{"total":217,"rows":[{"id":"2503.22020","title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","created":"2025-03-27","cited_by_count":451,"area":"lr"},{"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":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259,"area":"diffusion"},{"id":"2512.13030","title":"Motus: A Unified Latent Action World Model","created":"2025-12-15","cited_by_count":251,"area":"wm"},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217,"area":"diffusion"},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185,"area":"wm"},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175,"area":null},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170,"area":"diffusion"},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168,"area":null},{"id":"2501.18427","title":"SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer","created":"2025-01-30","cited_by_count":165,"area":"lr"},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163,"area":null},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123,"area":null},{"id":"2506.24113","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving","created":"2025-06-30","cited_by_count":117,"area":"wm"},{"id":"2505.18875","title":"Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation","created":"2025-05-24","cited_by_count":106,"area":"diffusion"},{"id":"2412.17808","title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders","created":"2024-12-23","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":"2509.24695","title":"SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer","created":"2025-09-29","cited_by_count":94,"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":"2503.09641","title":"SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation","created":"2025-03-12","cited_by_count":87,"area":"diffusion"},{"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":"2412.15205","title":"FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching","created":"2024-12-19","cited_by_count":80,"area":"diffusion"},{"id":"2502.14831","title":"Improving the Diffusability of Autoencoders","created":"2025-02-20","cited_by_count":80,"area":"diffusion"},{"id":"2503.18352","title":"Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models","created":"2025-03-24","cited_by_count":65,"area":"diffusion"},{"id":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"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":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2506.00045","title":"ACE-Step: A Step Towards Music Generation Foundation Model","created":"2025-05-28","cited_by_count":56,"area":"diffusion"},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2504.01934","title":"ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement","created":"2025-04-02","cited_by_count":54,"area":null},{"id":"2510.15857","title":"BLIP3o-NEXT: Next Frontier of Native Image Generation","created":"2025-10-17","cited_by_count":54,"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":"2511.18822","title":"DiP: Taming Diffusion Models in Pixel Space","created":"2025-11-24","cited_by_count":48,"area":"diffusion"},{"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":"2505.23661","title":"OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation","created":"2025-05-29","cited_by_count":46,"area":null},{"id":"2507.23278","title":"UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing","created":"2025-07-31","cited_by_count":44,"area":null},{"id":"2503.11056","title":"Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization","created":"2025-03-14","cited_by_count":36,"area":"diffusion"},{"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":"2605.10730","title":"Qwen-Image-2.0 Technical Report","created":"2026-05-11","cited_by_count":36,"area":null},{"id":"2509.04394","title":"Transition Models: Rethinking the Generative Learning Objective","created":"2025-09-04","cited_by_count":34,"area":"diffusion"},{"id":"2412.01819","title":"Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis","created":"2024-12-02","cited_by_count":33,"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":"2503.16430","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation","created":"2025-03-20","cited_by_count":29,"area":null},{"id":"2510.06590","title":"Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer","created":"2025-10-08","cited_by_count":28,"area":null},{"id":"2503.03206","title":"An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models","created":"2025-03-05","cited_by_count":26,"area":"diffusion"},{"id":"2503.16302","title":"Unleashing Vecset Diffusion Model for Fast Shape Generation","created":"2025-03-20","cited_by_count":26,"area":"diffusion"},{"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":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2505.14708","title":"DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance","created":"2025-05-17","cited_by_count":22,"area":"diffusion"},{"id":"2509.25079","title":"UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation","created":"2025-09-29","cited_by_count":20,"area":"diffusion"},{"id":"2602.17270","title":"Unified Latents (UL): How to train your latents","created":"2026-02-19","cited_by_count":20,"area":"diffusion"},{"id":"2507.02608","title":"Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation","created":"2025-07-03","cited_by_count":19,"area":"diffusion"},{"id":"2512.03018","title":"AutoBrep: Autoregressive B-Rep Generation with Unified Topology and