{"total":98,"rows":[{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703,"area":"diffusion"},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2403.17377","title":"Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance","created":"2024-03-26","cited_by_count":113,"area":"diffusion"},{"id":"2504.05741","title":"DDT: Decoupled Diffusion Transformer","created":"2025-04-08","cited_by_count":109,"area":"diffusion"},{"id":"2507.01467","title":"Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think","created":"2025-07-02","cited_by_count":102,"area":"diffusion"},{"id":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94,"area":"diffusion"},{"id":"2510.15301","title":"Latent Diffusion Model without Variational Autoencoder","created":"2025-10-17","cited_by_count":88,"area":"diffusion"},{"id":"2505.02831","title":"No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves","created":"2025-05-05","cited_by_count":56,"area":"diffusion"},{"id":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"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":"2510.03206","title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","created":"2025-10-03","cited_by_count":32,"area":"lr"},{"id":"2503.08685","title":"\"Principal Components\" Enable A New Language of Images","created":"2025-03-11","cited_by_count":27,"area":null},{"id":"2510.12586","title":"There is No VAE: End-to-End Pixel-Space Generative Modeling via Self-Supervised Pre-training","created":"2025-10-14","cited_by_count":24,"area":"diffusion"},{"id":"2502.20313","title":"FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction","created":"2025-02-27","cited_by_count":23,"area":null},{"id":"2506.08257","title":"Highly Compressed Tokenizer Can Generate Without Training","created":"2025-06-09","cited_by_count":18,"area":null},{"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":"2512.24176","title":"Guiding a Diffusion Transformer with the Internal Dynamics of Itself","created":"2025-12-30","cited_by_count":16,"area":"diffusion"},{"id":"2412.16326","title":"When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization","created":"2024-12-20","cited_by_count":15,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2504.17660","title":"Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models","created":"2025-04-24","cited_by_count":13,"area":null},{"id":"2507.08980","title":"Learning Diffusion Models with Flexible Representation Guidance","created":"2025-07-11","cited_by_count":13,"area":"diffusion"},{"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":"2509.12474","title":"Image Tokenizer Needs Post-Training","created":"2025-09-15","cited_by_count":12,"area":null},{"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":"2503.08253","title":"SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models","created":"2025-03-11","cited_by_count":11,"area":"diffusion"},{"id":"2506.05127","title":"PixCell: A generative foundation model for digital histopathology images","created":"2025-06-05","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":"2509.10140","title":"Scalable Training for Vector-Quantized Networks with 100% Codebook Utilization","created":"2025-09-12","cited_by_count":10,"area":null},{"id":"2509.21592","title":"What Happens Next? Anticipating Future Motion by Generating Point Trajectories","created":"2025-09-25","cited_by_count":10,"area":null},{"id":"2504.11295","title":"Autoregressive Distillation of Diffusion Transformers","created":"2025-04-15","cited_by_count":9,"area":"diffusion"},{"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":"2412.07767","title":"Learning Visual Generative Priors without Text","created":"2024-12-10","cited_by_count":8,"area":null},{"id":"2505.12742","title":"MVAR: Visual Autoregressive Modeling with Scale and Spatial Markovian Conditioning","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2602.06964","title":"Learning a Generative Meta-Model of LLM Activations","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2511.14063","title":"Semantic Context Matters: Improving Conditioning for Autoregressive Models","created":"2025-11-18","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":"2504.10188","title":"Efficient Generative Model Training via Embedded Representation Warmup","created":"2025-04-14","cited_by_count":6,"area":null},{"id":"2505.11196","title":"DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling","created":"2025-05-16","cited_by_count":6,"area":"diffusion"},{"id":"2512.20619","title":"SemanticGen: Video Generation in Semantic Space","created":"2025-12-23","cited_by_count":6,"area":"diffusion"},{"id":"2604.12887","title":"VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2604.15521","title":"Frequency-Aware Flow Matching for High-Quality Image Generation","created":"2026-04-16","cited_by_count":6,"area":"diffusion"},{"id":"2502.07160","title":"HDCompression: Hybrid-Diffusion Image Compression for Ultra-Low Bitrates","created":"2025-02-11","cited_by_count":5,"area":"diffusion"},{"id":"2505.19089","title":"Plug-and-Play Context Feature Reuse for Efficient Masked Generation","created":"2025-05-25","cited_by_count":5,"area":"inference"},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2512.11225","title":"VFMF: World Modeling by Forecasting Vision Foundation Model Features","created":"2025-12-12","cited_by_count":5,"area":"wm"},{"id":"2603.04239","title":"DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers","created":"2026-03-04","cited_by_count":5,"area":"diffusion"},{"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":"2405.11738","title":"Diffusion Models for Generating Ballistic Spacecraft Trajectories","created":"2024-05-20","cited_by_count":4,"area":"diffusion"},{"id":"2511.18838","title":"FVAR: Visual Autoregressive Modeling via Next Focus Prediction","created":"2025-11-24","cited_by_count":4,"area":null},{"id":"2505.10999","title":"Conditioning