

• Truncation Is All You Need: Improved Sampling Of Diffusion Models For Physics-Based Simulations [PDF]

• Glauber Generative Model: Discrete Diffusion Models via Binary Classification [PDF]

• Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors [PDF]

• On Statistical Rates of Conditional Diffusion Transformer: Approximation and Estimation [PDF]

• Learning to Permute with Discrete Diffusion [PDF]

• Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention [PDF]

• ClearSR: Latent Low-Resolution Image Embeddings Help Diffusion-Based Real-World Super Resolution Models See Clearer [PDF]

• FairSkin: Fair Diffusion for Skin Disease Image Geneartion [PDF]

• MRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers [PDF]

• Diffusion Feedback Helps CLIP See Better [PDF]

• Mixture-of-Diffusers: Dual-Stage Diffusion Model for Improved Time Series Generation [PDF]

• MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation [PDF]

• Diffusion2: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models [PDF]

• DIAR: Diffusion-model-guided Implicit Q-learning with Adaptive Revaluation [PDF]

• DiffPC: Diffusion-based High Perceptual Fidelity Image Compression with Semantic Refinement [PDF]

• DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector [PDF]

• WMAdapter: Adding WaterMark Control to Latent Diffusion Models [PDF]

• Federated Unlearning with Diffusion Models [PDF]

• Unified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers [PDF]

• A diffusion model on toric varieties with application to protein loop modeling [PDF]

• Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning [PDF]

• DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning [PDF]

• DSPart: A Large-scale Diffusion-generated Synthetic Dataset with Annotations from 3D Parts [PDF]

• Generating GFlowNets as You Wish with Diffusion Process [PDF]

• Spatio-temporal Diffusion Transformer for Action Recognition [PDF]

• Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images [PDF]

• DMDSpeech: Distilled Diffusion Model Surpassing The Teacher in Zero-shot Speech Synthesis via Direct Metric Optimization [PDF]

• Revamping Diffusion Guidance for Conditional and Unconditional Generation [PDF]

• Diffusion Minimization and Sheaf Neural Networks for Recommender Systems [PDF]

• Diffusion Curriculum: Synthetic-to-Real Data Curriculum via Image-Guided Diffusion [PDF]

• VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control [PDF]

• SFW sampling for diffusion models via external conditioning [PDF]

• DualFast: Dual-Speedup Framework for Fast Sampling of Diffusion Models [PDF]

• SVDQuant: Absorbing Outliers by Low-Rank Component for 4-Bit Diffusion Models [PDF]

• The Latent Road to Atoms: Backmapping Coarse-grained Protein Structures with Latent Diffusion [PDF]

• Balancing Token Efficiency and Structural Accuracy in LLMs Image Generation by Combining VQ-VAE and Diffusion Tokenizers [PDF]

• Stable Diffusion Feature Extraction for Sketching with One Example [PDF]

• One Step Diffusion via Shortcut Models [PDF]

• Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion [PDF]

• ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation [PDF]

• What Matters When Repurposing Diffusion Models for General Dense Perception Tasks? [PDF]

• Gradient based Causal Discovery with Diffusion Model [PDF]

• TerDiT: Ternary Diffusion Models with Transformers [PDF]

• Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion [PDF]

• MorphoDiff: Cellular Morphology Painting with Diffusion Models [PDF]

• DEEM: Diffusion models serve as the eyes of large language models for image perception [PDF]

• TabUnite: Efficient Encoding Schemes for Flow and Diffusion Tabular Generative Models [PDF]

• Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control [PDF]

• Parallel simulation for sampling under isoperimetry and score-based diffusion models [PDF]

• CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models [PDF]

• ToMA: Token Merging with Attention For Diffusion Models [PDF]

• UTSD: Unified Time Series Diffusion Model [PDF]

• FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality [PDF]

• Recurrent Diffusion for Large-Scale Parameter Generation [PDF]

• LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation [PDF]

• UniVIEDM: A Diffusion Model to Unify Visual Information Extraction Subtasks [PDF]

• Scaling With Text-Guided Diffusion Models [PDF]

• IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models [PDF]

• Mining your own secrets: Diffusion Classifier Scores for Continual Personalization of Text-to-Image Diffusion Models [PDF]

• Fast and Noise-Robust Diffusion Solvers for Inverse Problems: A Frequentist Approach [PDF]

• Discrete Copula Diffusion [PDF]

• Toward Exploratory Inverse Constraint Inference with Generative Diffusion Verifiers [PDF]

• Topology-aware Graph Diffusion Model with Persistent Homology [PDF]

• Diffusion Trajectory-guided Policy: A Novel Framework for Long-Horizon Robot Manipulation [PDF]

• Diffusion Models are Few-shot Learners for Dense Vision Tasks [PDF]

• Series-to-Series Diffusion Bridge Model [PDF]

• FreeTraj: Tuning-Free Trajectory Control via Noise Guided Video Diffusion [PDF]

• MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling [PDF]

• CELL-Diff: Unified Diffusion Modeling for Protein Sequences and Microscopy Images [PDF]

• Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [PDF]

• AuthFace: Towards Authentic Blind Face Restoration with Face-oriented Generative Diffusion Prior [PDF]

• Diff-Shape: A Novel Constrained Diffusion Model for Shape-based De Novo Drug Design [PDF]

• Unified Multimodal Discrete Diffusion [PDF]

• Iterative DPO with An Improvement Model for Fine-tuning Diffusion Models [PDF]

• FreqPrior: Improving Diffusion Models with Frequency Filtering Gaussian Noise as Prior [PDF]

• CoLa-DCE – -guided Latent Diffusion Counterfactual Explanations [PDF]

• Improving Editability in Compositional Image Diffusion with Layer-wise Memory [PDF]

• InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation [PDF]

• RestoreGrad: Signal Restoration Using Conditional Denoising Diffusion Models with Jointly Learned Prior [PDF]

• Haland: Human-AI Coordination via Policy Generation from Language-guided Diffusion [PDF]

• MaD-Scientist: AI-based Scientist solving Convection-Diffusion-Reaction Equations Using Massive PINN-Based Prior Data [PDF]

• Generating Model Parameters for Controlling: Parameter Diffusion for Controllable Multi-Task Recommendation [PDF]

• Generative bandit optimization via diffusion posterior sampling [PDF]

• Alignment without Over-optimization: Training-Free Solution for Diffusion Models [PDF]

• PFDiff: Training-free Acceleration of Diffusion Models through the Gradient Guidance of Past and Future [PDF]

• GuideCO: Training Objective-Guided Diffusion Solver with Imperfect Data for Combinatorial Optimization [PDF]

• VideoPanda: Video Panoramic Diffusion With Multi-view Attention [PDF]

• Improving Probabilistic Diffusion Models With Optimal Covariance Matching [PDF]

• Addressing domain shift with diffusion-based adaptation for real image dehazing [PDF]

• State Combinatorial Generalization In Decision Making With Conditional Diffusion Models [PDF]

• ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models [PDF]

• Boosting Latent Diffusion with Perceptual Objectives [PDF]

• Boost 3D Reconstruction using Diffusion-based Intrinsic Estimation [PDF]

• Reinforcement learning on structure-conditioned categorical diffusion for protein inverse folding [PDF]

• DRAG: Data Reconstruction Attack using Guided Diffusion [PDF]

• Fast Multi-Mode Adaptive Generative Distillation for Continually Learning Diffusion Models [PDF]

• GoodDrag: Towards Good Practices for Drag Editing with Diffusion Models [PDF]

• Bundle Neural Network for message diffusion on graphs [PDF]

• G4Seg: Generation for Online Segmentation Refinement with Diffusion Models [PDF]

