{"total":703,"rows":[{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561,"area":null},{"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":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"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":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163,"area":"diffusion"},{"id":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154,"area":null},{"id":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2510.12276","title":"Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model","created":"2025-10-14","cited_by_count":134,"area":"vla"},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132,"area":"wm"},{"id":"2602.04770","title":"Generative Modeling via Drifting","created":"2026-02-04","cited_by_count":116,"area":null},{"id":"2505.15659","title":"FLARE: Robot Learning with Implicit World Modeling","created":"2025-05-21","cited_by_count":113,"area":"wm"},{"id":"2512.02012","title":"Improved Mean Flows: On the Challenges of Fastforward Generative Models","created":"2025-12-01","cited_by_count":110,"area":null},{"id":"2504.05741","title":"DDT: Decoupled Diffusion Transformer","created":"2025-04-08","cited_by_count":109,"area":"diffusion"},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2507.01467","title":"Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think","created":"2025-07-02","cited_by_count":102,"area":"diffusion"},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98,"area":"diffusion"},{"id":"2502.03444","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","created":"2025-02-05","cited_by_count":96,"area":"diffusion"},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96,"area":"wm"},{"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":"2510.15301","title":"Latent Diffusion Model without Variational Autoencoder","created":"2025-10-17","cited_by_count":88,"area":"diffusion"},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2511.20645","title":"PixelDiT: Pixel Diffusion Transformers for Image Generation","created":"2025-11-25","cited_by_count":83,"area":"diffusion"},{"id":"2507.23268","title":"PixNerd: Pixel Neural Field Diffusion","created":"2025-07-31","cited_by_count":82,"area":"diffusion"},{"id":"2502.20388","title":"Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation","created":"2025-02-27","cited_by_count":71,"area":null},{"id":"2506.09027","title":"Diffuse and Disperse: Image Generation with Representation Regularization","created":"2025-06-10","cited_by_count":70,"area":"diffusion"},{"id":"2509.22642","title":"WoW: Towards a World omniscient World model Through Embodied Interaction","created":"2025-09-26","cited_by_count":67,"area":"wm"},{"id":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2511.19365","title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","created":"2025-11-24","cited_by_count":60,"area":"diffusion"},{"id":"2504.08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","created":"2025-04-11","cited_by_count":57,"area":null},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2505.02831","title":"No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves","created":"2025-05-05","cited_by_count":56,"area":"diffusion"},{"id":"2506.00045","title":"ACE-Step: A Step Towards Music Generation Foundation Model","created":"2025-05-28","cited_by_count":56,"area":"diffusion"},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53,"area":"diffusion"},{"id":"2601.22158","title":"One-step Latent-free Image Generation with Pixel Mean Flows","created":"2026-01-29","cited_by_count":53,"area":null},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52,"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":"2511.13649","title":"Distribution Matching Distillation Meets Reinforcement Learning","created":"2025-11-17","cited_by_count":50,"area":"diffusion"},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49,"area":null},{"id":"2508.00413","title":"DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space","created":"2025-08-01","cited_by_count":47,"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":"2412.06016","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","created":"2024-12-08","cited_by_count":44,"area":"diffusion"},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41,"area":"lr"},{"id":"2510.04333","title":"RAP: 3D Rasterization Augmented End-to-End Planning","created":"2025-10-05","cited_by_count":41,"area":"driving"},{"id":"2510.20771","title":"AlphaFlow: Understanding and Improving MeanFlow Models","created":"2025-10-23","cited_by_count":41,"area":"diffusion"},{"id":"2606.19531","title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","created":"2026-06-17","cited_by_count":38,"area":"wm"},{"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":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2604.28190","title":"Representation Fr\\'echet Loss for Visual Generation","created":"2026-04-30","cited_by_count":37,"area":null},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36,"area":null},{"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":"2510.27607","title":"Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model","created":"2025-10-31","cited_by_count":36,"area":"wm"},{"id":"2602.11401","title":"Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image Generation","created":"2026-02-11","cited_by_count":36,"area":"diffusion"},{"id":"2502.06805","title":"Efficient Diffusion Models: A Survey","created":"2025-02-03","cited_by_count":35,"area":"diffusion"},{"id":"2510.25616","title":"Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization","created":"2025-10-29","cited_by_count":35,"area":"mllm"},{"id":"2509.04394","title":"Transition