{"total":82,"rows":[{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175,"area":null},{"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":"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":"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":"2509.06155","title":"UniVerse-1: Unified Audio-Video Generation via Stitching of Experts","created":"2025-09-07","cited_by_count":61,"area":null},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"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":"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":"2605.10730","title":"Qwen-Image-2.0 Technical Report","created":"2026-05-11","cited_by_count":36,"area":null},{"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":"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":"2503.01103","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":"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":"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":"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":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"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":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12,"area":null},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"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":"2509.23736","title":"HieraTok: Multi-Scale Visual Tokenizer Improves Image Reconstruction and Generation","created":"2025-09-28","cited_by_count":8,"area":null},{"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":"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":"2512.07778","title":"Distribution Matching Variational AutoEncoder","created":"2025-12-08","cited_by_count":6,"area":null},{"id":"2505.19084","title":"Jodi: Unification of Visual Generation and Understanding via Joint Modeling","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2506.10395","title":"Pisces: An Auto-regressive Foundation Model for Image Understanding and Generation","created":"2025-06-12","cited_by_count":5,"area":null},{"id":"2502.11897","title":"DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2602.10095","title":"Causality in Video Diffusers is Separable from Denoising","created":"2026-02-10","cited_by_count":4,"area":null},{"id":"2602.14041","title":"BitDance: Scaling Autoregressive Generative Models with Binary Tokens","created":"2026-02-15","cited_by_count":4,"area":null},{"id":"2506.07863","title":"VIVAT: Virtuous Improving VAE Training through Artifact Mitigation","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2602.17682","title":"Duality Models: An Embarrassingly Simple One-step Generation Paradigm","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2605.05646","title":"MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2606.21781","title":"Physics-Preserving Latent Compression for Zero-Shot Resolution Transfer in 3D Turbulence","created":"2026-06-19","cited_by_count":3,"area":null},{"id":"2509.26282","title":"Reframing Generative Models for Physical Systems using Stochastic Interpolants","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2605.13565","title":"Qwen-Image-VAE-2.0 Technical Report","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.28272","title":"EchoAvatar: Real-time Generative Avatar Animation from Audio Streams","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2606.14700","title":"RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2607.26694","title":"Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2502.10475","title":"X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2506.06952","title":"LaTtE-Flow: Layerwise Timestep-Expert Flow-based Transformer","created":"2025-06-08","cited_by_count":1,"area":null},{"id":"2510.03049","title":"When and Where do Events Switch in Multi-Event Video Generation?","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2512.16910","title":"SFTok: Bridging the Performance Gap in Discrete Tokenizers","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2604.03064","title":"Gram-MMD: A Texture-Aware Metric for Image Realism Assessment","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.03619","title":"Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2604.07340","title":"TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2605.05331","title":"ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2607.19575","title":"VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2503.11591","title":"Pathology Image Compression with Pre-trained Autoencoders","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2506.07932","title":"Squeeze3D: Extreme Neural Compression with Latent Space Bridging","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.21731","title":"Exploring Image Generation via Mutually Exclusive Probability Spaces and Local Correlation Hypothesis","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.15724","title":"A Practical Investigation of Spatially-Controlled Image Generation with Transformers","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2508.07011","title":"HiMat: DiT-based Ultra-High Resolution SVBRDF Generation","created":"2025-08-09","cited_by_count":0,"area":null},{"id":"2510.17519","title":"MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2601.08807","title":"S3-CLIP: Video Super Resolution for Person-ReID","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2603.10702","title":"UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2603.19570","title":"Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2603.21073","title":"SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2604.01995","title":"MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.02134","title":"Video Generation with Predictive Latents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.14333","title":"InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation","created":"2026-05-14","cited_by_count":0,"area":null},{"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":"2607.07565","title":"Collaborative Synthetic Data Generation for Knowledge Transfer in Federated Learning","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2608.11254","title":"FarSky: Task-Aware Latent-Space Coupling for Generative Intra-Hour Solar Forecasting","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2609.01158","title":"Superposed Latent Autoencoder","created":"2026-09-01","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":"2609.34167","title":"Natural Image Autoencoder-Based fMRI Representations for Trait and State Prediction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.09670","title":"Quasi-Binarized Autoencoders: An Architecture-Independent Information Bottleneck for Medical Image Anomaly Detection","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12843","title":"APEX: Asynchronous Prefix Denoising for Extreme Compression","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14537","title":"Learn the Dynamics, Enforce the Physics: Generative Latent Operators for High-Dimensional Beam Evolution","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.15164","title":"TRIG: Toward Measuring Texture Realism in Image Generation","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.18284","title":"Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}