{"list":"other","total":105,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"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":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"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":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237},{"id":"2412.08629","title":"FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models","created":"2024-12-11","cited_by_count":217},{"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":"2411.04746","title":"Taming Rectified Flow for Inversion and Editing","created":"2024-11-07","cited_by_count":204},{"id":"2504.20690","title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","created":"2025-04-29","cited_by_count":204},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2312.06739","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models","created":"2023-12-11","cited_by_count":177},{"id":"2410.10792","title":"Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations","created":"2024-10-14","cited_by_count":165},{"id":"2506.15442","title":"Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material","created":"2025-06-18","cited_by_count":165},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2311.16711","title":"LEDITS++: Limitless Image Editing using Text-to-Image Models","created":"2023-11-28","cited_by_count":148},{"id":"2505.22705","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","created":"2025-05-28","cited_by_count":141},{"id":"2510.26583","title":"Emu3.5: Native Multimodal Models are World Learners","created":"2025-10-30","cited_by_count":132},{"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":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94},{"id":"2510.16888","title":"Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback","created":"2025-10-19","cited_by_count":79},{"id":"2312.06704","title":"SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction","created":"2023-12-10","cited_by_count":77},{"id":"2401.14828","title":"TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts","created":"2024-01-26","cited_by_count":77},{"id":"2312.02087","title":"VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence","created":"2023-12-04","cited_by_count":69},{"id":"2403.11868","title":"View-Consistent 3D Editing with Gaussian Splatting","created":"2024-03-18","cited_by_count":67},{"id":"2506.23044","title":"Ovis-U1 Technical Report","created":"2025-06-29","cited_by_count":67},{"id":"2506.03147","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","created":"2025-06-03","cited_by_count":66},{"id":"2504.15009","title":"Insert Anything: Image Insertion via In-Context Editing in DiT","created":"2025-04-21","cited_by_count":61},{"id":"2401.08392","title":"DoraemonGPT: Toward Understanding Dynamic Scenes with Large Language Models (Exemplified as A Video Agent)","created":"2024-01-16","cited_by_count":58},{"id":"2510.15857","title":"BLIP3o-NEXT: Next Frontier of Native Image Generation","created":"2025-10-17","cited_by_count":54},{"id":"2412.00518","title":"Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects","created":"2024-11-30","cited_by_count":44},{"id":"2309.13524","title":"Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction","created":"2023-09-24","cited_by_count":42},{"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":"2406.03293","title":"Text-to-Image Rectified Flow as Plug-and-Play Priors","created":"2024-06-05","cited_by_count":38},{"id":"2312.09246","title":"SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds","created":"2023-12-14","cited_by_count":37},{"id":"2311.09571","title":"3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation","created":"2023-11-16","cited_by_count":35},{"id":"2407.02329","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","created":"2024-07-02","cited_by_count":35},{"id":"2411.15843","title":"Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing","created":"2024-11-24","cited_by_count":34},{"id":"2510.23306","title":"ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation","created":"2025-10-27","cited_by_count":33},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25},{"id":"2412.01583","title":"3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting","created":"2024-12-02","cited_by_count":22},{"id":"2404.16510","title":"Interactive3D: Create What You Want by Interactive 3D Generation","created":"2024-04-25","cited_by_count":21},{"id":"2502.05176","title":"AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360{\\deg} Unbounded Scene Inpainting","created":"2025-02-07","cited_by_count":21},{"id":"2507.04961","title":"InterGSEdit: Interactive 3D Gaussian Splatting Editing with 3D Geometry-Consistent Attention Prior","created":"2025-07-07","cited_by_count":19},{"id":"2510.11000","title":"ContextGen: Contextual Layout Anchoring for Identity-Consistent Multi-Instance Generation","created":"2025-10-13","cited_by_count":18},{"id":"2510.21307","title":"Towards Physically Executable 3D Gaussian for Embodied Navigation","created":"2025-10-24","cited_by_count":17},{"id":"2406.13393","title":"Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images","created":"2024-06-19","cited_by_count":16},{"id":"2510.25970","title":"SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing","created":"2025-10-29","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":"2509.25916","title":"VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs","created":"2025-09-30","cited_by_count":13},{"id":"2412.01430","title":"MVImgNet2.0: A Larger-scale Dataset of Multi-view Images","created":"2024-12-02","cited_by_count":12},{"id":"2511.23172","title":"Fast Multi-view Consistent 3D Editing with Video Priors","created":"2025-11-28","cited_by_count":12},{"id":"2506.00512","title":"Pro3D-Editor : A Progressive-Views Perspective for Consistent and Precise 3D Editing","created":"2025-05-31","cited_by_count":11},{"id":"2407.10102","title":"3DEgo: 3D Editing on the Go!","created":"2024-07-14","cited_by_count":10},{"id":"2511.19268","title":"BideDPO: Conditional Image Generation with Simultaneous Text and Condition Alignment","created":"2025-11-24","cited_by_count":10},{"id":"2508.14811","title":"Tinker: Diffusion's Gift to 3D--Multi-View Consistent Editing From Sparse Inputs without Per-Scene Optimization","created":"2025-08-20","cited_by_count":9},{"id":"2503.10634","title":"V2Edit: Versatile Video Diffusion Editor for Videos and 3D Scenes","created":"2025-03-13","cited_by_count":8},{"id":"2411.10033","title":"GSEditPro: 3D Gaussian Splatting Editing with Attention-based Progressive Localization","created":"2024-11-15","cited_by_count":7},{"id":"2412.07984","title":"Diffusion-Based Attention Warping for Consistent 3D Scene Editing","created":"2024-12-10","cited_by_count":7},{"id":"2501.12935","title":"3D Object Manipulation in a Single Image using Generative Models","created":"2025-01-22","cited_by_count":7},{"id":"2505.01322","title":"FreeInsert: Disentangled Text-Guided Object Insertion in 3D Gaussian Scene without Spatial Priors","created":"2025-05-02","cited_by_count":5}],"next_cursor":"100"}