{"list":"other","total":66,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2311.12022","title":"GPQA: A Graduate-Level Google-Proof Q&A Benchmark","created":"2023-11-20","cited_by_count":2879},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1712.05877","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","created":"2017-12-15","cited_by_count":1593},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2502.09992","title":"Large Language Diffusion Models","created":"2025-02-14","cited_by_count":912},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"1911.11134","title":"Rigging the Lottery: Making All Tickets Winners","created":"2019-11-25","cited_by_count":495},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2006.05531","title":"GEOM: Energy-annotated molecular conformations for property prediction and molecular generation","created":"2020-06-09","cited_by_count":243},{"id":"2508.13009","title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","created":"2025-08-18","cited_by_count":186},{"id":"2506.06295","title":"dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching","created":"2025-05-17","cited_by_count":169},{"id":"2501.08316","title":"Diffusion Adversarial Post-Training for One-Step Video Generation","created":"2025-01-14","cited_by_count":151},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"2509.23951","title":"HunyuanImage 3.0 Technical Report","created":"2025-09-28","cited_by_count":149},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2410.19355","title":"FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality","created":"2024-10-25","cited_by_count":122},{"id":"2406.08552","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","created":"2024-06-12","cited_by_count":115},{"id":"2506.00413","title":"Accelerating Diffusion LLMs via Adaptive Parallel Decoding","created":"2025-05-31","cited_by_count":112},{"id":"2411.02397","title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers","created":"2024-11-04","cited_by_count":108},{"id":"2505.13389","title":"VSA: Faster Video Diffusion with Trainable Sparse Attention","created":"2025-05-19","cited_by_count":104},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98},{"id":"2510.06308","title":"Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding","created":"2025-10-07","cited_by_count":88},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82},{"id":"2408.05636","title":"Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion","created":"2024-08-10","cited_by_count":57},{"id":"2404.02747","title":"Faster Diffusion via Temporal Attention Decomposition","created":"2024-04-03","cited_by_count":54},{"id":"2403.12706","title":"AnimateDiff-Lightning: Cross-Model Diffusion Distillation","created":"2024-03-19","cited_by_count":47},{"id":"2503.10270","title":"EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing","created":"2025-03-13","cited_by_count":45},{"id":"2507.02860","title":"Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching","created":"2025-07-03","cited_by_count":45},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43},{"id":"2502.18924","title":"MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis","created":"2025-02-26","cited_by_count":41},{"id":"2506.09045","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","created":"2025-06-10","cited_by_count":41},{"id":"2406.06890","title":"Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation","created":"2024-06-11","cited_by_count":39},{"id":"2505.16864","title":"Training-Free Efficient Video Generation via Dynamic Token Carving","created":"2025-05-22","cited_by_count":34},{"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},{"id":"2501.05370","title":"Accelerated Diffusion Models via Speculative Sampling","created":"2025-01-09","cited_by_count":31},{"id":"2404.06091","title":"Hash3D: Training-free Acceleration for 3D Generation","created":"2024-04-09","cited_by_count":19},{"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},{"id":"2504.14582","title":"NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results","created":"2025-04-20","cited_by_count":12},{"id":"2305.17423","title":"Accelerating Text-to-Image Editing via Cache-Enabled Sparse Diffusion Inference","created":"2023-05-27","cited_by_count":11},{"id":"2412.05899","title":"Accelerating Video Diffusion Models via Distribution Matching","created":"2024-12-08","cited_by_count":11},{"id":"2508.17588","title":"HERO: Hierarchical Extrapolation and Refresh for Efficient World Models","created":"2025-08-25","cited_by_count":9},{"id":"2505.21036","title":"RainFusion: Adaptive Video Generation Acceleration via Multi-Dimensional Visual Redundancy","created":"2025-05-27","cited_by_count":7},{"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},{"id":"2501.04012","title":"FlexCache: Flexible Approximate Cache System for Video Diffusion","created":"2024-12-18","cited_by_count":5},{"id":"2407.19205","title":"Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions","created":"2024-07-27","cited_by_count":4},{"id":"2508.10963","title":"EVCtrl: Efficient Control Adapter for Visual Generation","created":"2025-08-14","cited_by_count":3},{"id":"2412.19489","title":"RAIN: Real-time Animation of Infinite Video Stream","created":"2024-12-27","cited_by_count":2},{"id":"2510.04646","title":"Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation","created":"2025-10-06","cited_by_count":2},{"id":"2508.03254","title":"V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models","created":"2025-08-05","cited_by_count":1},{"id":"2509.09748","title":"DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration","created":"2025-09-11","cited_by_count":1}],"next_cursor":null}