{"total":74,"rows":[{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188,"area":"diffusion"},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158,"area":null},{"id":"2310.16436","title":"DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models","created":"2023-10-25","cited_by_count":128,"area":"lr"},{"id":"2401.04334","title":"Large Language Models for Robotics: Opportunities, Challenges, and Perspectives","created":"2024-01-09","cited_by_count":89,"area":"mllm"},{"id":"2312.07509","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","created":"2023-12-12","cited_by_count":76,"area":"wm"},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2405.13872","title":"Image-of-Thought Prompting for Visual Reasoning Refinement in Multimodal Large Language Models","created":"2024-05-22","cited_by_count":65,"area":"lr"},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61,"area":"diffusion"},{"id":"2511.23429","title":"Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model","created":"2025-11-28","cited_by_count":61,"area":"wm"},{"id":"2310.10769","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","created":"2023-10-16","cited_by_count":59,"area":"diffusion"},{"id":"2408.00760","title":"Smoothed Energy Guidance: Guiding Diffusion Models with Reduced Energy Curvature of Attention","created":"2024-08-01","cited_by_count":59,"area":"diffusion"},{"id":"2403.05131","title":"Sora as a World Model? A Complete Survey on Text-to-Video Generation","created":"2024-03-08","cited_by_count":53,"area":"wm"},{"id":"2312.15770","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","created":"2023-12-25","cited_by_count":51,"area":"diffusion"},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50,"area":"lr"},{"id":"2402.13185","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","created":"2024-02-20","cited_by_count":48,"area":null},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2406.08656","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","created":"2024-06-12","cited_by_count":43,"area":null},{"id":"2312.04086","title":"MEVG: Multi-event Video Generation with Text-to-Video Models","created":"2023-12-07","cited_by_count":40,"area":"diffusion"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2405.04682","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","created":"2024-05-07","cited_by_count":25,"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":"2405.12796","title":"DisenStudio: Customized Multi-subject Text-to-Video Generation with Disentangled Spatial Control","created":"2024-05-21","cited_by_count":20,"area":null},{"id":"2311.15813","title":"FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax","created":"2023-11-27","cited_by_count":19,"area":"diffusion"},{"id":"2409.00558","title":"Compositional 3D-aware Video Generation with LLM Director","created":"2024-08-31","cited_by_count":18,"area":"diffusion"},{"id":"2507.00162","title":"FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion","created":"2025-06-30","cited_by_count":17,"area":null},{"id":"2311.00990","title":"VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning on Language-Video Foundation Models","created":"2023-11-02","cited_by_count":16,"area":null},{"id":"2312.08548","title":"EVP: Enhanced Visual Perception using Inverse Multi-Attentive Feature Refinement and Regularized Image-Text Alignment","created":"2023-12-13","cited_by_count":14,"area":"diffusion"},{"id":"2507.07831","title":"Rethinking Query-based Transformer for Continual Image Segmentation","created":"2025-07-10","cited_by_count":14,"area":null},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","cited_by_count":11,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2404.11957","title":"The devil is in the object boundary: towards annotation-free instance segmentation using Foundation Models","created":"2024-04-18","cited_by_count":10,"area":null},{"id":"2510.20229","title":"Why LVLMs Are More Prone to Hallucinations in Longer Responses: The Role of Context","created":"2025-10-23","cited_by_count":10,"area":"mllm"},{"id":"2410.02130","title":"MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation","created":"2024-10-03","cited_by_count":9,"area":"diffusion"},{"id":"2411.01647","title":"Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation","created":"2024-11-03","cited_by_count":8,"area":"diffusion"},{"id":"2311.16635","title":"MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2412.18688","title":"Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation","created":"2024-12-24","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":"2412.14484","title":"Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2511.17254","title":"Intervene-All-Paths: Unified Mitigation of LVLM Hallucinations across Alignment