{"list":"other","total":75,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"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":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"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":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"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":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2305.18292","title":"Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models","created":"2023-05-29","cited_by_count":261},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199},{"id":"2311.13600","title":"ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs","created":"2023-11-22","cited_by_count":194},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2310.08465","title":"MotionDirector: Motion Customization of Text-to-Video Diffusion Models","created":"2023-10-12","cited_by_count":173},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135},{"id":"2312.00777","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","created":"2023-12-01","cited_by_count":126},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2404.01292","title":"Measuring Style Similarity in Diffusion Models","created":"2024-04-01","cited_by_count":109},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88},{"id":"2506.05207","title":"Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning","created":"2025-06-05","cited_by_count":81},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80},{"id":"2305.16225","title":"ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models","created":"2023-05-25","cited_by_count":75},{"id":"2502.08639","title":"CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation","created":"2025-02-12","cited_by_count":74},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71},{"id":"2312.02432","title":"Orthogonal Adaptation for Modular Customization of Diffusion Models","created":"2023-12-05","cited_by_count":70},{"id":"2402.12974","title":"Visual Style Prompting with Swapping Self-Attention","created":"2024-02-20","cited_by_count":63},{"id":"2506.04590","title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting","created":"2025-06-05","cited_by_count":62},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60},{"id":"2407.00788","title":"InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation","created":"2024-06-30","cited_by_count":53},{"id":"2502.17363","title":"KV-Edit: Training-Free Image Editing for Precise Background Preservation","created":"2025-02-24","cited_by_count":49},{"id":"2502.18461","title":"K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs","created":"2025-02-25","cited_by_count":48},{"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":"2403.11781","title":"Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm","created":"2024-03-18","cited_by_count":39},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36},{"id":"2401.15975","title":"StableIdentity: Inserting Anybody into Anywhere at First Sight","created":"2024-01-29","cited_by_count":35},{"id":"2505.03730","title":"FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios","created":"2025-05-06","cited_by_count":25},{"id":"2404.15677","title":"CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models","created":"2024-04-24","cited_by_count":24},{"id":"2412.04465","title":"UnZipLoRA: Separating Content and Style from a Single Image","created":"2024-12-05","cited_by_count":24},{"id":"2602.05551","title":"FastVMT: Eliminating Redundancy in Video Motion Transfer","created":"2026-02-05","cited_by_count":23},{"id":"2512.18741","title":"Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation","created":"2025-12-21","cited_by_count":20},{"id":"2412.16919","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","created":"2024-12-22","cited_by_count":16},{"id":"2312.02503","title":"SAVE: Protagonist Diversification with Structure Agnostic Video Editing","created":"2023-12-05","cited_by_count":15},{"id":"2503.12929","title":"AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction","created":"2025-03-17","cited_by_count":15},{"id":"2510.20888","title":"Video-As-Prompt: Unified Semantic Control for Video Generation","created":"2025-10-23","cited_by_count":14},{"id":"2510.25772","title":"VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning","created":"2025-10-29","cited_by_count":12},{"id":"2603.22883","title":"Group Editing: Edit Multiple Images in One Go","created":"2026-03-24","cited_by_count":11},{"id":"2504.13206","title":"DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization","created":"2025-04-15","cited_by_count":10},{"id":"2505.02192","title":"DualReal: Adaptive Joint Training for Lossless Identity-Motion Fusion in Video Customization","created":"2025-05-04","cited_by_count":10},{"id":"2512.12193","title":"SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation","created":"2025-12-13","cited_by_count":10},{"id":"2412.19853","title":"Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation","created":"2024-12-25","cited_by_count":9},{"id":"2507.04599","title":"QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation","created":"2025-07-07","cited_by_count":9},{"id":"2503.13576","title":"A Comprehensive Survey on Visual Concept Mining in Text-to-image Diffusion Models","created":"2025-03-17","cited_by_count":5},{"id":"2503.23951","title":"JointTuner: Appearance-Motion Adaptive Joint Training for Customized Video Generation","created":"2025-03-31","cited_by_count":5},{"id":"2505.20909","title":"Create Anything Anywhere: Layout-Controllable Personalized Diffusion Model for Multiple Subjects","created":"2025-05-27","cited_by_count":3},{"id":"2507.21529","title":"Chain-of-Cooking:Cooking Process Visualization via Bidirectional Chain-of-Thought Guidance","created":"2025-07-29","cited_by_count":3},{"id":"2604.24625","title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","created":"2026-04-27","cited_by_count":3}],"next_cursor":null}