{"total":72,"rows":[{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340,"area":"diffusion"},{"id":"2410.11081","title":"Simplifying, Stabilizing and Scaling Continuous-Time Consistency Models","created":"2024-10-14","cited_by_count":283,"area":"diffusion"},{"id":"2504.05741","title":"DDT: Decoupled Diffusion Transformer","created":"2025-04-08","cited_by_count":109,"area":"diffusion"},{"id":"2503.09641","title":"SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation","created":"2025-03-12","cited_by_count":87,"area":"diffusion"},{"id":"2506.14603","title":"Align Your Flow: Scaling Continuous-Time Flow Map Distillation","created":"2025-06-17","cited_by_count":87,"area":"diffusion"},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2507.23268","title":"PixNerd: Pixel Neural Field Diffusion","created":"2025-07-31","cited_by_count":82,"area":"diffusion"},{"id":"2505.20171","title":"Long-Context State-Space Video World Models","created":"2025-05-26","cited_by_count":64,"area":"wm"},{"id":"2410.03456","title":"Dynamic Diffusion Transformer","created":"2024-10-04","cited_by_count":62,"area":"diffusion"},{"id":"2511.19365","title":"DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation","created":"2025-11-24","cited_by_count":60,"area":"diffusion"},{"id":"2405.18428","title":"DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention","created":"2024-05-28","cited_by_count":56,"area":"diffusion"},{"id":"2410.14919","title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","created":"2024-10-19","cited_by_count":47,"area":"diffusion"},{"id":"2412.01199","title":"TinyFusion: Diffusion Transformers Learned Shallow","created":"2024-12-02","cited_by_count":45,"area":"diffusion"},{"id":"2409.02097","title":"LinFusion: 1 GPU, 1 Minute, 16K Image","created":"2024-09-03","cited_by_count":43,"area":"diffusion"},{"id":"2412.09856","title":"LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity","created":"2024-12-13","cited_by_count":43,"area":"diffusion"},{"id":"2410.11795","title":"Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices","created":"2024-10-15","cited_by_count":41,"area":"diffusion"},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2412.11890","title":"SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation","created":"2024-12-16","cited_by_count":31,"area":null},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2409.07163","title":"Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models","created":"2024-09-11","cited_by_count":23,"area":"diffusion"},{"id":"2501.04765","title":"TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training","created":"2025-01-08","cited_by_count":21,"area":"diffusion"},{"id":"2410.03105","title":"Mamba in Vision: A Comprehensive Survey of Techniques and Applications","created":"2024-10-04","cited_by_count":18,"area":"ssm"},{"id":"2410.13925","title":"FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model","created":"2024-10-17","cited_by_count":15,"area":"diffusion"},{"id":"2408.11758","title":"MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs","created":"2024-08-21","cited_by_count":14,"area":"ssm"},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2501.00603","title":"DiC: Rethinking Conv3x3 Designs in Diffusion Models","created":"2024-12-31","cited_by_count":14,"area":"diffusion"},{"id":"2602.02493","title":"PixelGen: Improving Pixel Diffusion with Perceptual Supervision","created":"2026-02-02","cited_by_count":14,"area":"diffusion"},{"id":"2506.05340","title":"Exploring Diffusion Transformer Designs via Grafting","created":"2025-06-05","cited_by_count":12,"area":"diffusion"},{"id":"2408.15101","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders","created":"2024-08-27","cited_by_count":10,"area":"ssm"},{"id":"2501.12976","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation","created":"2025-01-22","cited_by_count":10,"area":"diffusion"},{"id":"2409.19937","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","created":"2024-09-30","cited_by_count":8,"area":"ssm"},{"id":"2508.17434","title":"TinySR: Pruning Diffusion for Real-World Image Super-Resolution","created":"2025-08-24","cited_by_count":7,"area":"diffusion"},{"id":"2510.08994","title":"Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation","created":"2025-10-10","cited_by_count":7,"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":"2511.15927","title":"DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone","created":"2025-11-19","cited_by_count":6,"area":"diffusion"},{"id":"2504.00037","title":"ViT-Linearizer: Distilling Quadratic Knowledge into Linear-Time Vision Models","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2408.02615","title":"LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mamba","created":"2024-08-05","cited_by_count":4,"area":"diffusion"},{"id":"2411.15224","title":"Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation","created":"2024-11-21","cited_by_count":4,"area":"ssm"},{"id":"2506.23283","title":"MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition","created":"2025-06-29","cited_by_count":4,"area":"ssm"},{"id":"2506.18999","title":"Diffusion