Formats","created":"2025-11-21","cited_by_count":6,"area":"mllm"},{"id":"2406.08845","title":"Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality","created":"2024-06-13","cited_by_count":4,"area":null},{"id":"2501.16714","title":"Separate Motion from Appearance: Customizing Motion via Customizing Text-to-Video Diffusion Models","created":"2025-01-28","cited_by_count":4,"area":"diffusion"},{"id":"2508.13602","title":"PersonaVlog: Personalized Multimodal Vlog Generation with Multi-Agent Collaboration and Iterative Self-Correction","created":"2025-08-19","cited_by_count":4,"area":null},{"id":"2509.23867","title":"Sim-DETR: Unlock DETR for Temporal Sentence Grounding","created":"2025-09-28","cited_by_count":4,"area":null},{"id":"2510.17384","title":"Closed-Loop Transfer for Weakly-supervised Affordance Grounding","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2405.13951","title":"Text Prompting for Multi-Concept Video Customization by Autoregressive Generation","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2412.05279","title":"Perturb-and-Revise: Flexible 3D Editing with Generative Trajectories","created":"2024-12-06","cited_by_count":3,"area":"diffusion"},{"id":"2509.00760","title":"No More Sibling Rivalry: Debiasing Human-Object Interaction Detection","created":"2025-08-31","cited_by_count":3,"area":null},{"id":"2511.04317","title":"RISE-T2V: Rephrasing and Injecting Semantics with LLM for Expansive Text-to-Video Generation","created":"2025-11-06","cited_by_count":3,"area":"diffusion"},{"id":"2403.10133","title":"E4C: Enhance Editability for Text-Based Image Editing by Harnessing Efficient CLIP Guidance","created":"2024-03-15","cited_by_count":2,"area":"diffusion"},{"id":"2504.06861","title":"EIDT-V: Exploiting Intersections in Diffusion Trajectories for Model-Agnostic, Zero-Shot, Training-Free Text-to-Video Generation","created":"2025-04-09","cited_by_count":2,"area":"diffusion"},{"id":"2505.08239","title":"ACT-R: Adaptive Camera Trajectories for Single View 3D Reconstruction","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2506.23263","title":"Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis","created":"2025-06-29","cited_by_count":2,"area":"diffusion"},{"id":"2510.04999","title":"Bridging Text and Video Generation: A Survey","created":"2025-10-06","cited_by_count":2,"area":null},{"id":"2601.22094","title":"RefAny3D: 3D Asset-Referenced Diffusion Models for Image Generation","created":"2026-01-29","cited_by_count":2,"area":"diffusion"},{"id":"2603.11048","title":"COMIC: Agentic Sketch Comedy Generation","created":"2026-03-11","cited_by_count":2,"area":"agents"},{"id":"2402.15746","title":"Intelligent Director: An Automatic Framework for Dynamic Visual Composition using ChatGPT","created":"2024-02-24","cited_by_count":1,"area":null},{"id":"2503.00276","title":"Learning to Animate Images from A Few Videos to Portray Delicate Human Actions","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2507.10972","title":"Teach Me Sign: Stepwise Prompting LLM for Sign Language Production","created":"2025-07-15","cited_by_count":1,"area":"lr"},{"id":"2509.19690","title":"From Prompt to Progression: Taming Video Diffusion Models for Seamless Attribute Transition","created":"2025-09-24","cited_by_count":1,"area":"diffusion"},{"id":"2510.19622","title":"Augmenting Moment Retrieval: Zero-Dependency Two-Stage Learning","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2602.00028","title":"ELLMPEG: An Edge-based Agentic LLM Video Processing Tool","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2603.09104","title":"Training-free Motion Factorization for Compositional Video Generation","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2403.07198","title":"Action Reimagined: Text-to-Pose Video Editing for Dynamic Human Actions","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2503.21190","title":"Leveraging LLMs with Iterative Loop Structure for Enhanced Social Intelligence in Video Question Answering","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2504.02361","title":"MG-Gen: Single Image to Motion Graphics Generation","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2505.24253","title":"Interactive Video Generation via Domain Adaptation","created":"2025-05-30","cited_by_count":0,"area":"diffusion"},{"id":"2509.01277","title":"Communicative Agents for Slideshow Storytelling Video Generation based on LLMs","created":"2025-09-01","cited_by_count":0,"area":"agents"},{"id":"2510.24103","title":"Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2512.13690","title":"DiffusionBrowser: Interactive Diffusion Previews via Multi-Branch Decoders","created":"2025-12-15","cited_by_count":0,"area":"diffusion"},{"id":"2604.17749","title":"Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2608.16513","title":"MLLM-Guided Semantic Correction for Text-to-Video Generation","created":"2026-08-17","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}