{"total":64,"rows":[{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393,"area":"diffusion"},{"id":"2411.15139","title":"DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving","created":"2024-11-22","cited_by_count":334,"area":"diffusion"},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225,"area":"diffusion"},{"id":"2502.09509","title":"EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling","created":"2025-02-13","cited_by_count":89,"area":null},{"id":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51,"area":"diffusion"},{"id":"2504.16064","title":"Boosting Generative Image Modeling via Joint Image-Feature Synthesis","created":"2025-04-22","cited_by_count":45,"area":"diffusion"},{"id":"2505.16792","title":"REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training","created":"2025-05-22","cited_by_count":37,"area":"diffusion"},{"id":"2509.25162","title":"AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models","created":"2025-09-29","cited_by_count":36,"area":"diffusion"},{"id":"2512.07829","title":"One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation","created":"2025-12-08","cited_by_count":28,"area":"diffusion"},{"id":"2507.08441","title":"Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"id":"2503.08619","title":"LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization","created":"2025-03-11","cited_by_count":20,"area":"alignment"},{"id":"2512.04926","title":"Semantics Lead the Way: Harmonizing Semantic and Texture Modeling with Asynchronous Latent Diffusion","created":"2025-12-04","cited_by_count":18,"area":"diffusion"},{"id":"2510.18457","title":"VFM-VAE: Vision Foundation Models Can Be Good Tokenizers for Latent Diffusion Models","created":"2025-10-21","cited_by_count":17,"area":"diffusion"},{"id":"2508.09136","title":"Turbo-VAED: Fast and Stable Transfer of Video-VAEs to Mobile Devices","created":"2025-08-12","cited_by_count":16,"area":null},{"id":"2602.02493","title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","created":"2026-02-02","cited_by_count":14,"area":"diffusion"},{"id":"2411.17616","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","created":"2024-11-26","cited_by_count":12,"area":"diffusion"},{"id":"2509.20890","title":"FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies","created":"2025-09-25","cited_by_count":12,"area":null},{"id":"2602.05435","title":"Stable Velocity: A Variance Perspective on Flow Matching","created":"2026-02-05","cited_by_count":12,"area":"diffusion"},{"id":"2512.15713","title":"DiffusionVL: Translating Any Autoregressive Models into Diffusion Vision Language Models","created":"2025-12-17","cited_by_count":10,"area":"mllm"},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"id":"2602.08620","title":"Improving Reconstruction of Representation Autoencoder","created":"2026-02-09","cited_by_count":9,"area":"diffusion"},{"id":"2605.07915","title":"What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion","created":"2026-05-08","cited_by_count":9,"area":"diffusion"},{"id":"2504.15159","title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","created":"2025-04-21","cited_by_count":8,"area":null},{"id":"2506.03275","title":"Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas","created":"2025-06-03","cited_by_count":8,"area":"diffusion"},{"id":"2509.05441","title":"Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2510.21250","title":"Improved Training Technique for Shortcut Models","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2511.20565","title":"DINO-Tok: Adapting DINO for Visual Tokenizers","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2512.07778","title":"Distribution Matching Variational AutoEncoder","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2506.13763","title":"Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value","created":"2025-06-16","cited_by_count":5,"area":"diffusion"},{"id":"2512.16636","title":"REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion","created":"2025-12-18","cited_by_count":5,"area":"diffusion"},{"id":"2505.19595","title":"Accelerating Diffusion-based Text-to-Speech Model Training with Dual Modality Alignment","created":"2025-05-26","cited_by_count":4,"area":"diffusion"},{"id":"2511.21475","title":"MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devices","created":"2025-11-26","cited_by_count":4,"area":"diffusion"},{"id":"2601.05823","title":"Boosting Latent Diffusion Models via Disentangled Representation Alignment","created":"2026-01-09","cited_by_count":4,"area":"diffusion"},{"id":"2507.06547","title":"Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution","created":"2025-07-09","cited_by_count":3,"area":"diffusion"},{"id":"2507.10768","title":"Spatial Reasoners for Continuous Variables in Any Domain","created":"2025-07-14","cited_by_count":3,"area":"lr"},{"id":"2601.11522","title":"UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation","created":"2026-01-16","cited_by_count":3,"area":null},{"id":"2511.23469","title":"Visual Generation Tuning","created":"2025-11-28","cited_by_count":2,"area":"mllm"},{"id":"2512.23258","title":"Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization","created":"2025-12-29","cited_by_count":2,"area":"diffusion"},{"id":"2601.05246","title":"Pixel-Perfect Visual Geometry Estimation","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.10365","title":"Geometric Autoencoder for Diffusion Models","created":"2026-03-11","cited_by_count":2,"area":"diffusion"},{"id":"2605.26391","title":"Garment Particles: A 2D--3D Symmetric Garment Representation for Generation and Editing","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2606.11096","title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2512.12083","title":"RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model","created":"2025-12-12","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":"2603.25249","title":"Semantic-Aware Prefix Learning for Token-Efficient Image Generation","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2605.18390","title":"Vision Foundation Models as Generalist Tokenizers for Image Generation","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.19662","title":"Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion","created":"2026-06-18","cited_by_count":1,"area":"diffusion"},{"id":"2607.14898","title":"FlashDecoder: Real-Time Latent-to-Pixel Streaming Decoder with Transformers","created":"2026-07-16","cited_by_count":1,"area":"diffusion"},{"id":"2608.01298","title":"UDT: Reconciling U-Nets and Diffusion Transformers with Data-Adaptive Token Reduction","created":"2026-08-02","cited_by_count":1,"area":"diffusion"},{"id":"2608.09438","title":"Unveiling the Secret of AdaLN-Zero in Diffusion Transformer","created":"2026-08-10","cited_by_count":1,"area":"diffusion"},{"id":"2506.16688","title":"Fast and Stable Diffusion Planning through Variational Adaptive Weighting","created":"2025-06-20","cited_by_count":0,"area":"diffusion"},{"id":"2509.03794","title":"Fitting Image Diffusion Models on Video Datasets","created":"2025-09-04","cited_by_count":0,"area":"diffusion"},{"id":"2601.17733","title":"Flatten The Complex: Joint B-Rep Generation via Compositional $k$-Cell Particles","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.02172","title":"TerraDiT: Point-Conditioned Diffusion Transformer for Satellite Image Synthesis","created":"2026-03-02","cited_by_count":0,"area":"diffusion"},{"id":"2603.07057","title":"SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer","created":"2026-03-07","cited_by_count":0,"area":"diffusion"},{"id":"2603.09408","title":"Reviving ConvNeXt for Efficient Convolutional Diffusion Models","created":"2026-03-10","cited_by_count":0,"area":"diffusion"},{"id":"2604.07397","title":"Data Warmup: Complexity-Aware Curricula for Efficient Diffusion Training","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.10790","title":"Elucidating Representation Degradation Problem in Diffusion Model Training","created":"2026-05-11","cited_by_count":0,"area":"diffusion"},{"id":"2605.15908","title":"RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2608.01306","title":"SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2609.11516","title":"LoopVAE: Recurrent Depth Across Scales for Visual Tokenization","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.32432","title":"Beyond the Manifold Hypothesis: Hybrid Spectral Parameterizations for Flow Matching","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2609.35292","title":"Scaffold Then Internalize: Representation Injection for Diffusion Transformers","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.40362","title":"Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}