Residuals for Diffusion Models via Representation Feedback","created":"2025-05-16","cited_by_count":3,"area":"diffusion"},{"id":"2507.12318","title":"Compositional Discrete Latent Code for High Fidelity, Productive Diffusion Models","created":"2025-07-16","cited_by_count":3,"area":"diffusion"},{"id":"2510.06529","title":"VUGEN: Visual Understanding priors for GENeration","created":"2025-10-08","cited_by_count":3,"area":"mllm"},{"id":"2510.11330","title":"Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap","created":"2025-10-13","cited_by_count":3,"area":"diffusion"},{"id":"2510.21167","title":"Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation","created":"2025-10-24","cited_by_count":3,"area":"diffusion"},{"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":"2501.00873","title":"Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation","created":"2025-01-01","cited_by_count":2,"area":"diffusion"},{"id":"2601.14671","title":"Mirai: Autoregressive Visual Generation Needs Foresight","created":"2026-01-21","cited_by_count":2,"area":null},{"id":"2601.22468","title":"Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector","created":"2026-01-30","cited_by_count":2,"area":"diffusion"},{"id":"2602.16664","title":"Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge","created":"2026-02-18","cited_by_count":2,"area":null},{"id":"2401.10721","title":"Generative Model for Constructing Reaction Path from Initial to Final States","created":"2024-01-19","cited_by_count":1,"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":"2509.15591","title":"Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.17313","title":"Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2601.04056","title":"Bridging the Discrete-Continuous Gap: Unified Multimodal Generation via Coupled Manifold Discrete Absorbing Diffusion","created":"2026-01-07","cited_by_count":1,"area":"diffusion"},{"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":"2602.03339","title":"Composable Visual Tokenizers with Generator-Free Diagnostics of Learnability","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.06993","title":"AdaGen: Learning Adaptive Policy for Image Synthesis","created":"2026-03-07","cited_by_count":1,"area":"diffusion"},{"id":"2603.15132","title":"WiT: Waypoint Diffusion Transformers for Alleviating Trajectory Conflict in Pixel-Space Image Generation","created":"2026-03-16","cited_by_count":1,"area":"diffusion"},{"id":"2603.21611","title":"SARe: Structure-Aware Generative 3D Fragment Reassembly","created":"2026-03-23","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":"2605.07693","title":"Toward Better Geometric Representations for Molecule Generative Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.10523","title":"Improving Human Image Animation via Semantic Representation Alignment","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.27192","title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","created":"2026-06-25","cited_by_count":1,"area":null},{"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":"2408.16613","title":"Blending Low and High-Level Semantics of Time Series for Better Masked Time Series Generation","created":"2024-08-29","cited_by_count":0,"area":null},{"id":"2504.21368","title":"Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2505.16798","title":"SEED: Speaker Embedding Enhancement Diffusion Model","created":"2025-05-22","cited_by_count":0,"area":"diffusion"},{"id":"2506.18164","title":"CDG-MAE: Cross-view Masked Modeling using Diffusion Generated Views","created":"2025-06-22","cited_by_count":0,"area":"diffusion"},{"id":"2509.15342","title":"LowDiff: Efficient Diffusion Sampling with Low-Resolution Condition","created":"2025-09-18","cited_by_count":0,"area":"diffusion"},{"id":"2511.16870","title":"Align & Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2512.06421","title":"Rethinking Training Dynamics in Scale-wise Autoregressive Generation","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2605.22133","title":"Atom-level Protein Representation Learning Improves Protein Structure Prediction","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.27343","title":"Towards Controllable Image Generation through Representation-Conditioned Diffusion Models","created":"2026-05-26","cited_by_count":0,"area":"diffusion"},{"id":"2605.27495","title":"Representation-Conditioned Diffusion Models for Guided Training Data Generation","created":"2026-05-26","cited_by_count":0,"area":"diffusion"},{"id":"2605.27696","title":"Structure over Pixels: Learning Variable-Length Visual Programs","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.20084","title":"Residual-Space Evolutionary Optimization via Flow-based Generative Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.29451","title":"The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training","created":"2026-06-28","cited_by_count":0,"area":"safety"},{"id":"2606.30147","title":"T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation","created":"2026-06-29","cited_by_count":0,"area":"wm"},{"id":"2608.08115","title":"SUMI: Scalable Unified Model for 3D Point Cloud Inference","created":"2026-08-08","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":"2609.34732","title":"What Visual Generators Need from Teachers: Rethinking Representation Alignment","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.39635","title":"SAGE: Salient Factor Discovery and Generation with Visual Foundation Representations","created":"2026-09-30","cited_by_count":0,"area":null},{"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":"2610.14136","title":"Correction Training for Diffusion Models","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.20533","title":"Generative Representation Learning for Scalable Latent Tokenization","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}