{"total":52,"rows":[{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023,"area":"diffusion"},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295,"area":"diffusion"},{"id":"2412.10117","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","created":"2024-12-13","cited_by_count":288,"area":"diffusion"},{"id":"2505.17589","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","created":"2025-05-23","cited_by_count":150,"area":"diffusion"},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132,"area":"diffusion"},{"id":"2409.16211","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","created":"2024-09-24","cited_by_count":98,"area":"diffusion"},{"id":"2503.11056","title":"Flow to the Mode: Mode-Seeking Diffusion Autoencoders for State-of-the-Art Image Tokenization","created":"2025-03-14","cited_by_count":36,"area":"diffusion"},{"id":"2406.05551","title":"Autoregressive Diffusion Transformer for Text-to-Speech Synthesis","created":"2024-06-08","cited_by_count":34,"area":"diffusion"},{"id":"2505.16687","title":"One-Step Diffusion-Based Image Compression with Semantic Distillation","created":"2025-05-22","cited_by_count":26,"area":"diffusion"},{"id":"2406.02328","title":"SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models","created":"2024-06-04","cited_by_count":23,"area":"diffusion"},{"id":"2409.20255","title":"PerCo (SD): Open Perceptual Compression","created":"2024-09-30","cited_by_count":18,"area":"diffusion"},{"id":"2408.13893","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","created":"2024-08-25","cited_by_count":17,"area":"diffusion"},{"id":"2507.20454","title":"Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis","created":"2025-07-28","cited_by_count":15,"area":"diffusion"},{"id":"2410.03755","title":"Denoising with a Joint-Embedding Predictive Architecture","created":"2024-10-02","cited_by_count":14,"area":"diffusion"},{"id":"2412.14453","title":"Multimodal Latent Diffusion Model for Complex Sewing Pattern Generation","created":"2024-12-19","cited_by_count":12,"area":"diffusion"},{"id":"2510.24717","title":"Uniform Discrete Diffusion with Metric Path for Video Generation","created":"2025-10-28","cited_by_count":12,"area":"diffusion"},{"id":"2506.10962","title":"SpectralAR: Spectral Autoregressive Visual Generation","created":"2025-06-12","cited_by_count":11,"area":"diffusion"},{"id":"2511.18706","title":"CoD: A Diffusion Foundation Model for Image Compression","created":"2025-11-24","cited_by_count":10,"area":"diffusion"},{"id":"2506.15980","title":"Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization","created":"2025-06-19","cited_by_count":9,"area":"diffusion"},{"id":"2509.20060","title":"Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens","created":"2025-09-24","cited_by_count":7,"area":"diffusion"},{"id":"2505.01263","title":"FlowDubber: Movie Dubbing with LLM-based Semantic-aware Learning and Flow Matching based Voice Enhancing","created":"2025-05-02","cited_by_count":6,"area":"diffusion"},{"id":"2510.15446","title":"VDRive: Leveraging Reinforced VLA and Diffusion Policy for End-to-end Autonomous Driving","created":"2025-10-17","cited_by_count":5,"area":"diffusion"},{"id":"2410.23820","title":"Disentangling Disentangled Representations: Towards Improved Latent Units via Diffusion Models","created":"2024-10-31","cited_by_count":4,"area":"diffusion"},{"id":"2510.00351","title":"Flow Autoencoders are Effective Protein Tokenizers","created":"2025-09-30","cited_by_count":4,"area":"diffusion"},{"id":"2510.21805","title":"DiffGRM: Diffusion-based Generative Recommendation Model","created":"2025-10-21","cited_by_count":4,"area":"diffusion"},{"id":"2601.17124","title":"iFSQ: Improving FSQ for Image Generation with 1 Line of Code","created":"2026-01-23","cited_by_count":4,"area":"diffusion"},{"id":"2606.16255","title":"UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer","created":"2026-06-15","cited_by_count":4,"area":"diffusion"},{"id":"2507.22746","title":"Next Tokens Denoising for Speech Synthesis","created":"2025-07-30","cited_by_count":3,"area":"diffusion"},{"id":"2509.24708","title":"SenSE: Semantic-Aware High-Fidelity Universal Speech Enhancement","created":"2025-09-29","cited_by_count":3,"area":"diffusion"},{"id":"2602.04220","title":"Adaptive 1D Video Diffusion Autoencoder","created":"2026-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2604.13030","title":"Generative Refinement Networks for Visual Synthesis","created":"2026-04-14","cited_by_count":3,"area":"diffusion"},{"id":"2405.17016","title":"$\\text{Di}^2\\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation","created":"2024-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2409.17487","title":"Learning Quantized Adaptive Conditions for Diffusion Models","created":"2024-09-26","cited_by_count":1,"area":"diffusion"},{"id":"2503.05229","title":"Discrete Contrastive Learning for Diffusion Policies in Autonomous Driving","created":"2025-03-07","cited_by_count":1,"area":"diffusion"},{"id":"2511.11074","title":"Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image","created":"2025-11-14","cited_by_count":1,"area":"diffusion"},{"id":"2601.09239","title":"DSA-Tokenizer: Disentangled Semantic-Acoustic Tokenization via Flow Matching-based Hierarchical Fusion","created":"2026-01-14","cited_by_count":1,"area":"diffusion"},{"id":"2602.18896","title":"Beyond Stationarity: Rethinking Codebook Collapse in Vector Quantization","created":"2026-02-21","cited_by_count":1,"area":"diffusion"},{"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":"2603.19232","title":"Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens","created":"2026-03-19","cited_by_count":1,"area":"diffusion"},{"id":"2606.09141","title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","created":"2026-06-08","cited_by_count":1,"area":"diffusion"},{"id":"2503.13859","title":"Less is More: Improving Motion Diffusion Models with Sparse Keyframes","created":"2025-03-18","cited_by_count":0,"area":"diffusion"},{"id":"2508.21153","title":"WaveLLDM: Design and Development of a Lightweight Latent Diffusion Model for Speech Enhancement and Restoration","created":"2025-08-28","cited_by_count":0,"area":"diffusion"},{"id":"2601.08450","title":"Decoding Order Matters in Autoregressive Speech Synthesis","created":"2026-01-13","cited_by_count":0,"area":"diffusion"},{"id":"2602.20731","title":"Communication-Inspired Tokenization for Structured Image Representations","created":"2026-02-24","cited_by_count":0,"area":"diffusion"},{"id":"2605.17085","title":"Taming Audio VAEs via Target-KL Regularization","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"id":"2606.09234","title":"End-to-End Training for Discrete Token LLM based TTS System","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"id":"2606.09962","title":"Optimality of FSQ Tokens for Continuous Diffusion for Categorical Data with Application to Text-to-Speech","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"id":"2606.29814","title":"Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis","created":"2026-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2607.09530","title":"FreyaTTS: A Compact Tokenizer-Free Flow-Matching Transformer for Turkish-First Speech Synthesis","created":"2026-07-10","cited_by_count":0,"area":"diffusion"},{"id":"2609.24691","title":"What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization","created":"2026-09-21","cited_by_count":0,"area":"diffusion"},{"id":"2610.15414","title":"OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation","created":"2026-10-11","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}