{"total":82,"rows":[{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269,"area":"diffusion"},{"id":"2503.06923","title":"From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers","created":"2025-03-10","cited_by_count":136,"area":"diffusion"},{"id":"2502.21079","title":"Training-free and Adaptive Sparse Attention for Efficient Long Video Generation","created":"2025-02-28","cited_by_count":69,"area":"diffusion"},{"id":"2508.17356","title":"DiCache: Let Diffusion Model Determine Its Own Cache","created":"2025-08-24","cited_by_count":42,"area":"diffusion"},{"id":"2506.09045","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","created":"2025-06-10","cited_by_count":41,"area":"diffusion"},{"id":"2506.03065","title":"Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers","created":"2025-06-03","cited_by_count":34,"area":"diffusion"},{"id":"2505.20353","title":"FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation","created":"2025-05-26","cited_by_count":24,"area":"diffusion"},{"id":"2505.18809","title":"VORTA: Efficient Video Diffusion via Routing Sparse Attention","created":"2025-05-24","cited_by_count":23,"area":"diffusion"},{"id":"2411.16720","title":"Importance-Based Token Merging for Efficient Image and Video Generation","created":"2024-11-23","cited_by_count":22,"area":"diffusion"},{"id":"2503.06545","title":"QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation","created":"2025-03-09","cited_by_count":21,"area":"diffusion"},{"id":"2508.16212","title":"OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models","created":"2025-08-22","cited_by_count":18,"area":"diffusion"},{"id":"2412.11706","title":"AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration","created":"2024-12-16","cited_by_count":16,"area":"diffusion"},{"id":"2510.19755","title":"A Survey on Cache Methods in Diffusion Models: Toward Efficient Multi-Modal Generation","created":"2025-10-22","cited_by_count":16,"area":"diffusion"},{"id":"2502.07590","title":"DSV: Exploiting Dynamic Sparsity to Accelerate Large-Scale Video DiT Training","created":"2025-02-11","cited_by_count":15,"area":"diffusion"},{"id":"2504.03140","title":"Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models","created":"2025-04-04","cited_by_count":15,"area":"diffusion"},{"id":"2505.18663","title":"DVD-Quant: Data-free Video Diffusion Transformers Quantization","created":"2025-05-24","cited_by_count":15,"area":"diffusion"},{"id":"2508.04016","title":"S$^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation","created":"2025-08-06","cited_by_count":13,"area":"diffusion"},{"id":"2411.17616","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","created":"2024-11-26","cited_by_count":12,"area":"diffusion"},{"id":"2502.20126","title":"FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute","created":"2025-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2508.21091","title":"ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion","created":"2025-08-27","cited_by_count":12,"area":"diffusion"},{"id":"2506.05096","title":"Astraea: A Token-wise Acceleration Framework for Video Diffusion Transformers","created":"2025-06-05","cited_by_count":11,"area":"diffusion"},{"id":"2509.13789","title":"BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching","created":"2025-09-17","cited_by_count":11,"area":"diffusion"},{"id":"2602.18993","title":"SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models","created":"2026-02-22","cited_by_count":11,"area":"diffusion"},{"id":"2508.08978","title":"TaoCache: Structure-Maintained Video Generation Acceleration","created":"2025-08-12","cited_by_count":10,"area":"diffusion"},{"id":"2603.08982","title":"SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing","created":"2026-03-09","cited_by_count":10,"area":"diffusion"},{"id":"2506.03275","title":"Chipmunk: Training-Free Acceleration of Diffusion Transformers with Dynamic Column-Sparse Deltas","created":"2025-06-03","cited_by_count":8,"area":"diffusion"},{"id":"2601.11641","title":"Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers","created":"2026-01-14","cited_by_count":8,"area":"diffusion"},{"id":"2602.13993","title":"Elastic Diffusion