Geometry","created":"2025-12-02","cited_by_count":17,"area":null},{"id":"2512.05150","title":"TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows","created":"2025-12-03","cited_by_count":17,"area":null},{"id":"2506.16349","title":"Watermarking Autoregressive Image Generation","created":"2025-06-19","cited_by_count":16,"area":"safety"},{"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":"2509.25182","title":"DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder","created":"2025-09-29","cited_by_count":16,"area":null},{"id":"2503.19462","title":"AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset","created":"2025-03-25","cited_by_count":15,"area":"diffusion"},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2602.02493","title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","created":"2026-02-02","cited_by_count":14,"area":"diffusion"},{"id":"2503.07197","title":"Effective and Efficient Masked Image Generation Models","created":"2025-03-10","cited_by_count":13,"area":"diffusion"},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2504.10567","title":"H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Models","created":"2025-04-14","cited_by_count":13,"area":"diffusion"},{"id":"2504.14470","title":"Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2507.04947","title":"DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2511.16175","title":"Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight","created":"2025-11-20","cited_by_count":13,"area":"vla"},{"id":"2601.07823","title":"Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions","created":"2026-01-12","cited_by_count":13,"area":"wm"},{"id":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","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":"2507.09984","title":"Latent Diffusion Models with Masked AutoEncoders","created":"2025-07-14","cited_by_count":11,"area":"diffusion"},{"id":"2512.05394","title":"Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability","created":"2025-12-05","cited_by_count":11,"area":"diffusion"},{"id":"2501.12976","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation","created":"2025-01-22","cited_by_count":10,"area":"diffusion"},{"id":"2511.22249","title":"Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective","created":"2025-11-27","cited_by_count":10,"area":"diffusion"},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"id":"2604.04913","title":"A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens","created":"2026-04-06","cited_by_count":10,"area":"wm"},{"id":"2507.07997","title":"MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization","created":"2025-07-10","cited_by_count":9,"area":null},{"id":"2509.01109","title":"GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation","created":"2025-09-01","cited_by_count":9,"area":null},{"id":"2601.17830","title":"SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training","created":"2026-01-25","cited_by_count":9,"area":"diffusion"},{"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":"2605.12013","title":"L2P: Unlocking Latent Potential for Pixel Generation","created":"2026-05-12","cited_by_count":9,"area":"diffusion"},{"id":"2508.04663","title":"HierarchicalPrune: Position-Aware Compression for Large-Scale Diffusion Models","created":"2025-08-06","cited_by_count":8,"area":"diffusion"},{"id":"2509.23736","title":"HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation","created":"2025-09-28","cited_by_count":8,"area":null},{"id":"2509.25180","title":"DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space","created":"2025-09-29","cited_by_count":8,"area":"diffusion"},{"id":"2512.04810","title":"EMMA: Efficient Multimodal Understanding, Generation, and Editing with a Unified Architecture","created":"2025-12-04","cited_by_count":8,"area":null},{"id":"2602.12322","title":"ForeAct: Steering Your VLA with Efficient Visual Foresight Planning","created":"2026-02-12","cited_by_count":8,"area":"vla"},{"id":"2606.27760","title":"PixelU: A U-Shaped Transformer for Efficient End-to-End Pixel Diffusion","created":"2026-06-26","cited_by_count":8,"area":"diffusion"},{"id":"2504.12259","title":"VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate","created":"2025-04-16","cited_by_count":7,"area":"diffusion"},{"id":"2505.19151","title":"SRDiffusion: Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation","created":"2025-05-25","cited_by_count":7,"area":"diffusion"},{"id":"2507.10547","title":"Quantize-then-Rectify: Efficient VQ-VAE Training","created":"2025-07-14","cited_by_count":7,"area":null},{"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":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2601.22904","title":"Hyperspherical Autoencoder for High-Fidelity Image Reconstruction and Generation","created":"2026-01-30","cited_by_count":7,"area":"diffusion"},{"id":"2603.14645","title":"Spectrum Matching: a Unified Perspective for Superior Diffusability in Latent Diffusion","created":"2026-03-15","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":"2503.08737","title":"Representing 3D Shapes With 64 Latent Vectors for 3D Diffusion Models","created":"2025-03-11","cited_by_count":6,"area":"diffusion"},{"id":"2506.09193","title":"LaDCast: A Latent Diffusion Model for Medium-Range Ensemble Weather Forecasting","created":"2025-06-10","cited_by_count":6,"area":"diffusion"},{"id":"2512.07778","title":"Distribution Matching Variational AutoEncoder","created":"2025-12-08","cited_by_count":6,"area":null}],"next_cursor":"100"}