{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"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":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"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":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2303.12789","title":"Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions","created":"2023-03-22","cited_by_count":484},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2112.05139","title":"CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields","created":"2021-12-09","cited_by_count":370},{"id":"2311.04145","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","created":"2023-11-07","cited_by_count":350},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2401.15977","title":"Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling","created":"2024-01-29","cited_by_count":211},{"id":"2306.13455","title":"DreamEditor: Text-Driven 3D Scene Editing with Neural Fields","created":"2023-06-23","cited_by_count":155},{"id":"2212.08070","title":"NeRF-Art: Text-Driven Neural Radiance Fields Stylization","created":"2022-12-15","cited_by_count":126},{"id":"2303.12048","title":"Vox-E: Text-guided Voxel Editing of 3D Objects","created":"2023-03-21","cited_by_count":115},{"id":"2403.08733","title":"GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing","created":"2024-03-13","cited_by_count":115},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"2406.05338","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","created":"2024-06-08","cited_by_count":105},{"id":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94},{"id":"2308.10608","title":"FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly","created":"2023-08-21","cited_by_count":76},{"id":"2312.06725","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","created":"2023-12-11","cited_by_count":72},{"id":"2312.02087","title":"VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence","created":"2023-12-04","cited_by_count":69},{"id":"2402.00864","title":"ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields","created":"2024-02-01","cited_by_count":68},{"id":"2406.10700","title":"Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection","created":"2024-06-15","cited_by_count":66},{"id":"2503.20287","title":"InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction","created":"2025-03-26","cited_by_count":62},{"id":"2405.16537","title":"I2VEdit: First-Frame-Guided Video Editing via Image-to-Video Diffusion Models","created":"2024-05-26","cited_by_count":55},{"id":"2310.11784","title":"Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts","created":"2023-10-18","cited_by_count":52},{"id":"2303.15780","title":"Instruct 3D-to-3D: Text Instruction Guided 3D-to-3D conversion","created":"2023-03-28","cited_by_count":48},{"id":"2309.07125","title":"Text-Guided Generation and Editing of Compositional 3D Avatars","created":"2023-09-13","cited_by_count":39},{"id":"2312.09246","title":"SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds","created":"2023-12-14","cited_by_count":37},{"id":"2403.14617","title":"Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion","created":"2024-03-21","cited_by_count":27},{"id":"2311.18827","title":"Motion-Conditioned Image Animation for Video Editing","created":"2023-11-30","cited_by_count":26},{"id":"2403.11105","title":"Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models","created":"2024-03-17","cited_by_count":22},{"id":"2306.09551","title":"Edit-DiffNeRF: Editing 3D Neural Radiance Fields using 2D Diffusion Model","created":"2023-06-15","cited_by_count":20},{"id":"2506.20652","title":"EditP23: 3D Editing via Propagation of Image Prompts to Multi-View","created":"2025-06-25","cited_by_count":20},{"id":"2306.05668","title":"RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Models","created":"2023-06-09","cited_by_count":19},{"id":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19},{"id":"2406.09404","title":"ConsistDreamer: 3D-Consistent 2D Diffusion for High-Fidelity Scene Editing","created":"2024-06-13","cited_by_count":18},{"id":"2310.09965","title":"ProteusNeRF: Fast Lightweight NeRF Editing using 3D-Aware Image Context","created":"2023-10-15","cited_by_count":17},{"id":"2312.08563","title":"Efficient-NeRF2NeRF: Streamlining Text-Driven 3D Editing with Multiview Correspondence-Enhanced Diffusion Models","created":"2023-12-13","cited_by_count":16},{"id":"2407.11394","title":"DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation","created":"2024-07-16","cited_by_count":14},{"id":"2404.02788","title":"GenN2N: Generative NeRF2NeRF Translation","created":"2024-04-03","cited_by_count":11},{"id":"2407.02034","title":"TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulation","created":"2024-07-02","cited_by_count":10},{"id":"2407.13748","title":"General Geometry-aware Weakly Supervised 3D Object Detection","created":"2024-07-18","cited_by_count":7},{"id":"2511.00503","title":"Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models","created":"2025-11-01","cited_by_count":7},{"id":"2406.17396","title":"SyncNoise: Geometrically Consistent Noise Prediction for Text-based 3D Scene Editing","created":"2024-06-25","cited_by_count":3},{"id":"2507.09168","title":"Stable Score Distillation","created":"2025-07-12","cited_by_count":3}],"next_cursor":null}