{"total":102,"rows":[{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2510.15301","title":"Latent Diffusion Model without Variational Autoencoder","created":"2025-10-17","cited_by_count":88,"area":"diffusion"},{"id":"2604.28190","title":"Representation Fr\\'echet Loss for Visual Generation","created":"2026-04-30","cited_by_count":37,"area":null},{"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":"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":"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":"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":"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"},{"id":"2512.24176","title":"Guiding a Diffusion Transformer with the Internal Dynamics of Itself","created":"2025-12-30","cited_by_count":16,"area":"diffusion"},{"id":"2602.02493","title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","created":"2026-02-02","cited_by_count":14,"area":"diffusion"},{"id":"2602.10099","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","created":"2026-02-10","cited_by_count":13,"area":"diffusion"},{"id":"2512.11749","title":"SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder","created":"2025-12-12","cited_by_count":12,"area":"diffusion"},{"id":"2602.05435","title":"Stable Velocity: A Variance Perspective on Flow Matching","created":"2026-02-05","cited_by_count":12,"area":"diffusion"},{"id":"2604.04406","title":"3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image","created":"2026-04-06","cited_by_count":11,"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":"2603.25743","title":"RefAlign: Representation Alignment for Reference-to-Video Generation","created":"2026-03-26","cited_by_count":10,"area":null},{"id":"2509.17562","title":"Visual Instruction Pretraining for Domain-Specific Foundation Models","created":"2025-09-22","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":"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":"2511.02607","title":"UniChange: Unifying Change Detection with Multimodal Large Language Model","created":"2025-11-04","cited_by_count":8,"area":"mllm"},{"id":"2507.23620","title":"DivControl: Knowledge Diversion for Controllable Image Generation","created":"2025-07-31","cited_by_count":7,"area":"diffusion"},{"id":"2511.14063","title":"Semantic Context Matters: Improving Conditioning for Autoregressive Models","created":"2025-11-18","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":"2602.04873","title":"Laminating Representation Autoencoders for Efficient Diffusion","created":"2026-02-04","cited_by_count":7,"area":"diffusion"},{"id":"2511.13019","title":"MeanFlow Transformers with Representation Autoencoders","created":"2025-11-17","cited_by_count":6,"area":"diffusion"},{"id":"2512.04483","title":"DeRA: Decoupled Representation Alignment for Video Tokenization","created":"2025-12-04","cited_by_count":6,"area":null},{"id":"2512.20619","title":"SemanticGen: Video Generation in Semantic Space","created":"2025-12-23","cited_by_count":6,"area":"diffusion"},{"id":"2605.06885","title":"Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment","created":"2026-05-07","cited_by_count":6,"area":"diffusion"},{"id":"2512.16636","title":"REGLUE Your Latents with Global and Local Semantics for Entangled Diffusion","created":"2025-12-18","cited_by_count":5,"area":"diffusion"},{"id":"2603.04239","title":"DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers","created":"2026-03-04","cited_by_count":5,"area":"diffusion"},{"id":"2606.24888","title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","created":"2026-06-23","cited_by_count":5,"area":"diffusion"},{"id":"2604.04050","title":"TORA: Topological Representation Alignment for 3D Shape Assembly","created":"2026-04-05","cited_by_count":4,"area":"diffusion"},{"id":"2605.03317","title":"AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers","created":"2026-05-05","cited_by_count":4,"area":"diffusion"},{"id":"2605.16949","title":"Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers","created":"2026-05-16","cited_by_count":4,"area":"diffusion"},{"id":"2607.03524","title":"Perceptual Flow Matching for Few-Step Generative Modeling","created":"2026-07-03","cited_by_count":4,"area":"diffusion"},{"id":"2509.20952","title":"Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive Remedy","created":"2025-09-25","cited_by_count":3,"area":"diffusion"},{"id":"2512.12386","title":"Speedrunning ImageNet Diffusion","created":"2025-12-13","cited_by_count":3,"area":"diffusion"},{"id":"2604.11331","title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","created":"2026-04-13","cited_by_count":3,"area":"diffusion"},{"id":"2608.13556","title":"V-RAE: Rethinking Video Latent Spaces for Generation","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2512.13840","title":"MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation","created":"2025-12-15","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":"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":"2605.21981","title":"RiT: Vanilla Diffusion Transformers Suffice in Representation Space","created":"2026-05-21","cited_by_count":2,"area":"diffusion"},{"id":"2605.22777","title":"DecQ: Detail-Condensing Queries for Enhanced Reconstruction and Generation in Representation Autoencoders","created":"2026-05-21","cited_by_count":2,"area":"diffusion"},{"id":"2606.08788","title":"MaskAlign: Token-Subset Representation Alignment for Efficient Diffusion Training","created":"2026-06-07","cited_by_count":2,"area":"diffusion"},{"id":"2606.11096","title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","created":"2026-06-09","cited_by_count":2,"area":null},{"id":"2606.27504","title":"ReWorld: Representation Learning for World Action Models","created":"2026-06-25","cited_by_count":2,"area":"wm"},{"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":"2511.22009","title":"StreamFlow: Theory, Algorithm, and Implementation for High-Efficiency Rectified Flow Generation","created":"2025-11-27","cited_by_count":1,"area":"diffusion"},{"id":"2512.10954","title":"Group Diffusion: Enhancing Image Generation by Unlocking Cross-Sample Collaboration","created":"2025-12-11","cited_by_count":1,"area":"diffusion"},{"id":"2512.12083","title":"RePack then Refine: Efficient Diffusion Transformer with Vision Foundation