• Robust Two-Hand Reconstruction with Additional 2D Information and Diffusion Prior [PDF]

• Unsupervised Radar Point Cloud Enhancement Using Diffusion Model as Prior without Paired Traning Data [PDF]

• Real-World Benchmarks Make Membership Inference Attacks Fail on Diffusion Models [PDF]

• Promptus: Representing Real-World Video as Stable Diffusion Prompts for Video Streaming [PDF]

• Group Diffusion Transformers are Unsupervised Multitask Learners [PDF]

• 3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion [PDF]

• FLEXOUNDIT: VARIABLE-LENGTH DIFFUSION TRANSFORMER FOR TEXT-TO-AUDIO GENERATION [PDF]

• Controlling Language and Diffusion Models by Transporting Activations [PDF]

• 3D-free meets 3D priors: Novel View Synthesis from a Single Image with Pretrained Diffusion Guidance [PDF]

• DM-Tune: Quantizing Diffusion Models with Mixture-of-Gaussian Guided Noise Tuning [PDF]

• Leveraging Natural Frequency Deviation for Diffusion-Generated Image Detection [PDF]

• Infinite-Resolution Integral Noise Warping for Diffusion Models [PDF]

• MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion [PDF]

• On Inductive Biases That Enable Generalization in Diffusion Transformers [PDF]

• Efficient Diffusion Posterior Sampling for Dose Reduced CT Reconstruction [PDF]

• Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation [PDF]

• Overcoming False Illusions in Real-World Face Restoration with Multi-Modal Guided Diffusion Model [PDF]

• Dynamic Diffusion Transformer [PDF]

• Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model [PDF]

• Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation [PDF]

• Lumina-T2X: Scalable Flow-based Large Diffusion Transformer for Flexible Resolution Generation [PDF]

• Uncertainty-aware Guided Diffusion for Missing Data in Sequential Recommendation [PDF]

• DISCO: Efficient Diffusion Solver for Large-Scale Combinatorial Optimization Problems [PDF]

• Diffusion Models as Cartoonists! The Curious Case of High Density Regions [PDF]

• Decouple-Then-Merge: Towards Better Training for Diffusion Models [PDF]

• Mitigating Unobserved Confounding via Diffusion Probabilistic Models [PDF]

• ZERO-1-to-G: Taming Pretrained 2D Diffusion Models for Direct 3D Generation [PDF]

• ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance [PDF]

• The Convergence of Second-Order Sampling Methods for Diffusion Models [PDF]

• DDRL: A DIFFUSION-DRIVEN REINFORCEMENT LEARNING APPROACH FOR ENHANCED TSP SOLUTIONS [PDF]

• MGD3: Mode-Guided Dataset Distillation using Diffusion Models [PDF]

• Compress Guidance in Conditional Diffusion Sampling [PDF]

• Topological Zigzag Spaghetti for Diffusion-based Generation and Prediction on Graphs [PDF]

• Diffusion Policy Policy Optimization [PDF]

• STABLE DIFFUSION MODELS ARE SECRETLY GOOD AT VISUAL IN-CONTEXT LEARNING [PDF]

• Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting [PDF]

• Growth Inhibitors for Suppressing Inappropriate Image s in Diffusion Models [PDF]

• Diffusion Compose: Compositional Depth Aware Scene Editing in Diffusion Models [PDF]

• Mitigating Embedding Collapse in Diffusion Models for Categorical Data [PDF]

• Underdamped Diffusion Bridges with Applications to Sampling [PDF]

• Scaling up Masked Diffusion Models on Text [PDF]

• Exploring Local Memorization in Diffusion Models via Bright Ending Attention [PDF]

• Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport [PDF]

• Tradiffusion++：Hierarchical Guidance for Fine-Grained Trajectory-Based Image Generation [PDF]

• Shallow diffusion networks provably learn hidden low-dimensional structure [PDF]

