{"total":165,"rows":[{"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":"2502.20321","title":"UniTok: A Unified Tokenizer for Visual Generation and Understanding","created":"2025-02-27","cited_by_count":153,"area":null},{"id":"2602.04770","title":"Generative Modeling via Drifting","created":"2026-02-04","cited_by_count":116,"area":null},{"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":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"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":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52,"area":null},{"id":"2509.07295","title":"Reconstruction Alignment Improves Unified Multimodal Models","created":"2025-09-08","cited_by_count":49,"area":null},{"id":"2604.28190","title":"Representation Fr\\'echet Loss for Visual Generation","created":"2026-04-30","cited_by_count":37,"area":null},{"id":"2605.10730","title":"Qwen-Image-2.0 Technical Report","created":"2026-05-11","cited_by_count":36,"area":null},{"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":"2503.10772","title":"FlowTok: Flowing Seamlessly Across Text and Image Tokens","created":"2025-03-13","cited_by_count":33,"area":null},{"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":"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":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27,"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":"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":"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":"2601.02204","title":"NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation","created":"2026-01-05","cited_by_count":14,"area":null},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2510.14630","title":"Adapting Self-Supervised Representations as a Latent Space for Efficient Generation","created":"2025-10-16","cited_by_count":13,"area":null},{"id":"2607.02375","title":"Representation Distribution Matching for One-Step Visual Generation","created":"2026-07-02","cited_by_count":11,"area":null},{"id":"2503.08354","title":"Robust Latent Matters: Boosting Image Generation with Sampling Error Synthesis","created":"2025-03-11","cited_by_count":10,"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":"2603.25743","title":"RefAlign: Representation Alignment for Reference-to-Video Generation","created":"2026-03-26","cited_by_count":10,"area":null},{"id":"2503.14494","title":"Deeply Supervised Flow-Based Generative Models","created":"2025-03-18","cited_by_count":9,"area":null},{"id":"2506.18882","title":"Light of Normals: Unified Feature Representation for Universal Photometric Stereo","created":"2025-06-23","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":"2510.04910","title":"Glocal Information Bottleneck for Time Series Imputation","created":"2025-10-06","cited_by_count":9,"area":null},{"id":"2602.09024","title":"Autoregressive Image Generation with Masked Bit Modeling","created":"2026-02-09","cited_by_count":9,"area":null},{"id":"2505.15197","title":"Intentional Gesture: Deliver Your Intentions with Gestures for Speech","created":"2025-05-21","cited_by_count":8,"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":"2605.12964","title":"Asymmetric Flow Models","created":"2026-05-13","cited_by_count":8,"area":null},{"id":"2506.00385","title":"MagiCodec: Simple Masked Gaussian-Injected Codec for High-Fidelity Reconstruction and Generation","created":"2025-05-31","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":"2511.14063","title":"Semantic Context Matters: Improving Conditioning for Autoregressive Models","created":"2025-11-18","cited_by_count":7,"area":null},{"id":"2512.04084","title":"SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2512.10953","title":"Bidirectional Normalizing Flow: From Data to Noise and Back","created":"2025-12-11","cited_by_count":7,"area":null},{"id":"2603.12267","title":"EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2605.30341","title":"GPIC: A Giant Permissive Image Corpus for Visual Generation","created":"2026-05-28","cited_by_count":7,"area":null},{"id":"2511.20565","title":"DINO-Tok: Adapting DINO for Visual Tokenizers","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2512.04483","title":"DeRA: Decoupled Representation Alignment for Video Tokenization","created":"2025-12-04","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":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2601.01535","title":"Improving Flexible Image Tokenizers for Autoregressive Image Generation","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2605.21573","title":"Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models","created":"2026-05-20","cited_by_count":6,"area":null},{"id":"2503.06671","title":"Emulating Self-attention with Convolution for Efficient Image Super-Resolution","created":"2025-03-09","cited_by_count":5,"area":null},{"id":"2505.23415","title":"Bidirectional predictive coding","created":"2025-05-29","cited_by_count":5,"area":null},{"id":"2509.24935","title":"Scalable GANs with Transformers","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2512.19271","title":"3SGen: Unified Subject, Style, and Structure-Driven Image Generation with Adaptive Task-specific Memory","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2601.03955","title":"ResTok: Learning Hierarchical Residuals in 1D Visual Tokenizers for Autoregressive Image Generation","created":"2026-01-07","cited_by_count":5,"area":null},{"id":"2601.15369","title":"OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation","created":"2026-01-21","cited_by_count":5,"area":null},{"id":"2603.06449","title":"CaTok: Taming Mean Flows for One-Dimensional Causal Image Tokenization","created":"2026-03-06","cited_by_count":5,"area":null},{"id":"2605.00503","title":"End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer","created":"2026-05-01","cited_by_count":5,"area":null},{"id":"2507.07867","title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2509.25187","title":"FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2509.25275","title":"VoiceBridge: General Speech Restoration with One-step Latent Bridge Models","created":"2025-09-28","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":"2605.19256","title":"Distribution Matching Distillation without Fake Score Network","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2607.27372","title":"Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generation","created":"2026-07-29","cited_by_count":4,"area":null},{"id":"2510.07961","title":"Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement","created":"2025-10-09","cited_by_count":3,"area":null},{"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":"2602.17682","title":"Duality Models: An Embarrassingly Simple One-step Generation Paradigm","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.20360","title":"Momentum Guidance: Plug-and-Play Guidance for Flow Models","created":"2026-02-23","cited_by_count":3,"area":null},{"id":"2603.03287","title":"Deep Sketch-Based 3D Modeling: A Survey","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2603.08590","title":"PRISM: Streaming Human Motion Generation with Per-Joint Latent Decomposition","created":"2026-03-09","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":"2605.06407","title":"WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.10780","title":"Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2606.15553","title":"Distilling Drifting Transformers with Representation Autoencoders","created":"2026-06-14","cited_by_count":3,"area":null},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2608.13556","title":"V-RAE: Rethinking Video Latent Spaces for Generation","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2506.05240","title":"Aligning Latent Spaces with Flow Priors","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2510.16791","title":"Personalized Image Filter: Mastering Your Photographic Style","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2601.05246","title":"Pixel-Perfect Visual Geometry Estimation","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.05887","title":"Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2603.15228","title":"HYDRA: Representation Harmonized Tokenization for Multimodal Generation and Understanding","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.16373","title":"Semantic One-Dimensional Tokenizer for Image Reconstruction and Generation","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.29634","title":"MacTok: Robust Continuous Tokenization for Image Generation","created":"2026-03-31","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":"2606.11096","title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.13289","title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2607.04311","title":"Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2607.26860","title":"Amortized Moment Matching for Visual Generation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2608.29335","title":"GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling","created":"2026-08-29","cited_by_count":2,"area":null},{"id":"2503.10096","title":"A Self-supervised Motion Representation for Portrait Video Generation","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2507.18405","title":"Iwin Transformer: Hierarchical Vision Transformer using Interleaved Windows","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2510.06673","title":"Heptapod: Language Modeling on Visual Signals","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2512.19311","title":"MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2602.03339","title":"Composable Visual Tokenizers with Generator-Free Diagnostics of Learnability","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.24262","title":"Forecasting with Guidance: Representation-Level Supervision for Time Series Forecasting","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2603.25249","title":"Semantic-Aware Prefix Learning for Token-Efficient Image Generation","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.01545","title":"RAE-AR: Taming Autoregressive Models with Representation Autoencoders","created":"2026-04-02","cited_by_count":1,"area":null}],"next_cursor":"100"}