{"total":206,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340,"area":null},{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212,"area":"diffusion"},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159,"area":null},{"id":"2312.10240","title":"Rich Human Feedback for Text-to-Image Generation","created":"2023-12-15","cited_by_count":141,"area":"diffusion"},{"id":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88,"area":"diffusion"},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87,"area":null},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83,"area":"diffusion"},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73,"area":"diffusion"},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61,"area":null},{"id":"2412.03859","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","created":"2024-12-05","cited_by_count":60,"area":"diffusion"},{"id":"2311.18830","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","created":"2023-11-30","cited_by_count":57,"area":"diffusion"},{"id":"2409.02426","title":"Breaking the Curse of Dimensionality: Diffusion Models Efficiently Learn Low-Dimensional Distributions","created":"2024-09-04","cited_by_count":53,"area":"diffusion"},{"id":"2312.00081","title":"Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding","created":"2023-11-30","cited_by_count":46,"area":"mllm"},{"id":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45,"area":null},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44,"area":"diffusion"},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44,"area":"diffusion"},{"id":"2501.16550","title":"PhysAnimator: Physics-Guided Generative Cartoon Animation","created":"2025-01-27","cited_by_count":42,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2409.04003","title":"DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes","created":"2024-09-06","cited_by_count":35,"area":"diffusion"},{"id":"2502.06805","title":"Efficient Diffusion Models: A Survey","created":"2025-02-03","cited_by_count":35,"area":"diffusion"},{"id":"2501.03931","title":"MagicMirror: ID-Preserved Video Generation in Video Diffusion Transformers","created":"2025-01-07","cited_by_count":34,"area":"diffusion"},{"id":"2403.09625","title":"Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2510.14973","title":"Attention Is All You Need for KV Cache in Diffusion LLMs","created":"2025-10-16","cited_by_count":32,"area":"inference"},{"id":"2403.17005","title":"TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models","created":"2024-03-25","cited_by_count":31,"area":"diffusion"},{"id":"2410.05227","title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","created":"2024-10-07","cited_by_count":31,"area":null},{"id":"2405.05538","title":"A Survey on Personalized Content Synthesis with Diffusion Models","created":"2024-05-09","cited_by_count":29,"area":"diffusion"},{"id":"2410.10122","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","created":"2024-10-14","cited_by_count":28,"area":null},{"id":"2411.00698","title":"Wasserstein Flow Matching: Generative modeling over families of distributions","created":"2024-11-01","cited_by_count":28,"area":"diffusion"},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2409.07452","title":"Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models","created":"2024-09-11","cited_by_count":27,"area":"diffusion"},{"id":"2407.08428","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2405.03025","title":"Matten: Video Generation with Mamba-Attention","created":"2024-05-05","cited_by_count":24,"area":"diffusion"},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2507.11245","title":"NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generation","created":"2025-07-15","cited_by_count":22,"area":null},{"id":"2406.06465","title":"AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction","created":"2024-06-10","cited_by_count":21,"area":"diffusion"},{"id":"2406.07754","title":"HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness","created":"2024-06-11","cited_by_count":21,"area":"diffusion"},{"id":"2410.16152","title":"Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models","created":"2024-10-21","cited_by_count":21,"area":"diffusion"},{"id":"2311.14768","title":"AdaDiff: Adaptive Step Selection for Fast Diffusion Models","created":"2023-11-24","cited_by_count":20,"area":"diffusion"},{"id":"2503.10704","title":"Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework","created":"2025-03-12","cited_by_count":20,"area":"diffusion"},{"id":"2508.10922","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","created":"2025-08-07","cited_by_count":20,"area":"mllm"},{"id":"2311.18837","title":"VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models","created":"2023-11-30","cited_by_count":19,"area":"diffusion"},{"id":"2406.14794","title":"ImageFlowNet: Forecasting Multiscale Image-Level Trajectories of Disease Progression with Irregularly-Sampled Longitudinal Medical Images","created":"2024-06-20","cited_by_count":19,"area":null},{"id":"2503.06564","title":"TR-DQ: Time-Rotation Diffusion Quantization","created":"2025-03-09","cited_by_count":19,"area":"diffusion"},{"id":"2504.09039","title":"Sculpting Memory: Multi-Concept Forgetting in Diffusion Models via Dynamic Mask and Concept-Aware Optimization","created":"2025-04-12","cited_by_count":19,"area":"diffusion"},{"id":"2506.04648","title":"FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion","created":"2025-06-05","cited_by_count":19,"area":"diffusion"},{"id":"2506.10540","title":"AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation","created":"2025-06-12","cited_by_count":19,"area":null},{"id":"2410.03160","title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","created":"2024-10-04","cited_by_count":18,"area":"diffusion"},{"id":"2412.04782","title":"A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges","created":"2024-12-06","cited_by_count":18,"area":null},{"id":"2412.03347","title":"DIVE: Taming DINO for Subject-Driven Video