Transformer","created":"2026-02-15","cited_by_count":8,"area":"diffusion"},{"id":"2602.22654","title":"Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache","created":"2026-02-26","cited_by_count":8,"area":"diffusion"},{"id":"2504.12259","title":"VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate","created":"2025-04-16","cited_by_count":7,"area":"diffusion"},{"id":"2505.21036","title":"RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy","created":"2025-05-27","cited_by_count":7,"area":"diffusion"},{"id":"2601.16515","title":"SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer","created":"2026-01-23","cited_by_count":7,"area":"diffusion"},{"id":"2602.05449","title":"DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching","created":"2026-02-05","cited_by_count":7,"area":"diffusion"},{"id":"2602.24208","title":"SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching","created":"2026-02-27","cited_by_count":7,"area":"diffusion"},{"id":"2604.15911","title":"Efficient Video Diffusion Models: Advancements and Challenges","created":"2026-04-17","cited_by_count":7,"area":"diffusion"},{"id":"2506.00329","title":"Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation","created":"2025-05-31","cited_by_count":6,"area":"diffusion"},{"id":"2508.17756","title":"SuperGen: An Efficient Ultra-high-resolution Video Generation System with Sketching and Tiling","created":"2025-08-25","cited_by_count":6,"area":"diffusion"},{"id":"2605.23445","title":"DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation","created":"2026-05-22","cited_by_count":6,"area":"diffusion"},{"id":"2602.20497","title":"LESA: Learnable Stage-Aware Predictors for Diffusion Model Acceleration","created":"2026-02-24","cited_by_count":5,"area":"diffusion"},{"id":"2604.02979","title":"Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation","created":"2026-04-03","cited_by_count":5,"area":"diffusion"},{"id":"2602.16968","title":"DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers","created":"2026-02-19","cited_by_count":4,"area":"diffusion"},{"id":"2602.13357","title":"AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers","created":"2026-02-13","cited_by_count":3,"area":"diffusion"},{"id":"2604.04451","title":"Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse","created":"2026-04-06","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":"2606.06060","title":"ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE","created":"2026-06-04","cited_by_count":3,"area":"diffusion"},{"id":"2506.09644","title":"DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning","created":"2025-06-11","cited_by_count":2,"area":"diffusion"},{"id":"2511.12207","title":"Mixture of States: Routing Token-Level Dynamics for Multimodal Generation","created":"2025-11-15","cited_by_count":2,"area":"diffusion"},{"id":"2511.19778","title":"Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer","created":"2025-11-24","cited_by_count":2,"area":"diffusion"},{"id":"2512.23258","title":"Plug-and-Play Fidelity Optimization for Diffusion Transformer Acceleration via Cumulative Error Minimization","created":"2025-12-29","cited_by_count":2,"area":"diffusion"},{"id":"2602.16132","title":"CHAI: CacHe Attention Inference for text2video","created":"2026-02-18","cited_by_count":2,"area":"diffusion"},{"id":"2603.00519","title":"Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness","created":"2026-02-28","cited_by_count":2,"area":"diffusion"},{"id":"2604.26365","title":"Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models","created":"2026-04-29","cited_by_count":2,"area":"diffusion"},{"id":"2605.11869","title":"FIS-DiT: Breaking the Few-Step Video Inference Barrier via Training-Free Frame Interleaved Sparsity","created":"2026-05-12","cited_by_count":1,"area":"diffusion"},{"id":"2605.23381","title":"VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation","created":"2026-05-22","cited_by_count":1,"area":"diffusion"},{"id":"2606.25040","title":"Chorus II: Cross-Request Sparsity Reuse for Efficient Image-to-Video Generation","created":"2026-06-23","cited_by_count":1,"area":"diffusion"},{"id":"2606.31026","title":"OTCache: Optimal Transport for Geometry-Aware Caching in Diffusion Models","created":"2026-06-30","cited_by_count":1,"area":"diffusion"},{"id":"2607.12358","title":"ACID: Adaptive Caching for vIDeo generation","created":"2026-07-14","cited_by_count":1,"area":"diffusion"},{"id":"2607.29398","title":"OnlineCache: Learning Dynamic Caching Policies with Error Correction for Efficient Diffusion Inference","created":"2026-07-31","cited_by_count":1,"area":"diffusion"},{"id":"2608.09231","title":"BAG: Budget-Aware Gating for Diffusion Caching","created":"2026-08-10","cited_by_count":1,"area":"diffusion"},{"id":"2608.12032","title":"LoSA: Near-Lossless Sparse Attention for Training-Free Video Diffusion Acceleration","created":"2026-08-12","cited_by_count":1,"area":"diffusion"},{"id":"2512.05134","title":"InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models","created":"2025-11-29","cited_by_count":0,"area":"diffusion"},{"id":"2603.07057","title":"SODA: Sensitivity-Oriented Dynamic Acceleration for Diffusion Transformer","created":"2026-03-07","cited_by_count":0,"area":"diffusion"},{"id":"2603.18742","title":"6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models","created":"2026-03-19","cited_by_count":0,"area":"diffusion"},{"id":"2605.18190","title":"Dual-Rate Diffusion: Accelerating diffusion models with an interleaved heavy-light network","created":"2026-05-18","cited_by_count":0,"area":"diffusion"},{"id":"2605.21042","title":"Dynamic Video Generation: Shaping Video Generation Across Time and Space","created":"2026-05-20","cited_by_count":0,"area":"diffusion"},{"id":"2605.22015","title":"ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration","created":"2026-05-21","cited_by_count":0,"area":"diffusion"},{"id":"2605.24870","title":"Trajectory-Consistent Calibration for Cache-Accelerated Diffusion Models","created":"2026-05-24","cited_by_count":0,"area":"diffusion"},{"id":"2606.06309","title":"RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Scheduling","created":"2026-06-04","cited_by_count":0,"area":"diffusion"},{"id":"2606.23682","title":"Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping","created":"2026-06-22","cited_by_count":0,"area":"diffusion"},{"id":"2607.03803","title":"CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation","created":"2026-07-04","cited_by_count":0,"area":"diffusion"},{"id":"2607.20048","title":"Importance-Aware OBS Pruning for Diffusion Models","created":"2026-07-22","cited_by_count":0,"area":"diffusion"},{"id":"2607.23844","title":"OmniCache: Multidimensional Hierarchical Feature Caching For Diffusion Models","created":"2026-07-26","cited_by_count":0,"area":"diffusion"},{"id":"2608.17695","title":"Magnitude-Direction Decoupling for Fast Video Generation with Flow Matching Models","created":"2026-08-18","cited_by_count":0,"area":"diffusion"},{"id":"2608.23429","title":"ChebBooster: A Training-Free Approach for Efficient Diffusion Transformer Inference via Chebyshev-Inspired Extrapolation","created":"2026-08-24","cited_by_count":0,"area":"diffusion"},{"id":"2609.32415","title":"RefAdapt-DiT: Adaptive Joint Attention for Reference-Conditioned Diffusion Transformers","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2609.33202","title":"ReAL: Accelerating Flow Matching through Segment Advancement with Shared Lookahead","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2609.33723","title":"GeoShrink: Accelerating Diffusion Transformers with Two Lines of Code","created":"2026-09-27","cited_by_count":0,"area":"diffusion"},{"id":"2610.03577","title":"Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection","created":"2026-10-02","cited_by_count":0,"area":"diffusion"},{"id":"2610.04510","title":"ManifoldCache: Training-Free Diffusion Acceleration via Constraint Manifold Caching","created":"2026-10-03","cited_by_count":0,"area":"diffusion"},{"id":"2610.12530","title":"CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration","created":"2026-10-08","cited_by_count":0,"area":"diffusion"},{"id":"2610.14657","title":"TGuide: Faster Autoregressive Video Diffusion via Historical Trajectory Guidance","created":"2026-10-10","cited_by_count":0,"area":"diffusion"},{"id":"2610.16545","title":"Heuristics are Not Enough: Calibrated and Corrected Caching for Video Diffusion Acceleration","created":"2026-10-12","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}