{"total":131,"rows":[{"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":"2604.28190","title":"Representation Fr\\'echet Loss for Visual Generation","created":"2026-04-30","cited_by_count":37,"area":null},{"id":"2603.27538","title":"LongCat-Next: Lexicalizing Modalities as Discrete Tokens","created":"2026-03-29","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":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2512.19693","title":"The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding","created":"2025-12-22","cited_by_count":22,"area":null},{"id":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21,"area":null},{"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":"2511.19428","title":"Flow Map Distillation Without Data","created":"2025-11-24","cited_by_count":14,"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":"2511.22475","title":"Adversarial Flow Models","created":"2025-11-27","cited_by_count":12,"area":null},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"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":"2510.27688","title":"Continuous Autoregressive Language Models","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2511.23386","title":"VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2604.02097","title":"LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model","created":"2026-04-02","cited_by_count":8,"area":null},{"id":"2605.12964","title":"Asymmetric Flow Models","created":"2026-05-13","cited_by_count":8,"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":"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":"2601.05116","title":"From Rays to Projections: Better Inputs for Feed-Forward View Synthesis","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2601.05328","title":"Bi-Orthogonal Factor Decomposition for Vision Transformers","created":"2026-01-08","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":"2604.19141","title":"Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation","created":"2026-04-21","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":"2602.14041","title":"BitDance: Scaling Autoregressive Generative Models with Binary Tokens","created":"2026-02-15","cited_by_count":4,"area":null},{"id":"2605.31604","title":"Representation Forcing for Bottleneck-Free Unified Multimodal Models","created":"2026-05-29","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":"2512.20052","title":"Learning Skills from Action-Free Videos","created":"2025-12-23","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":"2603.25819","title":"Geo$^\\textbf{2}$: Geometry-Guided Cross-view Geo-Localization and Image Synthesis","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2605.05781","title":"Steering Visual Generation in Unified Multimodal Models with Understanding Supervision","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":"2605.18613","title":"SAME: A Semantically-Aligned Music Autoencoder","created":"2026-05-18","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":"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":"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":"2608.05000","title":"Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes","created":"2026-08-05","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":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2603.14186","title":"Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models","created":"2026-03-15","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":"2604.18168","title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","created":"2026-04-20","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":"2606.14700","title":"RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.14981","title":"Inference-time Policy Steering via Vision and Touch","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2606.22527","title":"Trajectory Forcing: Structure-First Generation with Controllable Semantic Trajectories","created":"2026-06-21","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":"2608.20334","title":"Exploring the Performance Frontier of Compact Unified Image Generation Models","created":"2026-08-20","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":"2512.19311","title":"MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2601.14256","title":"Implicit Neural Representation Facilitates Unified Universal Vision Encoding","created":"2026-01-20","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":"2603.02667","title":"Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation","created":"2026-03-03","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},{"id":"2604.07340","title":"TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.24959","title":"CoreFlow: Low-Rank Matrix Generative Models","created":"2026-04-27","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":"2605.15592","title":"Efficient Image Synthesis with Sphere Latent Encoder","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.18115","title":"WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens","created":"2026-05-18","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":"2605.23531","title":"PixIE: Prompted Pixel-Space Low-Light Image Enhancement","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.00514","title":"Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2606.06357","title":"F3-Tokenizer: Taming Audio Autoencoder Latents for Understanding and Generation","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.26016","title":"MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.27371","title":"Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2606.32039","title":"GEAR: Guided End-to-End AutoRegression for Image Synthesis","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2608.08676","title":"UniSpace: Unified Visual Representation and Scalable Multimodal Modeling","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2609.31620","title":"FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2609.35763","title":"Unifying Distributional Training for One-Step Visual Generation","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2602.04883","title":"Protein Autoregressive Modeling via Multiscale Structure Generation","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.13249","title":"A Systematic Evaluation of Co-folding Model Representations for Small-Molecule Learning","created":"2026-02-02","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":"2603.23488","title":"One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.01053","title":"PHASOR: Anatomy- and Phase-Consistent Volumetric Diffusion for CT Virtual Contrast Enhancement","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.08837","title":"Discrete Meanflow Training Curriculum","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.16362","title":"SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning","created":"2026-03-20","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":"2605.06140","title":"SymDrift: One-Shot Generative Modeling under Symmetries","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.14821","title":"HDRFace: Rethinking Face Restoration with High-Dimensional Representation","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":"2605.18599","title":"Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.19622","title":"UniRefiner: Teaching Pre-trained ViTs to Self-Dispose Dross via Contrastive Register","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.26230","title":"Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.26449","title":"Cross-scale Aligned Supervision for Training GANs","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.27320","title":"Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2606.27978","title":"Parallel Rollout Approximation for Pixel-Space Autoregressive Image Generation","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.30705","title":"Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2607.22148","title":"dRAE: Representation Autoencoder with Hyper-Spherical Codes","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.23855","title":"OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.29363","title":"Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.00626","title":"Where Does Generative Difficulty Reside? An Empirical Study of Target Representations","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.08832","title":"Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.23864","title":"AffineTok: Semantic Affine Consistency for Diffusion-Friendly Visual Tokenizer","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.04174","title":"Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":"100"}