• EC-DIT: Scaling Diffusion Transformers with Adaptive Expert-Choice Routing [PDF]

• One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation [PDF]

• Learning to Discretize Denoising Diffusion ODEs [PDF]

• ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer [PDF]

• Graph Scattering Networks with Adaptive Diffusion Kernels [PDF]

• Efficient Physics-Constrained Diffusion Models for Solving Inverse Problems [PDF]

• CycleVTON: Improving Diffusion-Based Virtual Try-On with Cycle-Consistent Training [PDF]

• Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective [PDF]

• MimoUDiff: A Unified Multi-Source Data Fusion Framework via MIMO Unet and Refined Diffusion for Precipitation Nowcasting [PDF]

• Boosting Camera Motion Control for Video Diffusion Transformers [PDF]

• How do diffusion models learn and generalize on abstract rules for reasoning? [PDF]

• SiDyP: Simplex Diffusion with Dynamic Prior for Denoising Llama-Generated Labels [PDF]

• From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training [PDF]

• Cometh: A continuous-time discrete-state graph diffusion model [PDF]

• DSPO: Direct Score Preference Optimization for Diffusion Model Alignment [PDF]

• GravMAD: Grounded Spatial Value Maps Guided Action Diffusion for Generalized 3D Manipulation [PDF]

• Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning [PDF]

• Boosting Offline Multi-Objective Reinforcement Learning via Preference Conditioned Diffusion Models [PDF]

• Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare s with LLM Guidance [PDF]

• Regularized Diffusion Modeling for CAD Representation Generation [PDF]

• Step-wise Triple-Consistent Diffusion Sampling for Inverse Problems [PDF]

• CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation [PDF]

• xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing [PDF]

• Multi-Robot Motion Planning with Diffusion Models [PDF]

• Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies [PDF]

• Hierarchical Clustering for Conditional Diffusion in Image Generation [PDF]

• High-quality and controllable time series generation with diffusion in transformers [PDF]

• UniVAE: A Unified Frame-Enriched Video VAE for Latent Video Diffusion Models [PDF]

• A Simple Approach to Unifying Diffusion-based Conditional Generation [PDF]

• VFDiff: SE(3)-Equivariant Vector Field Guided Diffusion Model for Target-Aware Molecule Generation in 3D [PDF]

• Shape Assembly via Equivariant Diffusion [PDF]

• SANA: Efficient High-Resolution Text-to-Image Synthesis with Linear Diffusion Transformers [PDF]

• Distribution-Aware Diffusion Model Quantization via Distortion Minimization [PDF]

• d-Linear Generation Error Bound for Distributed Diffusion Models [PDF]

• PCDM: PERCEPTUAL CONSISTENCY IN DIFFUSION MODELS FOR NO-REFERENCE IMAGE QUALITY ASSESSMENT [PDF]

• SparseDM: Toward Sparse Efficient Diffusion Models [PDF]

• Task-agnostic Pre-training and Task-guided Fine-tuning for Versatile Diffusion Planner [PDF]

• G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving [PDF]

• Adaptive Caching for Faster Video Generation with Diffusion Transformers [PDF]

• WaveDiffusion: Exploring Full Waveform Inversion via Joint Diffusion in the Latent Space [PDF]

• TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation [PDF]

• Noise Prompt Learning: Learning the Winning Tickets for Diffusion Sampling [PDF]

• DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models [PDF]

• DiffSign: A Different Approach to Continuous Sign Language Recognition with Diffusion Model [PDF]

• TabWak: A Watermark for Tabular Diffusion Models [PDF]

• Simple and Controllable Uniform Discrete Diffusion Language Models [PDF]

• Frequency-Conditioned Diffusion Models for Time Series Generation [PDF]

• Inverse Engineering Diffusion: Deriving Variance Schedules with Rationale [PDF]

• Incorporating Visual Correspondence into Diffusion Model for Visual Try-On [PDF]