Models: Rethinking the Generative Learning Objective","created":"2025-09-04","cited_by_count":34,"area":"diffusion"},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34,"area":null},{"id":"2502.12154","title":"Diffusion Models without Classifier-free Guidance","created":"2025-02-17","cited_by_count":33,"area":"diffusion"},{"id":"2503.10772","title":"FlowTok: Flowing Seamlessly Across Text and Image Tokens","created":"2025-03-13","cited_by_count":33,"area":null},{"id":"2503.18414","title":"U-REPA: Aligning Diffusion U-Nets to ViTs","created":"2025-03-24","cited_by_count":32,"area":"diffusion"},{"id":"2510.03206","title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","created":"2025-10-03","cited_by_count":32,"area":"lr"},{"id":"2603.06507","title":"Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis","created":"2026-03-06","cited_by_count":31,"area":"diffusion"},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2511.07399","title":"StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation","created":"2025-11-10","cited_by_count":30,"area":"diffusion"},{"id":"2601.09881","title":"Transition Matching Distillation for Fast Video Generation","created":"2026-01-14","cited_by_count":30,"area":"diffusion"},{"id":"2506.05350","title":"Contrastive Flow Matching","created":"2025-06-05","cited_by_count":29,"area":"diffusion"},{"id":"2510.14974","title":"pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation","created":"2025-10-16","cited_by_count":29,"area":null},{"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":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27,"area":null},{"id":"2503.18211","title":"SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction","created":"2025-03-23","cited_by_count":27,"area":null},{"id":"2504.11427","title":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","created":"2025-04-15","cited_by_count":25,"area":"diffusion"},{"id":"2503.06132","title":"USP: Unified Self-Supervised Pretraining for Image Generation and Understanding","created":"2025-03-08","cited_by_count":24,"area":"diffusion"},{"id":"2510.11712","title":"DiT360: High-Fidelity Panoramic Image Generation via Hybrid Training","created":"2025-10-13","cited_by_count":24,"area":null},{"id":"2510.12586","title":"There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training","created":"2025-10-14","cited_by_count":24,"area":"diffusion"},{"id":"2605.11755","title":"One-Step Generative Modeling via Wasserstein Gradient Flows","created":"2026-05-12","cited_by_count":24,"area":"diffusion"},{"id":"2501.15417","title":"AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement","created":"2025-01-26","cited_by_count":23,"area":null},{"id":"2503.01103","title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2505.18584","title":"Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations","created":"2025-05-24","cited_by_count":23,"area":"diffusion"},{"id":"2510.10575","title":"UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation","created":"2025-10-12","cited_by_count":23,"area":null},{"id":"2503.08250","title":"Aligning Text to Image in Diffusion Models is Easier Than You Think","created":"2025-03-11","cited_by_count":22,"area":"diffusion"},{"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":"2501.04765","title":"TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training","created":"2025-01-08","cited_by_count":21,"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":"2506.05289","title":"Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model","created":"2025-06-05","cited_by_count":20,"area":null},{"id":"2507.15856","title":"Latent Denoising Makes Good Tokenizers","created":"2025-07-21","cited_by_count":20,"area":null},{"id":"2509.14181","title":"Bridging Past and Future: Distribution-Aware Alignment for Time Series Forecasting","created":"2025-09-17","cited_by_count":20,"area":null},{"id":"2510.24474","title":"Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling","created":"2025-10-28","cited_by_count":20,"area":null},{"id":"2601.21406","title":"Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation","created":"2026-01-29","cited_by_count":20,"area":null},{"id":"2410.15371","title":"FrameBridge: Improving Image-to-Video Generation with Bridge Models","created":"2024-10-20","cited_by_count":19,"area":"diffusion"},{"id":"2501.02576","title":"DepthMaster: Taming Diffusion Models for Monocular Depth Estimation","created":"2025-01-05","cited_by_count":19,"area":"diffusion"},{"id":"2503.24026","title":"HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation","created":"2025-03-31","cited_by_count":19,"area":null},{"id":"2502.05743","title":"Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling","created":"2025-02-09","cited_by_count":18,"area":"diffusion"},{"id":"2509.24526","title":"CMT: Mid-Training for Efficient Learning of Consistency, Mean Flow, and Flow Map Models","created":"2025-09-29","cited_by_count":18,"area":"diffusion"},{"id":"2510.01378","title":"Selective Underfitting in Diffusion Models","created":"2025-10-01","cited_by_count":18,"area":"diffusion"},{"id":"2510.23588","title":"FARMER: Flow AutoRegressive Transformer over Pixels","created":"2025-10-27","cited_by_count":18,"area":null},{"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":"2604.24763","title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","created":"2026-04-27","cited_by_count":18,"area":null},{"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"}],"next_cursor":"100"}