Transformer-to-Mamba Distillation for High-Resolution Image Generation","created":"2025-06-23","cited_by_count":3,"area":"diffusion"},{"id":"2510.13253","title":"End-to-End Multi-Modal Diffusion Mamba","created":"2025-10-15","cited_by_count":3,"area":"ssm"},{"id":"2602.04220","title":"Adaptive 1D Video Diffusion Autoencoder","created":"2026-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2605.02772","title":"Linearizing Vision Transformer with Test-Time Training","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2406.05992","title":"MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mamba","created":"2024-06-10","cited_by_count":2,"area":"ssm"},{"id":"2408.05743","title":"Neural Architecture Search based Global-local Vision Mamba for Palm-Vein Recognition","created":"2024-08-11","cited_by_count":2,"area":"ssm"},{"id":"2504.01466","title":"Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes","created":"2025-04-02","cited_by_count":2,"area":"ssm"},{"id":"2505.12685","title":"Mamba-Adaptor: State Space Model Adaptor for Visual Recognition","created":"2025-05-19","cited_by_count":2,"area":"ssm"},{"id":"2510.12573","title":"Learning Human Motion with Temporally Conditional Mamba","created":"2025-10-14","cited_by_count":2,"area":"ssm"},{"id":"2603.26357","title":"MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model","created":"2026-03-27","cited_by_count":2,"area":"diffusion"},{"id":"2604.25299","title":"The Thinking Pixel: Recursive Sparse Reasoning in Multimodal Diffusion Latents","created":"2026-04-28","cited_by_count":2,"area":"lr"},{"id":"2607.21553","title":"SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation","created":"2026-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2406.02013","title":"Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning","created":"2024-06-04","cited_by_count":1,"area":"ssm"},{"id":"2406.16722","title":"Venturing into Uncharted Waters: The Navigation Compass from Transformer to Mamba","created":"2024-06-24","cited_by_count":1,"area":"ssm"},{"id":"2411.12663","title":"PoM: Efficient Image and Video Generation with the Polynomial Mixer","created":"2024-11-19","cited_by_count":1,"area":"diffusion"},{"id":"2412.16602","title":"V\"Mean\"ba: Visual State Space Models only need 1 hidden dimension","created":"2024-12-21","cited_by_count":1,"area":null},{"id":"2504.06803","title":"DyDiT++: Diffusion Transformers with Timestep and Spatial Dynamics for Efficient Visual Generation","created":"2025-04-09","cited_by_count":1,"area":"diffusion"},{"id":"2505.11777","title":"Self-NPO: Data-Free Diffusion Model Enhancement via Truncated Diffusion Fine-Tuning","created":"2025-05-17","cited_by_count":1,"area":"diffusion"},{"id":"2506.08457","title":"Audio Generation Through Score-Based Generative Modeling: Design Principles and Implementation","created":"2025-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2506.15940","title":"Polyline Path Masked Attention for Vision Transformer","created":"2025-06-19","cited_by_count":1,"area":null},{"id":"2603.00576","title":"Efficient Long-Sequence Diffusion Modeling for Symbolic Music Generation","created":"2026-02-28","cited_by_count":1,"area":"diffusion"},{"id":"2603.09138","title":"Rotation Equivariant Mamba for Vision Tasks","created":"2026-03-10","cited_by_count":1,"area":"ssm"},{"id":"2409.07714","title":"CollaMamba: Efficient Collaborative Perception with Cross-Agent Spatial-Temporal State Space Model","created":"2024-09-12","cited_by_count":0,"area":null},{"id":"2503.13004","title":"TFDM: Time-Variant Frequency-Based Point Cloud Diffusion with Mamba","created":"2025-03-17","cited_by_count":0,"area":"diffusion"},{"id":"2507.09514","title":"QuarterMap: Efficient Post-Training Token Pruning for Visual State Space Models","created":"2025-07-13","cited_by_count":0,"area":"inference"},{"id":"2510.00862","title":"Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model","created":"2025-10-01","cited_by_count":0,"area":"ssm"},{"id":"2601.22630","title":"LINA: Linear Autoregressive Image Generative Models with Continuous Tokens","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.06419","title":"Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors","created":"2026-02-06","cited_by_count":0,"area":null},{"id":"2603.13663","title":"PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers","created":"2026-03-14","cited_by_count":0,"area":"diffusion"},{"id":"2604.01421","title":"EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation","created":"2026-04-01","cited_by_count":0,"area":"diffusion"},{"id":"2606.25324","title":"Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models","created":"2026-06-24","cited_by_count":0,"area":"distill"},{"id":"2606.25329","title":"State Space Models Meet Remote Sensing: A Survey","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.16104","title":"Nexus: Structured Synergy for Efficient Text-to-Image Generation using Rectified Flow Model","created":"2026-08-17","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}