Model","created":"2025-12-12","cited_by_count":1,"area":"diffusion"},{"id":"2512.19311","title":"MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture","created":"2025-12-22","cited_by_count":1,"area":null},{"id":"2601.07773","title":"Self-transcendence: Is External Feature Guidance Indispensable for Accelerating Diffusion Transformer Training?","created":"2026-01-12","cited_by_count":1,"area":"diffusion"},{"id":"2603.21085","title":"Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion Models","created":"2026-03-22","cited_by_count":1,"area":"diffusion"},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2604.16114","title":"Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset","created":"2026-04-17","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":"2605.25941","title":"Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Models","created":"2026-05-25","cited_by_count":1,"area":"diffusion"},{"id":"2606.00583","title":"Improving Visual Representation Alignment Generation with GRPO","created":"2026-05-30","cited_by_count":1,"area":"diffusion"},{"id":"2606.05552","title":"Balancing Image Compression and Generation with Bootstrapped Tokenization","created":"2026-06-04","cited_by_count":1,"area":null},{"id":"2606.19662","title":"Learning When to Denoise: Optimizing Asynchronous Schedules for Latent Diffusion","created":"2026-06-18","cited_by_count":1,"area":"diffusion"},{"id":"2606.22568","title":"SeFi-Image: A Text-to-Image Foundation Model with Semantic-First Diffusion","created":"2026-06-21","cited_by_count":1,"area":"diffusion"},{"id":"2608.03082","title":"DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers","created":"2026-08-04","cited_by_count":1,"area":"diffusion"},{"id":"2608.13205","title":"HPSD: Hybrid-Policy Self-Distillation for Text-Image-to-Video Diffusion Models","created":"2026-08-13","cited_by_count":1,"area":"diffusion"},{"id":"2609.29102","title":"ELF-REG: Scaling Continuous Diffusion Language Models to Reasoning Tasks","created":"2026-09-24","cited_by_count":1,"area":"lr"},{"id":"2609.35763","title":"Unifying Distributional Training for One-Step Visual Generation","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2511.23342","title":"Overcoming the Curvature Bottleneck in MeanFlow","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.07062","title":"$\\mathrm{D}^\\mathrm{3}$-Predictor: Noise-Free Deterministic Diffusion for Dense Prediction","created":"2025-12-08","cited_by_count":0,"area":"diffusion"},{"id":"2603.19122","title":"Revisiting Autoregressive Models for Generative Image Classification","created":"2026-03-19","cited_by_count":0,"area":"diffusion"},{"id":"2604.17492","title":"Coevolving Representations in Joint Image-Feature Diffusion","created":"2026-04-19","cited_by_count":0,"area":"diffusion"},{"id":"2605.04547","title":"Stage-adaptive audio diffusion modeling","created":"2026-05-06","cited_by_count":0,"area":"diffusion"},{"id":"2605.10790","title":"Elucidating Representation Degradation Problem in Diffusion Model Training","created":"2026-05-11","cited_by_count":0,"area":"diffusion"},{"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":"2605.18714","title":"Semantic Generative Tuning for Unified Multimodal Models","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.17989","title":"Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2607.02508","title":"From SRA to Self-Flow: Data Augmentation or Self-Supervision?","created":"2026-07-02","cited_by_count":0,"area":"diffusion"},{"id":"2607.28581","title":"ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation","created":"2026-07-30","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":"2608.24068","title":"Representation Learning in Diffusion and Flow-based Model: An Application Aspect","created":"2026-08-25","cited_by_count":0,"area":"diffusion"},{"id":"2609.03563","title":"FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08253","title":"Revisiting Spectral Representations in Generative Diffusion Models","created":"2026-09-08","cited_by_count":0,"area":"diffusion"},{"id":"2609.24919","title":"PixelDiT2: Representation-Grounded Pixel Diffusion Transformers","created":"2026-09-21","cited_by_count":0,"area":"diffusion"},{"id":"2609.28473","title":"On the Diffusibility of High-Dimensional Latents","created":"2026-09-23","cited_by_count":0,"area":"diffusion"},{"id":"2609.28561","title":"CARE: Condition-Aware Representation Regularization for Diffusion Models","created":"2026-09-23","cited_by_count":0,"area":"diffusion"},{"id":"2609.29320","title":"Off-manifold robustness in synthesizer inversion with joint distribution flow matching","created":"2026-09-24","cited_by_count":0,"area":"diffusion"},{"id":"2609.32708","title":"One-Step Generative Modeling via Unbalanced Optimal Transport","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33895","title":"Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2609.34732","title":"What Visual Generators Need from Teachers: Rethinking Representation Alignment","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.35292","title":"Scaffold Then Internalize: Representation Injection for Diffusion Transformers","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.36348","title":"Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2610.00483","title":"PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.02203","title":"Embedding Prediction Helps Image Generation","created":"2026-10-01","cited_by_count":0,"area":"diffusion"},{"id":"2610.05711","title":"From Pixels, Without Pre-training: Joint Generative and Self-Supervised Representation Learning in One Model","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.11174","title":"IntactWorld: Joint World Modeling with Intact Features","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.12843","title":"APEX: Asynchronous Prefix Denoising for Extreme Compression","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.12978","title":"Learning Representations to Guide Pixel Diffusion Transformers","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.13322","title":"CoVA: Composing VAE Representations for Generative Learning","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.17466","title":"Efficient Fr\\'echet Distributional Decoder Alignment for Latent Generative Models","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":"100"}