{"total":83,"rows":[{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"id":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"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":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113,"area":"diffusion"},{"id":"2412.00596","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","created":"2024-11-30","cited_by_count":80,"area":"diffusion"},{"id":"2312.07509","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","created":"2023-12-12","cited_by_count":76,"area":"wm"},{"id":"2411.17491","title":"What's in the Image? A Deep-Dive into the Vision of Vision Language Models","created":"2024-11-26","cited_by_count":68,"area":"mllm"},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66,"area":null},{"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":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52,"area":"diffusion"},{"id":"2406.04277","title":"VideoTetris: Towards Compositional Text-to-Video Generation","created":"2024-06-06","cited_by_count":51,"area":"diffusion"},{"id":"2312.04483","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","created":"2023-12-07","cited_by_count":50,"area":"lr"},{"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":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40,"area":null},{"id":"2503.14350","title":"VEGGIE: Instructional Editing and Reasoning Video Concepts with Grounded Generation","created":"2025-03-18","cited_by_count":40,"area":"lr"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2404.00995","title":"PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation","created":"2024-04-01","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":"2503.21765","title":"Exploring the Evolution of Physics Cognition in Video Generation: A Survey","created":"2025-03-27","cited_by_count":31,"area":"diffusion"},{"id":"2404.01322","title":"A Review of Multi-Modal Large Language and Vision Models","created":"2024-03-28","cited_by_count":30,"area":null},{"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":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25,"area":"diffusion"},{"id":"2502.02747","title":"PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification","created":"2025-02-04","cited_by_count":22,"area":"agents"},{"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":"2409.00558","title":"Compositional 3D-aware Video Generation with LLM Director","created":"2024-08-31","cited_by_count":18,"area":"diffusion"},{"id":"2501.06173","title":"VideoAuteur: Towards Long Narrative Video Generation","created":"2025-01-10","cited_by_count":18,"area":null},{"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":"2412.05275","title":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","created":"2024-12-06","cited_by_count":17,"area":"diffusion"},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15,"area":"mllm"},{"id":"2501.07647","title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations","created":"2025-01-13","cited_by_count":15,"area":"diffusion"},{"id":"2412.05355","title":"MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance","created":"2024-12-06","cited_by_count":14,"area":"diffusion"},{"id":"2408.06926","title":"SceneGPT: A Language Model for 3D Scene Understanding","created":"2024-08-13","cited_by_count":12,"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":"2411.17041","title":"Free$^2$Guide: Training-Free Text-to-Video Alignment using Image LVLM","created":"2024-11-26","cited_by_count":9,"area":"diffusion"},{"id":"2504.08641","title":"Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization","created":"2025-04-11","cited_by_count":9,"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":"2411.16657","title":"DreamRunner: Fine-Grained Compositional Story-to-Video Generation with Retrieval-Augmented Motion Adaptation","created":"2024-11-25","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":"2502.19868","title":"C-Drag: Chain-of-Thought Driven Motion Controller for Video Generation","created":"2025-02-27","cited_by_count":6,"area":null},{"id":"2511.17450","title":"Planning with Sketch-Guided Verification for Physics-Aware Video Generation","created":"2025-11-21","cited_by_count":6,"area":null},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"id":"2601.17717","title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","created":"2026-01-25","cited_by_count":6,"area":"synth"},{"id":"2510.02226","title":"TempoControl: Temporal Attention Guidance for Text-to-Video Models","created":"2025-10-02","cited_by_count":5,"area":null},{"id":"2604.02330","title":"ActionParty: Multi-Subject Action Binding in Generative Video Games","created":"2026-04-02","cited_by_count":5,"area":"wm"},{"id":"2606.20799","title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","created":"2026-06-18","cited_by_count":5,"area":null},{"id":"2503.13500","title":"Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection","created":"2025-03-12","cited_by_count":4,"area":null},{"id":"2503.19351","title":"Multi-Object Sketch Animation by Scene Decomposition and Motion Planning","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2510.07940","title":"TTOM: Test-Time Optimization and Memorization for Compositional Video Generation","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2512.11464","title":"Exploring MLLM-Diffusion Information Transfer with MetaCanvas","created":"2025-12-12","cited_by_count":4,"area":"mllm"},{"id":"2605.11363","title":"PresentAgent-2: Towards Generalist Multimodal Presentation Agents","created":"2026-05-12","cited_by_count":4,"area":null},{"id":"2403.14947","title":"GPT-Connect: Interaction between Text-Driven Human Motion Generator and 3D Scenes in a Training-free Manner","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2409.11919","title":"LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension","created":"2024-09-18","cited_by_count":3,"area":"mllm"},{"id":"2409.15259","title":"StarVid: Enhancing Semantic Alignment in Video Diffusion Models via Spatial and SynTactic Guided Attention Refocusing","created":"2024-09-23","cited_by_count":3,"area":"diffusion"},{"id":"2412.18966","title":"ModelGrow: Continual Text-to-Video Pre-training with Model Expansion and Language Understanding Enhancement","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2407.12579","title":"The Fabrication of Reality and Fantasy: Scene Generation with LLM-Assisted Prompt Interpretation","created":"2024-07-17","cited_by_count":2,"area":"diffusion"},{"id":"2503.06119","title":"Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2603.06533","title":"NEGATE: Constrained Semantic Guidance for Linguistic Negation in Text-to-Video Diffusion","created":"2026-03-06","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":"2604.07348","title":"MoRight: Motion Control Done Right","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2312.00651","title":"TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models","created":"2023-12-01","cited_by_count":1,"area":"wm"},{"id":"2405.15267","title":"Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor","created":"2024-05-24","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":"2503.11790","title":"Visualizing Thought: Conceptual Diagrams Enable Robust Planning in LMMs","created":"2025-03-14","cited_by_count":1,"area":"lr"},{"id":"2504.03235","title":"Enhancing Traffic Incident Response through Sub-Second Temporal Localization with HybridMamba","created":"2025-04-04","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":"2510.00806","title":"From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2511.08416","title":"Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications","created":"2025-11-11","cited_by_count":1,"area":"diffusion"},{"id":"2601.14602","title":"3D Space as a Scratchpad for Editable Text-to-Image Generation","created":"2026-01-21","cited_by_count":1,"area":"lr"},{"id":"2603.09104","title":"Training-free Motion Factorization for Compositional Video Generation","created":"2026-03-10","cited_by_count":1,"area":null},{"id":"2605.06512","title":"DCR: Counterfactual Attractor Guidance for Rare Compositional Generation","created":"2026-05-07","cited_by_count":1,"area":"diffusion"},{"id":"2609.13006","title":"Physics-Aware Video Generation via Agentic Planning and Graph-Guided Optimization","created":"2026-07-16","cited_by_count":1,"area":"diffusion"},{"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":"2504.02361","title":"MG-Gen: Single Image to Motion Graphics Generation","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2602.22745","title":"SPATIALALIGN: Aligning Dynamic Spatial Relationships in Video Generation","created":"2026-02-26","cited_by_count":0,"area":"alignment"},{"id":"2603.19672","title":"Making Video Models Adhere to User Intent with Minor Adjustments","created":"2026-03-20","cited_by_count":0,"area":"diffusion"},{"id":"2603.22091","title":"P-Flow: Prompting Visual Effects Generation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2606.27741","title":"SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models","created":"2026-06-26","cited_by_count":0,"area":"diffusion"},{"id":"2608.13037","title":"Spatially-Grounded Text-to-Video Generation via Inference-Time Gradient-Free Optimization","created":"2026-08-13","cited_by_count":0,"area":"diffusion"},{"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}