{"total":74,"rows":[{"id":"2605.05204","title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","created":"2026-05-06","cited_by_count":22,"area":"diffusion"},{"id":"2602.13515","title":"SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning","created":"2026-02-13","cited_by_count":18,"area":"diffusion"},{"id":"2604.19858","title":"Wan-Image: Pushing the Boundaries of Generative Visual Intelligence","created":"2026-04-21","cited_by_count":16,"area":"diffusion"},{"id":"2602.05951","title":"Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow Matching","created":"2026-02-05","cited_by_count":9,"area":"diffusion"},{"id":"2603.16271","title":"VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignment","created":"2026-03-17","cited_by_count":7,"area":"diffusion"},{"id":"2605.23902","title":"PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion","created":"2026-05-22","cited_by_count":7,"area":"diffusion"},{"id":"2603.04910","title":"VPWEM: Non-Markovian Visuomotor Policy with Working and Episodic Memory","created":"2026-03-05","cited_by_count":6,"area":"diffusion"},{"id":"2602.06159","title":"Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous Driving","created":"2026-02-05","cited_by_count":5,"area":"diffusion"},{"id":"2604.25427","title":"A Systematic Post-Train Framework for Video Generation","created":"2026-04-28","cited_by_count":5,"area":"diffusion"},{"id":"2605.22894","title":"SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control","created":"2026-05-21","cited_by_count":5,"area":"diffusion"},{"id":"2608.26794","title":"Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion","created":"2026-08-27","cited_by_count":5,"area":"diffusion"},{"id":"2603.12257","title":"DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning","created":"2026-03-12","cited_by_count":4,"area":"diffusion"},{"id":"2603.28713","title":"DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editing","created":"2026-03-30","cited_by_count":4,"area":"diffusion"},{"id":"2605.25195","title":"Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation","created":"2026-05-24","cited_by_count":4,"area":"diffusion"},{"id":"2606.28016","title":"TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL","created":"2026-06-26","cited_by_count":4,"area":"diffusion"},{"id":"2607.19139","title":"Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers","created":"2026-07-21","cited_by_count":4,"area":"diffusion"},{"id":"2604.10578","title":"Rein3D: Reinforced 3D Indoor Scene Generation with Panoramic Video Diffusion Models","created":"2026-04-12","cited_by_count":3,"area":"diffusion"},{"id":"2604.11331","title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","created":"2026-04-13","cited_by_count":3,"area":"diffusion"},{"id":"2605.00658","title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","created":"2026-05-01","cited_by_count":3,"area":"diffusion"},{"id":"2606.23254","title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","created":"2026-06-22","cited_by_count":3,"area":"diffusion"},{"id":"2607.02220","title":"DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation","created":"2026-07-02","cited_by_count":3,"area":"diffusion"},{"id":"2607.14681","title":"ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships","created":"2026-07-16","cited_by_count":3,"area":"diffusion"},{"id":"2607.19064","title":"Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing","created":"2026-07-21","cited_by_count":3,"area":"diffusion"},{"id":"2607.21529","title":"ElasticTTT: Prior-Preserving Test-Time Tuning for Video Editing","created":"2026-07-23","cited_by_count":3,"area":"diffusion"},{"id":"2607.23492","title":"To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion","created":"2026-07-26","cited_by_count":3,"area":"diffusion"},{"id":"2609.03796","title":"LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes","created":"2026-09-03","cited_by_count":3,"area":"diffusion"},{"id":"2605.01477","title":"Action Agent: Agentic Video Generation Meets Flow-Constrained Diffusion","created":"2026-05-02","cited_by_count":2,"area":"diffusion"},{"id":"2605.03849","title":"Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation","created":"2026-05-05","cited_by_count":2,"area":"diffusion"},{"id":"2605.23602","title":"GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes","created":"2026-05-22","cited_by_count":2,"area":"diffusion"},{"id":"2606.03943","title":"PointAction: 3D Points as Universal Action Representations for Robot Control","created":"2026-06-02","cited_by_count":2,"area":"diffusion"},{"id":"2606.11289","title":"i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models","created":"2026-06-09","cited_by_count":2,"area":"diffusion"},{"id":"2606.32033","title":"SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE","created":"2026-06-30","cited_by_count":2,"area":"diffusion"},{"id":"2601.12066","title":"Learning Stochastic Bridges for Video Object Removal via Video-to-Video Translation","created":"2026-01-17","cited_by_count":1,"area":"diffusion"},{"id":"2602.12155","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","created":"2026-02-12","cited_by_count":1,"area":"diffusion"},{"id":"2603.19643","title":"OmniDiT: Extending Diffusion Transformer to Omni-VTON Framework","created":"2026-03-20","cited_by_count":1,"area":"diffusion"},{"id":"2604.13509","title":"DiT as Real-Time Rerenderer: Streaming Video Stylization with Autoregressive Diffusion Transformer","created":"2026-04-15","cited_by_count":1,"area":"diffusion"},{"id":"2605.26460","title":"AnchorDiff: Training-Free Concept Grounding for MM-DiTs via Anchor-Based Graph