{"total":51,"rows":[{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158,"area":null},{"id":"2410.07718","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","created":"2024-10-10","cited_by_count":97,"area":"diffusion"},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73,"area":"diffusion"},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73,"area":null},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2408.17065","title":"Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning","created":"2024-08-30","cited_by_count":59,"area":null},{"id":"2411.17459","title":"WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model","created":"2024-11-26","cited_by_count":57,"area":"diffusion"},{"id":"2509.22799","title":"VideoScore2: Think before You Score in Generative Video Evaluation","created":"2025-09-26","cited_by_count":40,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2411.10836","title":"AnimateAnything: Consistent and Controllable Animation for Video Generation","created":"2024-11-16","cited_by_count":35,"area":null},{"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":"2409.01199","title":"OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model","created":"2024-09-02","cited_by_count":30,"area":"diffusion"},{"id":"2406.07966","title":"Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network","created":"2024-06-12","cited_by_count":26,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2508.10858","title":"Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation","created":"2025-08-14","cited_by_count":21,"area":"alignment"},{"id":"2502.14801","title":"AVD2: Accident Video Diffusion for Accident Video Description","created":"2025-02-20","cited_by_count":20,"area":null},{"id":"2503.10391","title":"CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance","created":"2025-03-13","cited_by_count":19,"area":"diffusion"},{"id":"2412.00397","title":"DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses","created":"2024-11-30","cited_by_count":17,"area":"diffusion"},{"id":"2412.04440","title":"GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration","created":"2024-12-05","cited_by_count":17,"area":"agents"},{"id":"2501.01790","title":"Ingredients: Blending Custom Photos with Video Diffusion Transformers","created":"2025-01-03","cited_by_count":13,"area":"diffusion"},{"id":"2505.18650","title":"ProphetDWM: A Driving World Model for Rolling Out Future Actions and Videos","created":"2025-05-24","cited_by_count":11,"area":"wm"},{"id":"2511.01775","title":"How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment","created":"2025-11-03","cited_by_count":11,"area":"wm"},{"id":"2407.12581","title":"Towards Understanding Unsafe Video Generation","created":"2024-07-17","cited_by_count":10,"area":null},{"id":"2410.05255","title":"Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization","created":"2024-10-07","cited_by_count":9,"area":"diffusion"},{"id":"2411.16619","title":"Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2406.15829","title":"MVOC: a training-free multiple video object composition method with diffusion models","created":"2024-06-22","cited_by_count":8,"area":"diffusion"},{"id":"2509.01362","title":"Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement","created":"2025-09-01","cited_by_count":8,"area":null},{"id":"2503.14941","title":"UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation","created":"2025-03-19","cited_by_count":7,"area":"mllm"},{"id":"2508.09912","title":"E-4DGS: High-Fidelity Dynamic Reconstruction from the Multi-view Event Cameras","created":"2025-08-13","cited_by_count":7,"area":null},{"id":"2506.23729","title":"Proteus-ID: ID-Consistent and Motion-Coherent Video Customization","created":"2025-06-30","cited_by_count":6,"area":null},{"id":"2603.26285","title":"PhysVid: Physics Aware Local Conditioning for Generative Video Models","created":"2026-03-27","cited_by_count":6,"area":null},{"id":"2509.25187","title":"FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2406.09181","title":"A Large-scale Universal Evaluation Benchmark For Face Forgery Detection","created":"2024-06-13","cited_by_count":3,"area":null},{"id":"2411.10867","title":"ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models","created":"2024-11-16","cited_by_count":3,"area":"mllm"},{"id":"2505.04347","title":"CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion","created":"2025-05-07","cited_by_count":3,"area":"diffusion"},{"id":"2508.07246","title":"Consistent and Controllable Image Animation with Motion Linear Diffusion Transformers","created":"2025-08-10","cited_by_count":3,"area":"diffusion"},{"id":"2607.16742","title":"Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model","created":"2026-07-18","cited_by_count":2,"area":"moe"},{"id":"2409.17093","title":"BitQ: Tailoring Block Floating Point Precision for Improved DNN Efficiency on Resource-Constrained Devices","created":"2024-09-25","cited_by_count":1,"area":null},{"id":"2503.14501","title":"Advances in 4D Generation: A Survey","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2601.07287","title":"Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models","created":"2026-01-12","cited_by_count":1,"area":"diffusion"},{"id":"2410.05804","title":"CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection","created":"2024-10-08","cited_by_count":0,"area":"mllm"},{"id":"2503.09154","title":"SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2503.14428","title":"Comp-Attn: Present-and-Align Attention for Compositional Video Generation","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2505.07477","title":"You Only Look One Step: Accelerating Backpropagation in Diffusion Sampling with Gradient Shortcuts","created":"2025-05-12","cited_by_count":0,"area":"diffusion"},{"id":"2512.02273","title":"Progressive Image Restoration via Text-Conditioned Video Generation","created":"2025-12-01","cited_by_count":0,"area":null},{"id":"2602.01340","title":"MTC-VAE: Multi-Level Temporal Compression with Content Awareness","created":"2026-02-01","cited_by_count":0,"area":"diffusion"},{"id":"2608.20749","title":"Identity-Preserving Text-to-Video Generation via Agentic Enhancement and Semantic Repair","created":"2026-08-21","cited_by_count":0,"area":"agents"},{"id":"2609.36832","title":"Motion Concept Unlearning in Video Diffusion Models","created":"2026-09-29","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}