• TD-Paint: Faster Diffusion Inpainting Through Time Aware Pixel Conditioning [PDF]

• Debiasing Text-to-image Diffusion Models with Self-discovering Latent Directions [PDF]

• Cohesion: Coherence-Based Diffusion for Long-Range Dynamics Forecasting [PDF]

• FreeMorph: Tuning-Free Generalized Image Morphing with Diffusion Model [PDF]

• RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models [PDF]

• GDrag:Towards General-Purpose Interactive Editing with Anti-ambiguity Point Diffusion [PDF]

• Feature-guided score diffusion for sampling conditional densities [PDF]

• Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models [PDF]

• Towards Generalization under Topological Shifts: A Diffusion PDE Perspective [PDF]

• LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion [PDF]

• Hybrid Regularization Improves Diffusion-based Inverse Problem Solving [PDF]

• A Tailored Framework for Aligning Diffusion Models with Human Preference [PDF]

• Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting [PDF]

• Compositional Generative Inference Using Diffusion-based Optimization [PDF]

• Supervised and Semi-Supervised Diffusion Maps with Label-Driven Diffusion [PDF]

• Diversity-Enhanced and Classification-Aware Prompt Learning for Few-Shot Learning via Stable Diffusion [PDF]

• Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models [PDF]

• SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models [PDF]

• Relation-Aware Diffusion for Heterogeneous Graphs with Partially Observed Features [PDF]

• Diffusion Models Are Real-Time Game Engines [PDF]

• X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models [PDF]

• Improved Noise Schedule for Diffusion Training [PDF]

• Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models [PDF]

• Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers [PDF]

• A3D: Does Diffusion Dream about 3D Alignment? [PDF]

• Generalizable Origin Identification for Text-Guided Image-to-Image Diffusion Models [PDF]

• ACDC: Autoregressive Coherent Multimodal Generation using Diffusion Correction [PDF]

• Multi-Scale Image Diffusion Transformers: Explainability Leads to Faster Training [PDF]

• VARIATIONAL DIFFUSION CHANNEL DECODING: A ULTRA-LOW-COST NEURAL CHANNEL DECODER [PDF]

• DiNO-Diffusion: Scaling Medical Diffusion Models via Self-Supervised Pre-Training [PDF]

• Diffusion Attacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak [PDF]

• Ensembling Diffusion Models via Adaptive Feature Aggregation [PDF]

• Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation [PDF]

• Write More at Once: Stylized Chinese Handwriting Generation via Two-stage Diffusion [PDF]

• HERO: Harnessing Temporal Modeling for Diffusion-Based Video Outpainting [PDF]

• ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler [PDF]

• Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization [PDF]

• RAGDP: Retrieve-Augmented Generative Diffusion Policy [PDF]

• End-to-end Learning of Gaussian Mixture Priors for Diffusion Sampler [PDF]

• Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation [PDF]

• Pixel-Aware Accelerated Reverse Diffusion Modeling [PDF]

• GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting [PDF]

• Low Variance: A Bottleneck in Diffusion-Based Graph Imputation [PDF]

• EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing [PDF]

• Diffusion-based Extreme Image Compression with Compressed Feature Initialization [PDF]

• Diffusion priors for Bayesian 3D reconstruction from incomplete measurements [PDF]

• GeNIe: Generative Hard Negative Images Through Diffusion [PDF]

• DART: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control [PDF]

• Text2PDE: Latent Diffusion Models for Accessible Physics Simulation [PDF]

• Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization [PDF]

• Training-free Long Video Generation with Chain of Diffusion Model Experts [PDF]

• Riemannian denoising diffusion probabilistic models [PDF]

• The Inductive Bias of Minimum-Norm Shallow Diffusion Models That Perfectly Fit the Data [PDF]

• Robust Watermarking for Diffusion Models: A Unified Multi-Dimensional Recipe [PDF]

• Neural Approximate Mirror Maps for Constrained Diffusion Models [PDF]