Propagation","created":"2026-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2606.05950","title":"Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing","created":"2026-06-04","cited_by_count":1,"area":"diffusion"},{"id":"2606.07053","title":"TrioPose: Native Triple-Stream Diffusion Transformers for Pose-Guided Text-to-Image Generation","created":"2026-06-05","cited_by_count":1,"area":"diffusion"},{"id":"2606.19194","title":"Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulation","created":"2026-06-17","cited_by_count":1,"area":"diffusion"},{"id":"2607.02798","title":"Track the Noise, Move the World:3D-Grounded Motion-Consistent Noise for Controllable Video Generation","created":"2026-07-02","cited_by_count":1,"area":"diffusion"},{"id":"2608.20818","title":"Scaling Muon for Diffusion Transformers","created":"2026-08-21","cited_by_count":1,"area":"diffusion"},{"id":"2608.25505","title":"Conditional Total Correlation and the Serial Depth of Adaptive Parallel Sampling","created":"2026-08-26","cited_by_count":1,"area":"diffusion"},{"id":"2609.20744","title":"Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation","created":"2026-09-17","cited_by_count":1,"area":"diffusion"},{"id":"2512.23245","title":"ASemConsist: Adaptive Semantic Feature Control for Training-Free Identity-Consistent Generation","created":"2025-12-29","cited_by_count":0,"area":"diffusion"},{"id":"2602.06806","title":"RAIGen: Rare Attribute Identification in Text-to-Image Generative Models","created":"2026-02-06","cited_by_count":0,"area":"diffusion"},{"id":"2603.10210","title":"Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation","created":"2026-03-10","cited_by_count":0,"area":"diffusion"},{"id":"2603.13386","title":"Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers","created":"2026-03-11","cited_by_count":0,"area":"diffusion"},{"id":"2603.17555","title":"FrescoDiffusion: 4K Image-to-Video with Prior-Regularized Tiled Diffusion","created":"2026-03-18","cited_by_count":0,"area":"diffusion"},{"id":"2603.23179","title":"Gimbal360: Canonicalizing Planar Diffusion for Spherical Panorama Completion","created":"2026-03-24","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":"2606.01079","title":"Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing","created":"2026-05-31","cited_by_count":0,"area":"diffusion"},{"id":"2606.13971","title":"Prompt2Effect: Training-Free Image-to-Video Model Specialization via LoRA Generation","created":"2026-06-11","cited_by_count":0,"area":"diffusion"},{"id":"2606.20924","title":"ELDiff: When Evidential Learning Meets Text-to-Image Diffusion","created":"2026-06-18","cited_by_count":0,"area":"diffusion"},{"id":"2606.21030","title":"FlowCodec: One-Step Flow Prior for Generative Image Compression","created":"2026-06-19","cited_by_count":0,"area":"diffusion"},{"id":"2606.29801","title":"Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion Sampling","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2606.29814","title":"Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2607.19701","title":"SafeGen: Goal-Conditioned Video Diffusion of Safety-Critical Scenarios for VLM-Based Autonomous Driving","created":"2026-07-22","cited_by_count":0,"area":"diffusion"},{"id":"2608.11562","title":"From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection","created":"2026-08-12","cited_by_count":0,"area":"diffusion"},{"id":"2608.19556","title":"Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models","created":"2026-08-20","cited_by_count":0,"area":"diffusion"},{"id":"2608.20478","title":"EndoLIFT: Language-Disambiguated Latent-Conditioned Rectified Flow for Bidirectional Endoscopic Control","created":"2026-08-20","cited_by_count":0,"area":"diffusion"},{"id":"2609.17414","title":"SlotDiT: Object-Centric Representations for Diffusion Transformers","created":"2026-09-15","cited_by_count":0,"area":"diffusion"},{"id":"2609.21379","title":"JEPA Guided Diffusion: Predictive Vision-Language Conditioning for Generative Traffic Forecasting","created":"2026-09-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.28473","title":"On the Diffusibility of High-Dimensional Latents","created":"2026-09-23","cited_by_count":0,"area":"diffusion"},{"id":"2609.33582","title":"Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2609.36199","title":"PreviewDiff: Multimodal Critic-Guided Search over Diffusion Latents","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.39441","title":"CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion Models","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.05066","title":"Salvation Lies Within: Eliciting Inherent Style Transfer in Step-Distilled Diffusion Models","created":"2026-10-04","cited_by_count":0,"area":"diffusion"},{"id":"2610.05608","title":"Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation","created":"2026-10-04","cited_by_count":0,"area":"diffusion"},{"id":"2610.06334","title":"SPIN: Image Immunization Against Diffusion Editing via Single-Step Projection in Stochastic Neighborhoods","created":"2026-10-05","cited_by_count":0,"area":"diffusion"},{"id":"2610.09450","title":"Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning","created":"2026-10-07","cited_by_count":0,"area":"diffusion"},{"id":"2610.11238","title":"Attributing HOW, Not Just WHICH: Counterfactual Response Trajectories for Diffusion Models","created":"2026-10-08","cited_by_count":0,"area":"diffusion"},{"id":"2610.13187","title":"Destination-Conditioned Adaptation with Semantic-Geometric Alignment for Generative Inbetweening","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.13333","title":"LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse","created":"2026-10-09","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}