{"total":85,"rows":[{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912,"area":"diffusion"},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625,"area":"diffusion"},{"id":"2505.19223","title":"LLaDA 1.5: Variance-Reduced Preference Optimization for Large Language Diffusion Models","created":"2025-05-25","cited_by_count":285,"area":"diffusion"},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259,"area":"diffusion"},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250,"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":"2505.15781","title":"dKV-Cache: The Cache for Diffusion Language Models","created":"2025-05-21","cited_by_count":143,"area":"diffusion"},{"id":"2508.09192","title":"Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing","created":"2025-08-08","cited_by_count":116,"area":"diffusion"},{"id":"2505.13389","title":"VSA: Faster Video Diffusion with Trainable Sparse Attention","created":"2025-05-19","cited_by_count":104,"area":"diffusion"},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88,"area":"diffusion"},{"id":"2510.09212","title":"Stable Video Infinity: Infinite-Length Video Generation with Error Recycling","created":"2025-10-10","cited_by_count":73,"area":"diffusion"},{"id":"2502.03930","title":"DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation","created":"2025-02-06","cited_by_count":57,"area":"diffusion"},{"id":"2508.10711","title":"NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale","created":"2025-08-14","cited_by_count":57,"area":"diffusion"},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53,"area":"diffusion"},{"id":"2510.08666","title":"dInfer: An Efficient Inference Framework for Diffusion Language Models","created":"2025-10-09","cited_by_count":37,"area":"diffusion"},{"id":"2501.01097","title":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","created":"2025-01-02","cited_by_count":33,"area":"diffusion"},{"id":"2508.13148","title":"MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models","created":"2025-08-18","cited_by_count":32,"area":"diffusion"},{"id":"2601.09881","title":"Transition Matching Distillation for Fast Video Generation","created":"2026-01-14","cited_by_count":30,"area":"diffusion"},{"id":"2504.11651","title":"70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)","created":"2025-04-15","cited_by_count":24,"area":"diffusion"},{"id":"2507.08801","title":"Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective","created":"2025-07-11","cited_by_count":22,"area":"diffusion"},{"id":"2510.13721","title":"NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching","created":"2025-10-15","cited_by_count":21,"area":"diffusion"},{"id":"2511.19269","title":"CDLM: Consistency Diffusion Language Models For Faster Sampling","created":"2025-11-24","cited_by_count":21,"area":"diffusion"},{"id":"2510.09094","title":"Dense2MoE: Restructuring Diffusion Transformer to MoE for Efficient Text-to-Image Generation","created":"2025-10-10","cited_by_count":16,"area":"diffusion"},{"id":"2510.17206","title":"Soft-Masked Diffusion Language Models","created":"2025-10-20","cited_by_count":16,"area":"diffusion"},{"id":"2503.17350","title":"Decouple and Track: Benchmarking and Improving Video Diffusion Transformers for Motion Transfer","created":"2025-03-21","cited_by_count":14,"area":"diffusion"},{"id":"2602.22661","title":"dLLM: Simple Diffusion Language Modeling","created":"2026-02-26","cited_by_count":14,"area":"diffusion"},{"id":"2606.25331","title":"Improved Large Language Diffusion Models","created":"2026-06-24","cited_by_count":14,"area":"diffusion"},{"id":"2502.02088","title":"Dual-IPO: Dual-Iterative Preference Optimization for Text-to-Video Generation","created":"2025-02-04","cited_by_count":13,"area":"diffusion"},{"id":"2503.06884","title":"Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help","created":"2025-03-10","cited_by_count":12,"area":"diffusion"},{"id":"2507.05963","title":"Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation","created":"2025-07-08","cited_by_count":12,"area":"diffusion"},{"id":"2503.00084","title":"InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation","created":"2025-02-28","cited_by_count":11,"area":"diffusion"},{"id":"2511.05007","title":"MoE-DP: An MoE-Enhanced Diffusion Policy for Robust Long-Horizon Robotic Manipulation with Skill Decomposition and Failure Recovery","created":"2025-11-07","cited_by_count":10,"area":"diffusion"},{"id":"2512.22234","title":"DiRL: An Efficient Post-Training Framework for Diffusion Language Models","created":"2025-12-23","cited_by_count":10,"area":"diffusion"},{"id":"2504.19669","title":"Multimodal Conditioned Diffusive Time Series Forecasting","created":"2025-04-28","cited_by_count":9,"area":"diffusion"},{"id":"2510.18087","title":"Planned Diffusion","created":"2025-10-20","cited_by_count":9,"area":"diffusion"},{"id":"2507.07510","title":"Divergence Minimization Preference Optimization for Diffusion Model Alignment","created":"2025-07-10","cited_by_count":8,"area":"diffusion"},{"id":"2510.08632","title":"Next Semantic Scale Prediction via Hierarchical Diffusion Language Models","created":"2025-10-08","cited_by_count":8,"area":"diffusion"},{"id":"2605.07820","title":"Scaling Categorical Flow Maps","created":"2026-05-08","cited_by_count":8,"area":"diffusion"},{"id":"2505.19261","title":"Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning","created":"2025-05-25","cited_by_count":7,"area":"diffusion"},{"id":"2507.22731","title":"GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation","created":"2025-07-30","cited_by_count":7,"area":"diffusion"},{"id":"2602.05859","title":"DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders","created":"2026-02-05","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":"2602.21472","title":"The Design Space of Tri-Modal Masked Diffusion Models","created":"2026-02-25","cited_by_count":6,"area":"diffusion"},{"id":"2510.02291","title":"Test-Time Anchoring for Discrete Diffusion Posterior Sampling","created":"2025-10-02","cited_by_count":5,"area":"diffusion"},{"id":"2504.08111","title":"POEM: Precise Object-level Editing via MLLM control","created":"2025-04-10","cited_by_count":4,"area":"diffusion"},{"id":"2601.16214","title":"CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback","created":"2026-01-22","cited_by_count":4,"area":"diffusion"},{"id":"2606.07080","title":"dots.tts Technical Report","created":"2026-06-05","cited_by_count":4,"area":"diffusion"},{"id":"2606.18702","title":"UniTemp: Unlocking Video Generation in Any Temporal Order via Bidirectional Distillation","created":"2026-06-17","cited_by_count":4,"area":"diffusion"},{"id":"2507.15249","title":"FreeCus: Free Lunch Subject-driven Customization in Diffusion Transformers","created":"2025-07-21","cited_by_count":3,"area":"diffusion"},{"id":"2509.13866","title":"Masked Diffusion Models as Energy Minimization","created":"2025-09-17","cited_by_count":3,"area":"diffusion"},{"id":"2511.17986","title":"Plan-X: Instruct Video Generation via Semantic Planning","created":"2025-11-22","cited_by_count":3,"area":"diffusion"},{"id":"2511.23146","title":"InstanceV: Instance-Level Video Generation","created":"2025-11-28","cited_by_count":3,"area":"diffusion"},{"id":"2603.16566","title":"VideoMatGen: PBR Materials through Joint Generative Modeling","created":"2026-03-17","cited_by_count":3,"area":"diffusion"},{"id":"2606.04432","title":"DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation","created":"2026-06-03","cited_by_count":3,"area":"diffusion"},{"id":"2608.05237","title":"In-Context Forcing: Uncovering Context Effects in Autoregressive Video Diffusion","created":"2026-08-05","cited_by_count":3,"area":"diffusion"},{"id":"2510.17247","title":"From Preferences to Prejudice: The Role of Alignment Tuning in Shaping Social Bias in Video Diffusion Models","created":"2025-10-20","cited_by_count":2,"area":"diffusion"},{"id":"2605.13974","title":"Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers","created":"2026-05-13","cited_by_count":2,"area":"diffusion"},{"id":"2605.26266","title":"Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion","created":"2026-05-25","cited_by_count":2,"area":"diffusion"},{"id":"2607.04206","title":"Sangam: Efficiently Serving Diffusion LLMs with the AR Stack","created":"2026-07-05","cited_by_count":2,"area":"diffusion"},{"id":"2503.24357","title":"InstructRestore: Region-Customized Image Restoration with Human Instructions","created":"2025-03-31","cited_by_count":1,"area":"diffusion"},{"id":"2505.16875","title":"T2I-ConBench: Text-to-Image Benchmark for Continual Post-training","created":"2025-05-22","cited_by_count":1,"area":"diffusion"},{"id":"2506.10639","title":"GigaVideo-1: Advancing Video Generation via Automatic Feedback with 4 GPU-Hours Fine-Tuning","created":"2025-06-12","cited_by_count":1,"area":"diffusion"},{"id":"2605.12522","title":"Differences in Text Generated by Diffusion and Autoregressive Language Models","created":"2026-04-04","cited_by_count":1,"area":"diffusion"},{"id":"2605.30325","title":"Veda: Scalable Video Diffusion via Distilled Sparse Attention","created":"2026-05-28","cited_by_count":1,"area":"diffusion"},{"id":"2608.07594","title":"Scaling Inherently Interpretable Language Models","created":"2026-08-06","cited_by_count":1,"area":"diffusion"},{"id":"2608.25505","title":"Conditional Total Correlation and the Serial Depth of Adaptive Parallel Sampling","created":"2026-08-26","cited_by_count":1,"area":"diffusion"},{"id":"2505.04974","title":"ReAlign: Bilingual Text-to-Motion Generation via Step-Aware Reward-Guided Alignment","created":"2025-05-08","cited_by_count":0,"area":"diffusion"},{"id":"2601.23182","title":"FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation","created":"2026-01-30","cited_by_count":0,"area":"diffusion"},{"id":"2603.01565","title":"Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation","created":"2026-03-02","cited_by_count":0,"area":"diffusion"},{"id":"2606.09098","title":"HoliDubber: Holistic Video Dubbing for Complex Acoustic Scenes via Text-Guided Audio Synthesis","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":"2606.15327","title":"Semantic DLM+: Improving Diffusion Language Models through Bias-variance Trade-off in Transition Kernel Design","created":"2026-06-13","cited_by_count":0,"area":"diffusion"},{"id":"2607.26237","title":"LumaGuide: Distribution Shaping for Training-Free HDR Generation in Diffusion Models","created":"2026-07-28","cited_by_count":0,"area":"diffusion"},{"id":"2608.08791","title":"Unsure but Certain: Uncovering the Representation-Confidence Gap in Diffusion Language Models","created":"2026-08-09","cited_by_count":0,"area":"diffusion"},{"id":"2609.20751","title":"dQwen3.5: Hybrid-Attention Diffusion Language Models","created":"2026-09-17","cited_by_count":0,"area":"diffusion"},{"id":"2609.21455","title":"CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation","created":"2026-09-18","cited_by_count":0,"area":"diffusion"},{"id":"2609.24657","title":"Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models","created":"2026-09-21","cited_by_count":0,"area":"diffusion"},{"id":"2609.35224","title":"TANGO: Watermarking Masked Diffusion Language Models in Token Pairs","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.37654","title":"Texture Space Material Diffusion","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.06844","title":"Learning to Read the Contextual Tokens in Diffusion Transformers","created":"2026-10-05","cited_by_count":0,"area":"diffusion"},{"id":"2610.08834","title":"JoyAI-Voice 2.0: A Full-Continuous Autoregressive Speech Generation Model with Semantic-Acoustic Joint Representation","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.13834","title":"On the Design Space of Continuous Diffusion Language Models","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.15339","title":"MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching","created":"2026-10-11","cited_by_count":0,"area":"diffusion"},{"id":"2610.15667","title":"Rate-Resolved Text Evaluation with Masked Diffusion Language Models","created":"2026-10-11","cited_by_count":0,"area":"diffusion"},{"id":"2610.18407","title":"Multi-Stream Residual Computation in Diffusion Language Models","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}