• Improving Denoising Diffusion with Efficient Conditional Entropy Reduction [PDF]

• VideoDiT: Bridging Image Diffusion Transformers for Streamlined Video Generation [PDF]

• Anomaly Detection through Conditional Diffusion Probability Modeling on Graphs [PDF]

• Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception [PDF]

• Adaptive Source Localization on Complex Networks via Conditional Diffusion Model [PDF]

• ConsisSR: Delving Deep into Consistency in Diffusion-based Image Super-Resolution [PDF]

• Statistical Test on Diffusion Model-based Anomaly Detection by Selective Inference [PDF]

• Energy-Based Diffusion Language Models for Text Generation [PDF]

• VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference [PDF]

• Latent Diffusion Planning for Imitation Learning [PDF]

• Uncertainty-Regularized Diffusional Subgoals for Hierarchical Reinforcement Learning [PDF]

• Losing dimensions: Geometric memorization in generative diffusion [PDF]

• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [PDF]

• CADO: Cost-Aware Diffusion Models for Combinatorial Optimization via RL Fine-tuning [PDF]

• DC3DO: Diffusion Classifier for 3D Objects [PDF]

• Improved Convergence Rate for Diffusion Probabilistic Models [PDF]

• Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models [PDF]

• Differentiable Solver Search for fast diffusion sampling [PDF]

• CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation [PDF]

• Solving Inverse Problems in Protein Space Using Diffusion-Based Priors [PDF]

• Enhancing Human Body Generation in Diffusion Models with Dual-Level Prior Knowledge [PDF]

• GUD: Generation with Unified Diffusion [PDF]

• Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation [PDF]

• DOME: Taming Diffusion Model into High-Fidelity Controllable Occupancy World Model [PDF]

• DDIL: Improved Diffusion Distillation with Imitation Learning [PDF]

• Structure-Preserving Text-Based Editing for Few-Step Diffusion Models [PDF]

• Controlled Denoising For Diffusion Models [PDF]

• Code diffusion models are continuous human noise operators [PDF]

• Physics-aligned field reconstruction with diffusion bridge [PDF]

• SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training [PDF]

• Learning Distributions of Complex Fluid Simulations with Diffusion Graph Networks [PDF]

• Variational Diffusion Posterior Sampling with Midpoint Guidance [PDF]

• BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation [PDF]

• Unlocking Point Processes through Point Set Diffusion [PDF]

• Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis [PDF]

• Does Diffusion Beat GAN in Image Super Resolution? [PDF]

• Interpolating Autoregressive and Discrete Denoising Diffusion Language Models [PDF]

• Structured Diffusion Models with Mixture of Gaussians as Prior Distribution [PDF]

• Data-Centric Graph Condensation via Diffusion Trajectory Matching [PDF]

• Fast Diversity-Preserving Reward Finetuning of Diffusion Models via Nabla-GFlowNets [PDF]

• Stable Signature is Unstable: Removing Image Watermark from Diffusion Models [PDF]

• Continuous Diffusion for Mixed-Type Tabular Data [PDF]

• APCtrl: Adding Conditional Control to Diffusion Models by Alternative Projection [PDF]

• Preserving the Unique Heritage of Chinese Ancient Architecture in Diffusion Models with Text and Image Integration [PDF]

• Bias Mitigation in Graph Diffusion Models [PDF]

• Unveiling Concept Attribution in Diffusion Models [PDF]

• Diffusion Preference Alignment via Relative Text-Image Contrast [PDF]

• Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics [PDF]

• Conditional Trajectories in Diffusion Models - Modeling Galaxy Evolution from Redshift [PDF]

• The Superposition of Diffusion Models [PDF]

• Physics-Informed Self-Guided Diffusion Model for High-Fidelity Simulations [PDF]

• BetterBodies: Reinforcement Learning guided Diffusion for Antibody Sequence Design [PDF]

• Constrained Diffusion Implicit Models [PDF]

• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [PDF]

• Bellman Diffusion: Generative Modeling as Learning a Linear Operator in the Distribution Space [PDF]

• QuaDiM: A Conditional Diffusion Model For Quantum State Property Estimation [PDF]

• CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control [PDF]

• GaussianAnything: Interactive Point Cloud Latent Diffusion for 3D Generation [PDF]

• Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation [PDF]

• Direct Distributional Optimization for Provable Alignment of Diffusion Models [PDF]

• Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems [PDF]

• Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model [PDF]

• Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion [PDF]

• Avoiding mode collapse in diffusion models fine-tuned with reinforcement learning [PDF]

• Video Diffusion Models Learn the Structure of the Dynamic World [PDF]

• Sampling from Energy-based Policies using Diffusion [PDF]

• Accelerate Quantization Aware Training for Diffusion Models with Difficulty-aware Time Allocation [PDF]

• Beyond Transformations: Augmenting Anything for Image Super-Resolution via Diffusion Model [PDF]

• VideoGuide: Improving Video Diffusion Models without Training Through a Teacher's Guide [PDF]

• InverseBench: Benchmarking Plug-and-Play Diffusion Models for Scientific Inverse Problems [PDF]

• HarmoniCa: Harmonizing Training and Inference for Better Feature Cache in Diffusion Transformer Acceleration [PDF]

• Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data [PDF]

• DoF: A Diffusion Factorization Framework for Offline Multi-Agent Decision Making [PDF]

• Beyond Isolated Words: Diffusion Brush for Handwritten Text-Line Generation [PDF]

• SuperMark: Robust and Training-free Image Watermarking via Diffusion-based Super-Resolution [PDF]

• Sequential Controlled Langevin Diffusions [PDF]

• Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection [PDF]

• ET-SEED: EFFICIENT TRAJECTORY-LEVEL SE(3) EQUIVARIANT DIFFUSION POLICY [PDF]

• DiffusionTrend: A Minimalist Approach to Virtual Fashion Try-On [PDF]

• DiffImp: Efficient Diffusion Model for Probabilistic Time Series Imputation with Bidirectional Mamba Backbone [PDF]

• Efficient Perplexity Bound and Ratio Matching in Discrete Diffusion Language Models [PDF]

• STDM: Spatio-Temporal Diffusion Models for Time Series Analysis [PDF]

• Multi-Task Dense Predictions via Unleashing the Power of Diffusion [PDF]

• TopoDiffusionNet: A Topology-aware Diffusion Model [PDF]

• DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior [PDF]

• SoundMorpher: Perceptually-Uniform Sound Morphing with Diffusion Model [PDF]

• LISA: UNLEASHING 2D DIFFUSION FOR 3D GENERATION VIA LIGHTWEIGHT IMAGE SPLATS ADAPTATION [PDF]

• Aggregation of Multi Diffusion Models for Enhancing Learned Representations [PDF]

• Human-Feedback Efficient Reinforcement Learning for Online Diffusion Model Finetuning [PDF]

• SeaDAG: Semi-autoregressive Diffusion for Conditional Directed Acyclic Graph Generation [PDF]

• Camera Pose Estimation Emerging In Video Diffusion Transformer [PDF]

• UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models [PDF]

• Diffusion-Based Offline RL for Improved Decision-Making in Augmented Single ARC Task [PDF]

• Not All Noises Are Created Equally: Diffusion Noise Selection and Optimization [PDF]

• Multi-Student Diffusion Distillation for Better One-Step Generators [PDF]

• Blending Concepts in Text-to-Image Diffusion Models using the Black Scholes Algorithm [PDF]

• Diffusion SigFormer for Interference Time-series Signal Recognition [PDF]

• Efficient Diffusion Models for Symmetric Manifolds [PDF]

• Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models [PDF]

• Unveiling the Secret of AdaLN-Zero in Diffusion Transformer [PDF]