{"list":"other","total":100,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2007.15651","title":"Contrastive Learning for Unpaired Image-to-Image Translation","created":"2020-07-30","cited_by_count":639},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2101.03697","title":"RepVGG: Making VGG-style ConvNets Great Again","created":"2021-01-11","cited_by_count":522},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2211.13218","title":"CODA-Prompt: COntinual Decomposed Attention-based Prompting for Rehearsal-Free Continual Learning","created":"2022-11-23","cited_by_count":450},{"id":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"1812.01243","title":"Efficient Attention: Attention with Linear Complexities","created":"2018-12-04","cited_by_count":368},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2410.10629","title":"SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers","created":"2024-10-14","cited_by_count":340},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2210.10960","title":"Diffusion Models already have a Semantic Latent Space","created":"2022-10-20","cited_by_count":328},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305},{"id":"2112.00390","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","created":"2021-12-01","cited_by_count":280},{"id":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2209.02646","title":"A Survey on Generative Diffusion Model","created":"2022-09-06","cited_by_count":240},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232},{"id":"2303.04226","title":"A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT","created":"2023-03-07","cited_by_count":224},{"id":"2303.17604","title":"Token Merging for Fast Stable Diffusion","created":"2023-03-30","cited_by_count":224},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213},{"id":"2404.00228","title":"InfLoRA: Interference-Free Low-Rank Adaptation for Continual Learning","created":"2024-03-30","cited_by_count":198},{"id":"2308.09592","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","created":"2023-08-18","cited_by_count":183},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171},{"id":"2311.16037","title":"GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions","created":"2023-11-27","cited_by_count":168},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"2403.08733","title":"GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing","created":"2024-03-13","cited_by_count":115},{"id":"2406.08552","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","created":"2024-06-12","cited_by_count":115},{"id":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94},{"id":"2312.08874","title":"Agent Attention: On the Integration of Softmax and Linear Attention","created":"2023-12-14","cited_by_count":90},{"id":"2305.15241","title":"Robust Classification via a Single Diffusion Model","created":"2023-05-24","cited_by_count":79},{"id":"2310.03270","title":"EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models","created":"2023-10-05","cited_by_count":78},{"id":"1901.09024","title":"Diversity-Sensitive Conditional Generative Adversarial Networks","created":"2019-01-25","cited_by_count":77},{"id":"2412.18597","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","created":"2024-12-24","cited_by_count":74},{"id":"2305.17328","title":"Zero-TPrune: Zero-Shot Token Pruning through Leveraging of the Attention Graph in Pre-Trained Transformers","created":"2023-05-27","cited_by_count":62},{"id":"2312.10113","title":"Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation","created":"2023-12-15","cited_by_count":62},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59},{"id":"2307.08702","title":"Diffusion Models Beat GANs on Image Classification","created":"2023-07-17","cited_by_count":58},{"id":"2405.18428","title":"DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention","created":"2024-05-28","cited_by_count":56},{"id":"2210.09292","title":"Efficient Diffusion Models for Vision: A Survey","created":"2022-10-07","cited_by_count":51},{"id":"2502.17258","title":"VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing","created":"2025-02-24","cited_by_count":50},{"id":"2311.18608","title":"Contrastive Denoising Score for Text-guided Latent Diffusion Image Editing","created":"2023-11-30","cited_by_count":49},{"id":"2401.01702","title":"Image Sculpting: Precise Object Editing with 3D Geometry Control","created":"2024-01-02","cited_by_count":45},{"id":"2412.11520","title":"EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting","created":"2024-12-16","cited_by_count":41},{"id":"2404.13679","title":"GScream: Learning 3D Geometry and Feature Consistent Gaussian Splatting for Object Removal","created":"2024-04-21","cited_by_count":39},{"id":"2405.05252","title":"Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models","created":"2024-05-08","cited_by_count":38},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37},{"id":"1811.05544","title":"An Introductory Survey on Attention Mechanisms in NLP Problems","created":"2018-11-12","cited_by_count":32},{"id":"2303.12343","title":"LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation","created":"2023-03-22","cited_by_count":29},{"id":"2308.07687","title":"DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models","created":"2023-08-15","cited_by_count":26},{"id":"2003.13853","title":"Semi-supervised Learning for Few-shot Image-to-Image Translation","created":"2020-03-30","cited_by_count":25},{"id":"2309.16608","title":"KV Inversion: KV Embeddings Learning for Text-Conditioned Real Image Action Editing","created":"2023-09-28","cited_by_count":22},{"id":"2205.11423","title":"Decoder Denoising Pretraining for Semantic Segmentation","created":"2022-05-23","cited_by_count":20},{"id":"2406.01629","title":"RecDiff: Diffusion Model for Social Recommendation","created":"2024-06-01","cited_by_count":20},{"id":"2410.01359","title":"FlashMask: Efficient and Rich Mask Extension of FlashAttention","created":"2024-10-02","cited_by_count":20},{"id":"2303.14863","title":"DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion","created":"2023-03-27","cited_by_count":19},{"id":"2311.18837","title":"VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models","created":"2023-11-30","cited_by_count":19},{"id":"2312.03611","title":"DreamComposer: Controllable 3D Object Generation via Multi-View Conditions","created":"2023-12-06","cited_by_count":18},{"id":"2308.00135","title":"InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing","created":"2023-07-22","cited_by_count":17},{"id":"2310.10624","title":"DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing","created":"2023-10-16","cited_by_count":17},{"id":"2411.18552","title":"FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion","created":"2024-11-27","cited_by_count":12},{"id":"2312.03459","title":"F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis","created":"2023-12-06","cited_by_count":10},{"id":"2404.12541","title":"GenVideo: One-shot Target-image and Shape Aware Video Editing using T2I Diffusion Models","created":"2024-04-18","cited_by_count":7}],"next_cursor":null}