Editing","created":"2024-12-04","cited_by_count":17,"area":"diffusion"},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2412.11706","title":"AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration","created":"2024-12-16","cited_by_count":16,"area":"diffusion"},{"id":"2501.15167","title":"Enhancing Intent Understanding for Ambiguous prompt: A Human-Machine Co-Adaption Strategy","created":"2025-01-25","cited_by_count":16,"area":null},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","cited_by_count":15,"area":"alignment"},{"id":"2503.19462","title":"AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset","created":"2025-03-25","cited_by_count":15,"area":"diffusion"},{"id":"2511.08585","title":"Simulating the Visual World with Artificial Intelligence: A Roadmap","created":"2025-11-11","cited_by_count":15,"area":"wm"},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2507.15064","title":"StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation","created":"2025-07-20","cited_by_count":14,"area":"diffusion"},{"id":"2406.04253","title":"A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2501.01790","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","created":"2025-01-03","cited_by_count":13,"area":"diffusion"},{"id":"2508.10774","title":"BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation","created":"2025-08-14","cited_by_count":13,"area":"diffusion"},{"id":"2601.07823","title":"Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions","created":"2026-01-12","cited_by_count":13,"area":"wm"},{"id":"2503.16400","title":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","created":"2025-03-20","cited_by_count":12,"area":"diffusion"},{"id":"2506.05340","title":"Exploring Diffusion Transformer Designs via Grafting","created":"2025-06-05","cited_by_count":12,"area":"diffusion"},{"id":"2408.15241","title":"GenRec: Unifying Video Generation and Recognition with Diffusion Models","created":"2024-08-27","cited_by_count":11,"area":"diffusion"},{"id":"2405.14582","title":"PoseCrafter: One-Shot Personalized Video Synthesis Following Flexible Pose Control","created":"2024-05-23","cited_by_count":10,"area":null},{"id":"2505.12098","title":"LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation","created":"2025-05-17","cited_by_count":10,"area":"mllm"},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10,"area":null},{"id":"2507.07633","title":"T-GVC: Trajectory-Guided Generative Video Coding at Ultra-Low Bitrates","created":"2025-07-10","cited_by_count":10,"area":null},{"id":"2404.13680","title":"Zero-shot High-fidelity and Pose-controllable Character Animation","created":"2024-04-21","cited_by_count":9,"area":null},{"id":"2408.12601","title":"DreamCinema: Cinematic Transfer with Free Camera and 3D Character","created":"2024-08-22","cited_by_count":9,"area":null},{"id":"2411.04709","title":"TIP-I2V: A Million-Scale Real Text and Image Prompt Dataset for Image-to-Video Generation","created":"2024-11-05","cited_by_count":9,"area":null},{"id":"2412.09122","title":"LVMark: Robust Watermark for Latent Video Diffusion Models","created":"2024-12-12","cited_by_count":9,"area":"diffusion"},{"id":"2504.16907","title":"BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation","created":"2025-04-23","cited_by_count":9,"area":"safety"},{"id":"2506.18655","title":"RDPO: Real Data Preference Optimization for Physics Consistency Video Generation","created":"2025-06-23","cited_by_count":9,"area":"alignment"},{"id":"2508.18268","title":"SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulation","created":"2025-08-25","cited_by_count":9,"area":null},{"id":"2601.06162","title":"Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models","created":"2026-01-06","cited_by_count":9,"area":"diffusion"},{"id":"2501.01987","title":"Gender Bias in Text-to-Video Generation Models: A case study of Sora","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2502.17119","title":"Diffusion and Flow Matching Models for Tabular Data: A Survey","created":"2025-02-24","cited_by_count":8,"area":"diffusion"},{"id":"2504.13226","title":"Image Editing with Diffusion Models: A Survey","created":"2025-04-17","cited_by_count":8,"area":"diffusion"},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2401.14718","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","created":"2024-01-26","cited_by_count":7,"area":"wm"},{"id":"2410.17218","title":"Creativity in AI: Progresses and Challenges","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2503.14064","title":"AIGVE-Tool: AI-Generated Video Evaluation Toolkit with Multifaceted Benchmark","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2604.06339","title":"Evolution of Video Generative Foundations","created":"2026-04-07","cited_by_count":7,"area":"wm"},{"id":"2401.16224","title":"Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models","created":"2024-01-29","cited_by_count":6,"area":"diffusion"},{"id":"2409.07451","title":"FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising Process","created":"2024-09-11","cited_by_count":6,"area":"diffusion"},{"id":"2411.13609","title":"What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2507.07202","title":"A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2512.10286","title":"ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitions","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2604.18348","title":"AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation","created":"2026-04-20","cited_by_count":6,"area":"diffusion"},{"id":"2605.15855","title":"Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?","created":"2026-05-15","cited_by_count":6,"area":"diffusion"},{"id":"2403.10242","title":"GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting","created":"2024-03-15","cited_by_count":5,"area":"diffusion"},{"id":"2408.08315","title":"Segment Anything for Videos: A Systematic Survey","created":"2024-07-31","cited_by_count":5,"area":null},{"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,"area":"diffusion"},{"id":"2505.24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2508.03034","title":"MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention","created":"2025-08-05","cited_by_count":5,"area":"diffusion"}],"next_cursor":"100"}